For decades visual field defects were considered irreversible because it was thought that in the visual system the regeneration potential of the neuronal tissues is low.Nevertheless,there is always some potential for ...For decades visual field defects were considered irreversible because it was thought that in the visual system the regeneration potential of the neuronal tissues is low.Nevertheless,there is always some potential for partial recovery of the visual field defect that can be achieved through induction of neuroplasticity.Neuroplasticity refers to the ability of the brain to change its own functional architecture by modulating synaptic efficacy.It is maintained throughout life and just as neurological rehabilitation can improve motor coordination,visual field defects in glaucoma,diabetic retinopathy or optic neuropathy can be improved by inducing neuroplasticity.In ophthalmology many new treatment paradigms have been tested that can induce neuroplastic changes,including non-invasive alternating current stimulation.Treatment with alternating current stimulation(e.g.,30 minutes,daily for 10 days using transorbital electrodes and^10 Hz)activates the entire retina and parts of the brain.Electroencephalography and functional magnetic resonance imaging studies revealed local activation of the visual cortex,global reorganization of functional brain networks,and enhanced blood flow,which together activate neurons and their networks.The future of low vision is optimistic because vision loss is indeed,partially reversible.展开更多
AIM:To adapt the low vision-related quality of life(LVQOL) instrument into Turkish language and to assess its validity and reliability.METHODS:The study was conducted in 387 patients attending the Centre of Low Vision...AIM:To adapt the low vision-related quality of life(LVQOL) instrument into Turkish language and to assess its validity and reliability.METHODS:The study was conducted in 387 patients attending the Centre of Low Vision Rehabilitation,Faculty of Medicine,Ankara University.For statistical analyses,the Spearman's correlation coefficient,Cronbach's alpha coefficient and Confirmatory Factor Analysis(CFA) were used.RESULTS:According to results of CFA,the item in the 'Adjustment' subscale because of having the factor loading below 0.40,was excluded from the questionnaire.The reliability of the questionnaire was assessed according to Cronbach's alpha coefficients.The reliability of the 'Distance Vision,Mobility,and Lighting' subscale was ?琢=0.863;of the 'Adjustment' subscale was ?琢=0.694;'Reading and Fine Work' was ?琢=0.791,and 'Activities of Daily Living' was ?琢= 0.770.So these results indicate that the questionnaire is reliable to measure the vision related quality of life of low-vision patients.The correlations between the subscales were also analyzed,and the correlation between 'Adjustment' and 'Reading and Fine Work' was found to be the lowest(rs=0.336,P <0.001),whereas the strongest correlation was found between the 'Reading and Fine Work',and 'Activities of Daily Living'.Additionally,the 'Adjustment' dimension showed the strongest correlation with only 'Distance Vision,Mobility,and Lighting' dimension.CONCLUSION:After removing the last item in the second dimension,the Turkish adaptation of all dimensions of the LVQOL has been shown to be reliable,valid and suitable for use in patients with low vision in Turkey.展开更多
AIM:To evaluate the effectiveness of Grand Seiko Ref/Keratometer WAM-5500 compared to Topcon KR800 autorefractor in detecting refractive error in large scale vision screening for Chinese school age children with the W...AIM:To evaluate the effectiveness of Grand Seiko Ref/Keratometer WAM-5500 compared to Topcon KR800 autorefractor in detecting refractive error in large scale vision screening for Chinese school age children with the WHO criteria.METHODS:A total of 886 participants were enrolled with mean age of 9.49±1.88 y from Tianjin,China.Spherical equivalent(SE)was obtained from un-cycloplegic autorefraction and cycloplegic autorefraction.Topcon KR 800(Topcon)and Grand Seiko WAM-5500(WAM)autorefractors were used.Bland-Altman Plot and regression were generated to compare their performance.The overall effectiveness of detecting early stage refractive error was analyzed with receiver operating characteristic(ROC)curves.RESULTS:The mean SE was-0.98±1.81 diopter(D)and the prevalence of myopia was 48.9%defined by WHO criteria according to the result of cycloplegic autorefraction.The mean SE of un-cycloplegic autorefraction with Topcon and WAM were-1.21±1.65 and-1.20±1.68 D respectively.There was a strong linear agreement between result obtained from WAM and cycloplegic autorefraction with an R2 of 0.8318.Bland-Altman plot indicated a moderate agreement of cylinder values between the two methods.The sensitivity and specificity for detecting hyperopia were 90.52%and 83.51%;for detecting myopia were 95.60%and 90.24%;for detecting astigmatism were 79.40%and 90.21%;for detecting high myopia were 98.16%and 98.91%respectively.CONCLUSION:These findings suggest that both Grand Seiko and Topcon autorefractor can be used in large-scale vision screening for detecting refractive error in Chinese population.Grand Seiko gives relatively better performance in detecting myopia,hyperopia,and high myopia for school age children.展开更多
AIM: To investigate the one-year refractive outcomes and optical quality following PRESBYOND laser-blended vision(LBV).METHODS: This retrospective study included 20 patients who underwent PRESBYOND treatment between J...AIM: To investigate the one-year refractive outcomes and optical quality following PRESBYOND laser-blended vision(LBV).METHODS: This retrospective study included 20 patients who underwent PRESBYOND treatment between Jan 2019 and Aug 2020. The patients were asked to attend a followup outpatient visit one year after surgery. Distance and near visual acuity as well as subjective refraction were examined. Optical quality was assessed using wavefront-supported custom ablation. A questionnaire evaluating optical quality and satisfaction was completed at the last visit.RESULTS: The average patient age was 48.1±7.4 y(range, 41 to 58 y). The mean preoperative spherical equivalent was-7.59±2.39D. At the one-year follow-up, two eyes(both dominant eyes) lost one line of corrected distance visual acuity(CDVA), while the remaining eyes(38/40) maintained or gained lines of CDVA. The average binocular uncorrected distance visual acuity improved from 0.15±0.03 to 0.90±0.26(decimal vision;P<0.001). The average binocular uncorrected near visual acuity increased from 0.34±0.28 to 0.97±0.07(P<0.001). The spherical aberration was 0.04±0.06 μm in the nondominant eye and 0.09±0.09 μm in the dominant eye(P=0.02). All patients were satisfied with or accepted the outcomes of the surgery. The primary complaints were related to disturbances in night vision and relatively inferior near vision.CONCLUSION: Over the one-year observation period, PRESBYOND is a safe and effective option for presbyopia correction. The optical quality and near vision deserve further investigation.展开更多
The occurrence of geological disasters can have a large impact on urban safety. Protecting people’s safety is the most important concern when disasters occur. Safety improvement requires a large amount of comprehensi...The occurrence of geological disasters can have a large impact on urban safety. Protecting people’s safety is the most important concern when disasters occur. Safety improvement requires a large amount of comprehensive and representative risk analysis and a large collection of information related to geological hazards, including unstructured knowledge and experience. To address the relevant information and support safety risk analysis, a geological hazard knowledge graph is developed automatically based on computer vision and domain-geoscience ontology to identify geological hazards from input images while obeying safety rules and regulations, even when affected by changes. In the implementation of the knowledge graph, we design an ontology schema of geological disasters based on a top-down approach, and by organizing knowledge as a logical semantic expression, it can be shared using ontology technologies and therefore enable semantic interoperability. Computer vision approaches are then used to automatically detect a set of entities and attributes, using the data from input images, and object types and their attributes are identified so that they can be stored in Neo4j for reasoning and searching. Finally, a reasoning model for geological hazard identification was developed using the Neo4j database to create nodes, relationships, and their properties for modeling, and geological hazards in the images can be automatically identified by searching the Neo4j database. An application on geological hazard is presented. The results show the effectiveness of the proposed approach in terms of identifying possible potential hazards in geological hazards and assisting in formulating targeted preventive measures.展开更多
AIM:To compare and analyse the diagnostic efficacy of the College of Optometrists Vision Development Quality of Life Questionnaire(COVD-QOL)and the Convergence Insufficiency Symptom Survey(CISS)in detecting convergenc...AIM:To compare and analyse the diagnostic efficacy of the College of Optometrists Vision Development Quality of Life Questionnaire(COVD-QOL)and the Convergence Insufficiency Symptom Survey(CISS)in detecting convergence insufficiency and to compare their diagnostic value in clinical applications.METHODS:Using the diagnostic test method,62 adult patients with convergence insufficiency(age:24.74±3.75y)and 62 normal participants(age:23.61±3.13y)who visited the Optometry Clinic of West China Hospital of Sichuan University from April 2021 to January 2023 were included.All subjects completed the CISS and COVD-QOL.Statistical analysis of the sensitivity and specificity of the CISS and COVD-QOL and comparison and joint experimental analysis of their diagnostic efficacy were performed.RESULTS:The sensitivity of the CISS and COVD-QOL for convergence insufficiency was 64.5%and 71.0%,respectively,while the specificity was 96.8%and 67.7%,respectively.Compared to the CISS alone,the combination of the CISS and COVD-QOL demonstrated lower sensitivity and specificity.The areas under the receiver operating characteristic curve of CISS,COVD-QOL and CISS combined with COVD-QOL were 0.806,0.694 and 0.782,respectively.CONCLUSION:Considering the low sensitivity of the CISS and the low specificity of the COVD-QOL,it is recommended to supplement these questionnaires with other screening tests for the detection of convergence insufficiency.展开更多
Background:Stereoscopic Vision uses the disparity between the two images received by the two eyes in order to create a tridimensional representation.With this study,we aimed at providing an estimate of binocular visio...Background:Stereoscopic Vision uses the disparity between the two images received by the two eyes in order to create a tridimensional representation.With this study,we aimed at providing an estimate of binocular vision at a level prior to disparity processing.In particular,we wanted to assess the spatial properties of the visual system for detecting interocular correlations(IOC).Methods:We developed dichoptic stimuli,made of textures which IOC is sinusoidally modulated at various correlation spatial frequencies.Then,we compared the sensitivity to these stimuli to the sensitivity to analogous stimuli with disparity modulation.Results:We observed that IOC sensitivity presents a low-pass/band-pass profile and increases as a function of presentation duration and contrast,in a similar way as disparity sensitivity.Conclusions:IOC sensitivity is weakly-though significantly-correlated with disparity sensitivity in the general population,which suggests that it could provide a marker for binocular vision,prior to disparity processing.展开更多
Background:We investigate whether changes in visual plasticity induced by monocular deprivation can be maintained across multiple days.It has been known that monocular deprivation strengthens the deprived eye in adult...Background:We investigate whether changes in visual plasticity induced by monocular deprivation can be maintained across multiple days.It has been known that monocular deprivation strengthens the deprived eye in adults with normal vision for a short period of time(30-60 minutes).This has been shown through a variety of visual tasks such as binocular combination and rivalry.Methods:Ten subjects were recruited and patched for five consecutive days for two hours.We used a binocular phase combination task to measure the subjects’sensory eye balances.We initially measured their baseline of sensory eye balance,patched their dominant eye,and then conducted post-patching measurements at 0,3,6,12,24 and 48 minutes after patching.Results:We performed a 2-way ANOVA(Before vs.after patching×Day);we found that although the effect of monocular deprivation on the deprived eye was significant,F(1,9)=17.32,P=0.002,the effect of Day was not.Conclusions:Hence we found no accumulation of the patching effect across five days in healthy adults.This suggests that the degree of remnant neural plasticity in adult primary visual cortex may be too limited to be exploited therapeutically.展开更多
AIM:To determine the association between distance and near visual acuity(VA)and cognitive function among older adults in Selangor,Malaysia.METHODS:A total of 230 older adults(age≥60y)participated in this study.Habitu...AIM:To determine the association between distance and near visual acuity(VA)and cognitive function among older adults in Selangor,Malaysia.METHODS:A total of 230 older adults(age≥60y)participated in this study.Habitual distance and near VA were measured using the Early Treatment Diabetic Retinopathy Study Chart and Lighthouse Near Visual Acuity Chart,respectively.Global cognitive function was assessed using the Mini-Mental State Examination(M-MSE)and the Malay language version of the Montreal Cognitive Assessment(M-MoCA).Digit Symbol(DS)subtest was used to measure information processing.RESULTS:No significant association was observed between vision and M-MSE and M-MoCA scores.However,poor distance and near VA were found to be significantly associated with low DS scores[distance VA:β=-0.01,R2=0.1,P=0.02;odds ratio(OR)=2.84,95%confidence interval(CI),1.10-7.33,P=0.03;near VA:β=-0.05,R2=0.08,P=0.00;OR=3.32,95%CI,1.28-8.59,P=0.01].CONCLUSION:Poor vision is associated with a decline in information processing in older adults and substantiates the importance of preserving good vision in maintaining cognitive function.展开更多
Architecture and the city are two major constituents of human development which, today more than ever, have to be present in the long-term. The Year of France in China is, for the first time, the occasion to present t...Architecture and the city are two major constituents of human development which, today more than ever, have to be present in the long-term. The Year of France in China is, for the first time, the occasion to present to the Chinese public a vision of the contemporary French architectural production, not only in France but also in China.展开更多
AIM:To evaluate clinical outcomes following implantation of an extended range of vision intraocular lens(IOL),the ZXR00,and a diffractive multifocal IOL with+2.75 diopters(D)add power,the ZKB00.METHODS:Totally 30 pati...AIM:To evaluate clinical outcomes following implantation of an extended range of vision intraocular lens(IOL),the ZXR00,and a diffractive multifocal IOL with+2.75 diopters(D)add power,the ZKB00.METHODS:Totally 30 patients who underwent either bilateral implantation of the ZXR00 IOL with intended emmetropia(ZXR00 emmetropia group:20 eyes)and intended micromonovision(ZXR00 monovision group:20 eyes),or bilateral implantation of the ZKB00 IOL with intended emmetropia(ZKB00 group:20 eyes)were included in this study.Visual acuity at 4 m,80,and 40 cm;and the types of halos(misty,fine,and rainbow)were analyzed at one and three months after surgery.RESULTS:There were no significant differences in distance visual acuity among the three groups.The mean uncorrected intermediate visual acuity was better in the ZXR00 emmetropia and monovision groups(0.02 logMAR and 0.02 logMAR,respectively)than in the ZKB00 group(0.14 logMAR).The mean uncorrected near visual acuity was worse in the ZXR00 emmetropia group(0.26 logMAR)than in the ZXR00 monovision and ZKB00 groups(0.12 logMAR and 0.10 logMAR,respectively).There was an increased incidence of rainbow halos in the ZKB00 group vs in either ZXR00 group(P=0.033).CONCLUSION:Implantation of the ZXR00 IOL with intended micromonovision provide superior visual acuity than implantation of the ZXR00 IOL with intended emmetropia.The ZXR00 IOLs tend to show a lower incidence of rainbow halos than did the ZKB00 IOL.展开更多
With the increasing intensive and large-scale development of the sika deer breeding industry,it is crucial to assess the health status of the sika deer by monitoring their behaviours.A machine vision-based method for ...With the increasing intensive and large-scale development of the sika deer breeding industry,it is crucial to assess the health status of the sika deer by monitoring their behaviours.A machine vision-based method for the behaviour recognition of sika deer is proposed in this paper.Google Inception Net(GoogLeNet)is used to optimise the model in this paper.First,the number of layers and size of the model were reduced.Then,the 5×5 convolution was changed to two 3×3 convolutions,which reduced the parameters and increased the nonlinearity of the model.A 5×5 convolution kernel was used to replace the original convolution for extracting coarse-grained features and improving the model’s extraction ability.A multi-scale module was added to the model to enhance the multi-faceted feature extraction capability of the model.Simultaneously,the Squeeze-and-Excitation Networks(SE-Net)module was included to increase the channel’s attention and improve the model’s accuracy.The dataset’s images were rotated to reduce overfitting.For image rotation,the angle wasmultiplied by 30°to obtain the dataset enhanced by rotation operations of 30°,60°,90°,120°and 150°.The experimental results showed that the recognition rate of this model in the behaviour of sika deer was 98.92%.Therefore,the model presented in this paper can be applied to the behaviour recognition of sika deer.The results will play an essential role in promoting animal behaviour recognition technology and animal health monitoring management.展开更多
The quantum yield formula for uniform-doping GaAIAs/GaAs transmission-mode photocathodes is revised by taking into account the light absorption in the window layer.By using the revised quantum yield formula,the domest...The quantum yield formula for uniform-doping GaAIAs/GaAs transmission-mode photocathodes is revised by taking into account the light absorption in the window layer.By using the revised quantum yield formula,the domestic and ITT's experimental quantum yield curves are fitted and the fitted curves match well with the experimental curves.In addition,the fit results show that the integral sensitivity and quantum yield of domestic image intensifier tube has achieved 2130μA/lm and 45%,nearly reaching ITT's third generation level in 2002,whereas the discrepancy in cathode performance is mainly embodied in the electron diffusion length and back interface recombination velocity.展开更多
Background:In situations where one eye gives a more blurred input to visual processing than the other,the input from the sharper eye tends to dominate the percept.This phenomenon has clinical relevance for monovision ...Background:In situations where one eye gives a more blurred input to visual processing than the other,the input from the sharper eye tends to dominate the percept.This phenomenon has clinical relevance for monovision treatment,where the two eyes are corrected separately for different distances.We performed a psychophysical investigation of subjects’ability to identify which of a set of images was blurred in one eye.Methods:We tested 17 subjects with normal or corrected-to-normal vision.On each trial,subjects viewed an array of four pictures using a monitor with shutter goggles.In the first experiment,three of the pictures were sharp in both eyes(distractors).The fourth picture was sharp in one eye and blurred by a low-pass filter in the other.Subjects identified that odd-one-out target over many trials with different degrees of blur.In the second experiment the target picture was given the same treatment,but the three non-target pictures were made monocular(sharp in one eye,mean grey in the other).Results:The results from the first experiment with binocular distractors followed our expectations,with subjects showing better performance at detecting more severe blurs.In the second experiment with monocular distractors,we found large individual differences between our observers.Some performed the same as they did in the first condition,others now found the task impossible,and a few performed worse with severe blurs than they did with slight blurs.Conclusions:Previous studies have reported individual differences in blur suppression,however this study reveals that these differences may depend on the precise details of the judgements being made.展开更多
Background:This study evaluated the VIsion PERformance(VIPER)simulator’s ability to assess the functional visual performance in warfighters conducting civilian and military tasks.Methods:Thirty service members,aged 2...Background:This study evaluated the VIsion PERformance(VIPER)simulator’s ability to assess the functional visual performance in warfighters conducting civilian and military tasks.Methods:Thirty service members,aged 25–35 years old with a best corrected distance visual acuity(VA)better than or equal to 20/20 or logarithm of the minimum angle of resolution(logMAR)0.00,were randomized to locate and identify road signs and mock improvised explosive devices(IEDs)under either daytime conditions or with infrared imagery,with(cc)and without(sc)wearing their habitual correction.Participants also underwent binocular uncorrected(UDVA)and corrected(CDVA)visual assessment,refraction,contrast sensitivity testing and wavefront aberrometry.Results:The mean age was 28.47 years.The manifest spherical equivalent was–3.16±1.75 diopters(D),the UDVA in both eyes(OU)was logMAR 0.83±0.47,and the CDVA OU was–0.11±0.06.For VIPER,the mean difference in the detection distance(DD)for road signs ccDD vs.scDD was(76.7±52.8)m(P<0.001).The average difference in identification distance(ID)ccID vs.scID was(13.9±6.3)m(P<0.001).The mean accuracies were 83.5%and 27.9%for cc and sc,respectively(P<0.001).The regression analysis indicated that a 1.6 m change in the distance accounts for a 1%change in the accuracy(P=0.002).Without correction,a 4.1 m change accounts for a 1%change in the accuracy(P<0.001).The average IED ccDD was(29.9±8.2)m,and that for scDD was(13.2±13.6)m(P<0.001).The average IED ccID was(32.2±6.2)m and that for the scID was(7.4±10.3)m(P<0.001).The mean IED identification accuracy was 46.7 and 11.4%for cc and sc,respectively(P<0.001).Conclusions:The preliminary results reflect VIPER’s ability to assess functional visual performance when detecting and identifying signs and IEDs.Furthermore,VIPER is able to detect performance changes with and without correction.展开更多
This paper presents an efficient robot calibration method with non-contact vision metrology. Using the coplanar pattern to calibrate camera made the active-vision-based end-effector pose measurement be a feasible and ...This paper presents an efficient robot calibration method with non-contact vision metrology. Using the coplanar pattern to calibrate camera made the active-vision-based end-effector pose measurement be a feasible and costeffective way. Kinematic parameter errors were linearized and identified through two-step procedure, thus the singular and non-linear condition was overcome. These errors were then compensated using inverse model method. The whole calibration process is flexible, easy to implement and prevents the error propagation from the earlier stages to the later ones. Calibration was performed on MOTOMAN SV3industrial robot. Experiment results show that the proposed method is easy to setup and with satisfactory accuracy.展开更多
Background:Vision and vision-language foundation models,a subset of advanced artificial intelligence(AI)frameworks,have shown transformative potential in various medical fields.In ophthalmology,these models,particular...Background:Vision and vision-language foundation models,a subset of advanced artificial intelligence(AI)frameworks,have shown transformative potential in various medical fields.In ophthalmology,these models,particularly large language models and vision-based models,have demonstrated great potential to improve diagnostic accuracy,enhance treatment planning,and streamline clinical workflows.However,their deployment in ophthalmology has faced several challenges,particularly regarding generalizability and integration into clinical practice.This systematic review aims to summarize the current evidence on the use of vision and visionlanguage foundation models in ophthalmology,identifying key applications,outcomes,and challenges.Main text:A comprehensive search on PubMed,Web of Science,Scopus,and Google Scholar was conducted to identify studies published between January 2020 and July 2025.Studies were included if they developed or applied foundation models,such as vision-based models and large language models,to clinically relevant ophthalmic applications.A total of 10 studies met the inclusion criteria,covering areas such as retinal diseases,glaucoma,and ocular surface tumor.The primary outcome measures are model performance metrics,integration into clinical workflows,and the clinical utility of the models.Additionally,the review explored the limitations of foundation models,such as the reliance on large datasets,computational resources,and interpretability challenges.The majority of studies demonstrated that foundation models could achieve high diagnostic accuracy,with several reports indicating excellent performance comparable to or exceeding those of experienced clinicians.Foundation models achieved high accuracy rates up to 95%for diagnosing retinal diseases,and similar performances for detecting glaucoma progression.Despite promising results,concerns about algorithmic bias,overfitting,and the need for diverse training data were common.High computational demands,EHR compatibility,and the need for clinician validation also posed challenges.Additionally,model interpretability issues hindered clinician trust and adoption.Conclusions:Vision and vision-language foundation models in ophthalmology show significant potential for advancing diagnostic accuracy and treatment strategies,particularly in retinal diseases,glaucoma,and ocular oncology.However,challenges such as data quality,transparency,and ethical considerations must be addressed.Future research should focus on refining model performance,improving interpretability and generalizability,and exploring strategies for integrating these models into routine clinical practice to maximize their impact in clinical ophthalmology.展开更多
Earthwork productivity analysis is essential for successful construction projects.If productivity analysis results can be accessed anytime and anywhere,then project management can be performed more efficiently.To this...Earthwork productivity analysis is essential for successful construction projects.If productivity analysis results can be accessed anytime and anywhere,then project management can be performed more efficiently.To this end,this paper proposes an earthwork productivity monitoring framework via a real-time scene updating multi-vision platform.The framework consists of four main processes:1)site-optimized database development;2)real-time monitoring model updating;3)multi-vision productivity monitoring;and 4)web-based monitoring platform for Internetconnected devices.The experimental results demonstrated satisfactory performance,with an average macro F1-score of 87.3%for continuous site-specific monitoring,an average accuracy of 86.2%for activity recognition,and the successful operation of multi-vision productivity monitoring through a web-based platform in real time.The findings can contribute to supporting site managers to understand real-time earthmoving operations while achieving better construction project and information management.展开更多
The increase in precision agriculture has promoted the development of picking robot technology,and the visual recognition system at its core is crucial for improving the level of agricultural automation.This paper rev...The increase in precision agriculture has promoted the development of picking robot technology,and the visual recognition system at its core is crucial for improving the level of agricultural automation.This paper reviews the progress of visual recognition tech-nology for picking robots,including image capture technology,target detection algorithms,spatial positioning strategies and scene un-derstanding.This article begins with a description of the basic structure and function of the vision system of the picking robot and em-phasizes the importance of achieving high-efficiency and high-accuracy recognition in the natural agricultural environment.Sub-sequently,various image processing techniques and vision algorithms,including color image analysis,three-dimensional depth percep-tion,and automatic object recognition technology that integrates machine learning and deep learning algorithms,were analysed.At the same time,the paper also highlights the challenges of existing technologies in dynamic lighting,occlusion problems,fruit maturity di-versity,and real-time processing capabilities.This paper further discusses multisensor information fusion technology and discusses methods for combining visual recognition with a robot control system to improve the accuracy and working rate of picking.At the same time,this paper also introduces innovative research,such as the application of convolutional neural networks(CNNs)for accurate fruit detection and the development of event-based vision systems to improve the response speed of the system.At the end of this paper,the future development of visual recognition technology for picking robots is predicted,and new research trends are proposed,including the refinement of algorithms,hardware innovation,and the adaptability of technology to different agricultural conditions.The purpose of this paper is to provide a comprehensive analysis of visual recognition technology for researchers and practitioners in the field of agricul-tural robotics,including current achievements,existing challenges and future development prospects.展开更多
文摘For decades visual field defects were considered irreversible because it was thought that in the visual system the regeneration potential of the neuronal tissues is low.Nevertheless,there is always some potential for partial recovery of the visual field defect that can be achieved through induction of neuroplasticity.Neuroplasticity refers to the ability of the brain to change its own functional architecture by modulating synaptic efficacy.It is maintained throughout life and just as neurological rehabilitation can improve motor coordination,visual field defects in glaucoma,diabetic retinopathy or optic neuropathy can be improved by inducing neuroplasticity.In ophthalmology many new treatment paradigms have been tested that can induce neuroplastic changes,including non-invasive alternating current stimulation.Treatment with alternating current stimulation(e.g.,30 minutes,daily for 10 days using transorbital electrodes and^10 Hz)activates the entire retina and parts of the brain.Electroencephalography and functional magnetic resonance imaging studies revealed local activation of the visual cortex,global reorganization of functional brain networks,and enhanced blood flow,which together activate neurons and their networks.The future of low vision is optimistic because vision loss is indeed,partially reversible.
文摘AIM:To adapt the low vision-related quality of life(LVQOL) instrument into Turkish language and to assess its validity and reliability.METHODS:The study was conducted in 387 patients attending the Centre of Low Vision Rehabilitation,Faculty of Medicine,Ankara University.For statistical analyses,the Spearman's correlation coefficient,Cronbach's alpha coefficient and Confirmatory Factor Analysis(CFA) were used.RESULTS:According to results of CFA,the item in the 'Adjustment' subscale because of having the factor loading below 0.40,was excluded from the questionnaire.The reliability of the questionnaire was assessed according to Cronbach's alpha coefficients.The reliability of the 'Distance Vision,Mobility,and Lighting' subscale was ?琢=0.863;of the 'Adjustment' subscale was ?琢=0.694;'Reading and Fine Work' was ?琢=0.791,and 'Activities of Daily Living' was ?琢= 0.770.So these results indicate that the questionnaire is reliable to measure the vision related quality of life of low-vision patients.The correlations between the subscales were also analyzed,and the correlation between 'Adjustment' and 'Reading and Fine Work' was found to be the lowest(rs=0.336,P <0.001),whereas the strongest correlation was found between the 'Reading and Fine Work',and 'Activities of Daily Living'.Additionally,the 'Adjustment' dimension showed the strongest correlation with only 'Distance Vision,Mobility,and Lighting' dimension.CONCLUSION:After removing the last item in the second dimension,the Turkish adaptation of all dimensions of the LVQOL has been shown to be reliable,valid and suitable for use in patients with low vision in Turkey.
基金Supported by Tianjin Major Science and Technology Projects(No.17ZXHLSY00070)Tianjin Clinical Key Discipline Project(No.TJLCZDXKQ012)。
文摘AIM:To evaluate the effectiveness of Grand Seiko Ref/Keratometer WAM-5500 compared to Topcon KR800 autorefractor in detecting refractive error in large scale vision screening for Chinese school age children with the WHO criteria.METHODS:A total of 886 participants were enrolled with mean age of 9.49±1.88 y from Tianjin,China.Spherical equivalent(SE)was obtained from un-cycloplegic autorefraction and cycloplegic autorefraction.Topcon KR 800(Topcon)and Grand Seiko WAM-5500(WAM)autorefractors were used.Bland-Altman Plot and regression were generated to compare their performance.The overall effectiveness of detecting early stage refractive error was analyzed with receiver operating characteristic(ROC)curves.RESULTS:The mean SE was-0.98±1.81 diopter(D)and the prevalence of myopia was 48.9%defined by WHO criteria according to the result of cycloplegic autorefraction.The mean SE of un-cycloplegic autorefraction with Topcon and WAM were-1.21±1.65 and-1.20±1.68 D respectively.There was a strong linear agreement between result obtained from WAM and cycloplegic autorefraction with an R2 of 0.8318.Bland-Altman plot indicated a moderate agreement of cylinder values between the two methods.The sensitivity and specificity for detecting hyperopia were 90.52%and 83.51%;for detecting myopia were 95.60%and 90.24%;for detecting astigmatism were 79.40%and 90.21%;for detecting high myopia were 98.16%and 98.91%respectively.CONCLUSION:These findings suggest that both Grand Seiko and Topcon autorefractor can be used in large-scale vision screening for detecting refractive error in Chinese population.Grand Seiko gives relatively better performance in detecting myopia,hyperopia,and high myopia for school age children.
基金Supported by National Natural Science Foundation of China(No.81770955)National Natural Science Foundation of China for Young Scholars(No.82000929)+6 种基金Project of Shanghai Science and Technology(No.20410710100)Clinical Research Plan of SHDC(No.SHDC2020CR1043B)Project of Shanghai Xuhui District Science and Technology(No.2020-015)Project of Shanghai Xuhui District Science and Technology(No.XHLHGG202104)Shanghai Engineering Research Center of Laser and Autostereoscopic 3D for Vision Care(No.20DZ2255000)Shanghai Sailing Program(No.20YF1405000)。
文摘AIM: To investigate the one-year refractive outcomes and optical quality following PRESBYOND laser-blended vision(LBV).METHODS: This retrospective study included 20 patients who underwent PRESBYOND treatment between Jan 2019 and Aug 2020. The patients were asked to attend a followup outpatient visit one year after surgery. Distance and near visual acuity as well as subjective refraction were examined. Optical quality was assessed using wavefront-supported custom ablation. A questionnaire evaluating optical quality and satisfaction was completed at the last visit.RESULTS: The average patient age was 48.1±7.4 y(range, 41 to 58 y). The mean preoperative spherical equivalent was-7.59±2.39D. At the one-year follow-up, two eyes(both dominant eyes) lost one line of corrected distance visual acuity(CDVA), while the remaining eyes(38/40) maintained or gained lines of CDVA. The average binocular uncorrected distance visual acuity improved from 0.15±0.03 to 0.90±0.26(decimal vision;P<0.001). The average binocular uncorrected near visual acuity increased from 0.34±0.28 to 0.97±0.07(P<0.001). The spherical aberration was 0.04±0.06 μm in the nondominant eye and 0.09±0.09 μm in the dominant eye(P=0.02). All patients were satisfied with or accepted the outcomes of the surgery. The primary complaints were related to disturbances in night vision and relatively inferior near vision.CONCLUSION: Over the one-year observation period, PRESBYOND is a safe and effective option for presbyopia correction. The optical quality and near vision deserve further investigation.
基金the IUGS Deep-time Digital Earth (DDE) Big Science Programfinancially supported by the National Key R & D Program of China (No.2022YFF0711601)+3 种基金the Natural Science Foundation of Hubei Province of China (No.2022CFB640)the Opening Fund of Hubei Key Laboratory of Intelligent Vision-Based Monitoring for Hydroelectric Engineering (No.2022SDSJ04)the Opening Fund of Key Laboratory of Geological Survey and Evaluation of Ministry of Education (No.GLAB 2023ZR01)the Fundamental Research Funds for the Central Universities。
文摘The occurrence of geological disasters can have a large impact on urban safety. Protecting people’s safety is the most important concern when disasters occur. Safety improvement requires a large amount of comprehensive and representative risk analysis and a large collection of information related to geological hazards, including unstructured knowledge and experience. To address the relevant information and support safety risk analysis, a geological hazard knowledge graph is developed automatically based on computer vision and domain-geoscience ontology to identify geological hazards from input images while obeying safety rules and regulations, even when affected by changes. In the implementation of the knowledge graph, we design an ontology schema of geological disasters based on a top-down approach, and by organizing knowledge as a logical semantic expression, it can be shared using ontology technologies and therefore enable semantic interoperability. Computer vision approaches are then used to automatically detect a set of entities and attributes, using the data from input images, and object types and their attributes are identified so that they can be stored in Neo4j for reasoning and searching. Finally, a reasoning model for geological hazard identification was developed using the Neo4j database to create nodes, relationships, and their properties for modeling, and geological hazards in the images can be automatically identified by searching the Neo4j database. An application on geological hazard is presented. The results show the effectiveness of the proposed approach in terms of identifying possible potential hazards in geological hazards and assisting in formulating targeted preventive measures.
文摘AIM:To compare and analyse the diagnostic efficacy of the College of Optometrists Vision Development Quality of Life Questionnaire(COVD-QOL)and the Convergence Insufficiency Symptom Survey(CISS)in detecting convergence insufficiency and to compare their diagnostic value in clinical applications.METHODS:Using the diagnostic test method,62 adult patients with convergence insufficiency(age:24.74±3.75y)and 62 normal participants(age:23.61±3.13y)who visited the Optometry Clinic of West China Hospital of Sichuan University from April 2021 to January 2023 were included.All subjects completed the CISS and COVD-QOL.Statistical analysis of the sensitivity and specificity of the CISS and COVD-QOL and comparison and joint experimental analysis of their diagnostic efficacy were performed.RESULTS:The sensitivity of the CISS and COVD-QOL for convergence insufficiency was 64.5%and 71.0%,respectively,while the specificity was 96.8%and 67.7%,respectively.Compared to the CISS alone,the combination of the CISS and COVD-QOL demonstrated lower sensitivity and specificity.The areas under the receiver operating characteristic curve of CISS,COVD-QOL and CISS combined with COVD-QOL were 0.806,0.694 and 0.782,respectively.CONCLUSION:Considering the low sensitivity of the CISS and the low specificity of the COVD-QOL,it is recommended to supplement these questionnaires with other screening tests for the detection of convergence insufficiency.
文摘Background:Stereoscopic Vision uses the disparity between the two images received by the two eyes in order to create a tridimensional representation.With this study,we aimed at providing an estimate of binocular vision at a level prior to disparity processing.In particular,we wanted to assess the spatial properties of the visual system for detecting interocular correlations(IOC).Methods:We developed dichoptic stimuli,made of textures which IOC is sinusoidally modulated at various correlation spatial frequencies.Then,we compared the sensitivity to these stimuli to the sensitivity to analogous stimuli with disparity modulation.Results:We observed that IOC sensitivity presents a low-pass/band-pass profile and increases as a function of presentation duration and contrast,in a similar way as disparity sensitivity.Conclusions:IOC sensitivity is weakly-though significantly-correlated with disparity sensitivity in the general population,which suggests that it could provide a marker for binocular vision,prior to disparity processing.
文摘Background:We investigate whether changes in visual plasticity induced by monocular deprivation can be maintained across multiple days.It has been known that monocular deprivation strengthens the deprived eye in adults with normal vision for a short period of time(30-60 minutes).This has been shown through a variety of visual tasks such as binocular combination and rivalry.Methods:Ten subjects were recruited and patched for five consecutive days for two hours.We used a binocular phase combination task to measure the subjects’sensory eye balances.We initially measured their baseline of sensory eye balance,patched their dominant eye,and then conducted post-patching measurements at 0,3,6,12,24 and 48 minutes after patching.Results:We performed a 2-way ANOVA(Before vs.after patching×Day);we found that although the effect of monocular deprivation on the deprived eye was significant,F(1,9)=17.32,P=0.002,the effect of Day was not.Conclusions:Hence we found no accumulation of the patching effect across five days in healthy adults.This suggests that the degree of remnant neural plasticity in adult primary visual cortex may be too limited to be exploited therapeutically.
基金Supported by the Ministry of Higher Education Malaysia Long-Term Research Grant Scheme(LRGS/BU/2012/UKM-UKM/K/01)Cabaran Perdana Grant Scheme(DCP-2017-002/1)。
文摘AIM:To determine the association between distance and near visual acuity(VA)and cognitive function among older adults in Selangor,Malaysia.METHODS:A total of 230 older adults(age≥60y)participated in this study.Habitual distance and near VA were measured using the Early Treatment Diabetic Retinopathy Study Chart and Lighthouse Near Visual Acuity Chart,respectively.Global cognitive function was assessed using the Mini-Mental State Examination(M-MSE)and the Malay language version of the Montreal Cognitive Assessment(M-MoCA).Digit Symbol(DS)subtest was used to measure information processing.RESULTS:No significant association was observed between vision and M-MSE and M-MoCA scores.However,poor distance and near VA were found to be significantly associated with low DS scores[distance VA:β=-0.01,R2=0.1,P=0.02;odds ratio(OR)=2.84,95%confidence interval(CI),1.10-7.33,P=0.03;near VA:β=-0.05,R2=0.08,P=0.00;OR=3.32,95%CI,1.28-8.59,P=0.01].CONCLUSION:Poor vision is associated with a decline in information processing in older adults and substantiates the importance of preserving good vision in maintaining cognitive function.
文摘Architecture and the city are two major constituents of human development which, today more than ever, have to be present in the long-term. The Year of France in China is, for the first time, the occasion to present to the Chinese public a vision of the contemporary French architectural production, not only in France but also in China.
基金Supported by the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Science and ICT(No.2018R1C1B6002794)Korea University Grant(No.K1625491,No.K1722121,No.K1811051)。
文摘AIM:To evaluate clinical outcomes following implantation of an extended range of vision intraocular lens(IOL),the ZXR00,and a diffractive multifocal IOL with+2.75 diopters(D)add power,the ZKB00.METHODS:Totally 30 patients who underwent either bilateral implantation of the ZXR00 IOL with intended emmetropia(ZXR00 emmetropia group:20 eyes)and intended micromonovision(ZXR00 monovision group:20 eyes),or bilateral implantation of the ZKB00 IOL with intended emmetropia(ZKB00 group:20 eyes)were included in this study.Visual acuity at 4 m,80,and 40 cm;and the types of halos(misty,fine,and rainbow)were analyzed at one and three months after surgery.RESULTS:There were no significant differences in distance visual acuity among the three groups.The mean uncorrected intermediate visual acuity was better in the ZXR00 emmetropia and monovision groups(0.02 logMAR and 0.02 logMAR,respectively)than in the ZKB00 group(0.14 logMAR).The mean uncorrected near visual acuity was worse in the ZXR00 emmetropia group(0.26 logMAR)than in the ZXR00 monovision and ZKB00 groups(0.12 logMAR and 0.10 logMAR,respectively).There was an increased incidence of rainbow halos in the ZKB00 group vs in either ZXR00 group(P=0.033).CONCLUSION:Implantation of the ZXR00 IOL with intended micromonovision provide superior visual acuity than implantation of the ZXR00 IOL with intended emmetropia.The ZXR00 IOLs tend to show a lower incidence of rainbow halos than did the ZKB00 IOL.
基金This research is supported by the Science and Technology Department of Jilin Province[20210202128NC http://kjt.jl.gov.cn]The People’s Republic of China Ministry of Science and Technology[2018YFF0213606-03 http://www.most.gov.cn]+1 种基金Jilin Province Development and Reform Commission[2019C021 http://jldrc.jl.gov.cn]the Science and Technology Bureau of Changchun City[21ZGN27 http://kjj.changchun.gov.cn].
文摘With the increasing intensive and large-scale development of the sika deer breeding industry,it is crucial to assess the health status of the sika deer by monitoring their behaviours.A machine vision-based method for the behaviour recognition of sika deer is proposed in this paper.Google Inception Net(GoogLeNet)is used to optimise the model in this paper.First,the number of layers and size of the model were reduced.Then,the 5×5 convolution was changed to two 3×3 convolutions,which reduced the parameters and increased the nonlinearity of the model.A 5×5 convolution kernel was used to replace the original convolution for extracting coarse-grained features and improving the model’s extraction ability.A multi-scale module was added to the model to enhance the multi-faceted feature extraction capability of the model.Simultaneously,the Squeeze-and-Excitation Networks(SE-Net)module was included to increase the channel’s attention and improve the model’s accuracy.The dataset’s images were rotated to reduce overfitting.For image rotation,the angle wasmultiplied by 30°to obtain the dataset enhanced by rotation operations of 30°,60°,90°,120°and 150°.The experimental results showed that the recognition rate of this model in the behaviour of sika deer was 98.92%.Therefore,the model presented in this paper can be applied to the behaviour recognition of sika deer.The results will play an essential role in promoting animal behaviour recognition technology and animal health monitoring management.
基金Supported by the National Natural Science Foundation of China under Grant Nos 10794125,60808006,60821004,61078051 and 60978017.
文摘The quantum yield formula for uniform-doping GaAIAs/GaAs transmission-mode photocathodes is revised by taking into account the light absorption in the window layer.By using the revised quantum yield formula,the domestic and ITT's experimental quantum yield curves are fitted and the fitted curves match well with the experimental curves.In addition,the fit results show that the integral sensitivity and quantum yield of domestic image intensifier tube has achieved 2130μA/lm and 45%,nearly reaching ITT's third generation level in 2002,whereas the discrepancy in cathode performance is mainly embodied in the electron diffusion length and back interface recombination velocity.
文摘Background:In situations where one eye gives a more blurred input to visual processing than the other,the input from the sharper eye tends to dominate the percept.This phenomenon has clinical relevance for monovision treatment,where the two eyes are corrected separately for different distances.We performed a psychophysical investigation of subjects’ability to identify which of a set of images was blurred in one eye.Methods:We tested 17 subjects with normal or corrected-to-normal vision.On each trial,subjects viewed an array of four pictures using a monitor with shutter goggles.In the first experiment,three of the pictures were sharp in both eyes(distractors).The fourth picture was sharp in one eye and blurred by a low-pass filter in the other.Subjects identified that odd-one-out target over many trials with different degrees of blur.In the second experiment the target picture was given the same treatment,but the three non-target pictures were made monocular(sharp in one eye,mean grey in the other).Results:The results from the first experiment with binocular distractors followed our expectations,with subjects showing better performance at detecting more severe blurs.In the second experiment with monocular distractors,we found large individual differences between our observers.Some performed the same as they did in the first condition,others now found the task impossible,and a few performed worse with severe blurs than they did with slight blurs.Conclusions:Previous studies have reported individual differences in blur suppression,however this study reveals that these differences may depend on the precise details of the judgements being made.
文摘Background:This study evaluated the VIsion PERformance(VIPER)simulator’s ability to assess the functional visual performance in warfighters conducting civilian and military tasks.Methods:Thirty service members,aged 25–35 years old with a best corrected distance visual acuity(VA)better than or equal to 20/20 or logarithm of the minimum angle of resolution(logMAR)0.00,were randomized to locate and identify road signs and mock improvised explosive devices(IEDs)under either daytime conditions or with infrared imagery,with(cc)and without(sc)wearing their habitual correction.Participants also underwent binocular uncorrected(UDVA)and corrected(CDVA)visual assessment,refraction,contrast sensitivity testing and wavefront aberrometry.Results:The mean age was 28.47 years.The manifest spherical equivalent was–3.16±1.75 diopters(D),the UDVA in both eyes(OU)was logMAR 0.83±0.47,and the CDVA OU was–0.11±0.06.For VIPER,the mean difference in the detection distance(DD)for road signs ccDD vs.scDD was(76.7±52.8)m(P<0.001).The average difference in identification distance(ID)ccID vs.scID was(13.9±6.3)m(P<0.001).The mean accuracies were 83.5%and 27.9%for cc and sc,respectively(P<0.001).The regression analysis indicated that a 1.6 m change in the distance accounts for a 1%change in the accuracy(P=0.002).Without correction,a 4.1 m change accounts for a 1%change in the accuracy(P<0.001).The average IED ccDD was(29.9±8.2)m,and that for scDD was(13.2±13.6)m(P<0.001).The average IED ccID was(32.2±6.2)m and that for the scID was(7.4±10.3)m(P<0.001).The mean IED identification accuracy was 46.7 and 11.4%for cc and sc,respectively(P<0.001).Conclusions:The preliminary results reflect VIPER’s ability to assess functional visual performance when detecting and identifying signs and IEDs.Furthermore,VIPER is able to detect performance changes with and without correction.
文摘This paper presents an efficient robot calibration method with non-contact vision metrology. Using the coplanar pattern to calibrate camera made the active-vision-based end-effector pose measurement be a feasible and costeffective way. Kinematic parameter errors were linearized and identified through two-step procedure, thus the singular and non-linear condition was overcome. These errors were then compensated using inverse model method. The whole calibration process is flexible, easy to implement and prevents the error propagation from the earlier stages to the later ones. Calibration was performed on MOTOMAN SV3industrial robot. Experiment results show that the proposed method is easy to setup and with satisfactory accuracy.
基金supported by Natural Science Foundation of China(grant number 82201195).
文摘Background:Vision and vision-language foundation models,a subset of advanced artificial intelligence(AI)frameworks,have shown transformative potential in various medical fields.In ophthalmology,these models,particularly large language models and vision-based models,have demonstrated great potential to improve diagnostic accuracy,enhance treatment planning,and streamline clinical workflows.However,their deployment in ophthalmology has faced several challenges,particularly regarding generalizability and integration into clinical practice.This systematic review aims to summarize the current evidence on the use of vision and visionlanguage foundation models in ophthalmology,identifying key applications,outcomes,and challenges.Main text:A comprehensive search on PubMed,Web of Science,Scopus,and Google Scholar was conducted to identify studies published between January 2020 and July 2025.Studies were included if they developed or applied foundation models,such as vision-based models and large language models,to clinically relevant ophthalmic applications.A total of 10 studies met the inclusion criteria,covering areas such as retinal diseases,glaucoma,and ocular surface tumor.The primary outcome measures are model performance metrics,integration into clinical workflows,and the clinical utility of the models.Additionally,the review explored the limitations of foundation models,such as the reliance on large datasets,computational resources,and interpretability challenges.The majority of studies demonstrated that foundation models could achieve high diagnostic accuracy,with several reports indicating excellent performance comparable to or exceeding those of experienced clinicians.Foundation models achieved high accuracy rates up to 95%for diagnosing retinal diseases,and similar performances for detecting glaucoma progression.Despite promising results,concerns about algorithmic bias,overfitting,and the need for diverse training data were common.High computational demands,EHR compatibility,and the need for clinician validation also posed challenges.Additionally,model interpretability issues hindered clinician trust and adoption.Conclusions:Vision and vision-language foundation models in ophthalmology show significant potential for advancing diagnostic accuracy and treatment strategies,particularly in retinal diseases,glaucoma,and ocular oncology.However,challenges such as data quality,transparency,and ethical considerations must be addressed.Future research should focus on refining model performance,improving interpretability and generalizability,and exploring strategies for integrating these models into routine clinical practice to maximize their impact in clinical ophthalmology.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korean government(MSIT)(Nos.RS-2023-00241758,2021R1A2C2003696,and RS-2024-00334513).
文摘Earthwork productivity analysis is essential for successful construction projects.If productivity analysis results can be accessed anytime and anywhere,then project management can be performed more efficiently.To this end,this paper proposes an earthwork productivity monitoring framework via a real-time scene updating multi-vision platform.The framework consists of four main processes:1)site-optimized database development;2)real-time monitoring model updating;3)multi-vision productivity monitoring;and 4)web-based monitoring platform for Internetconnected devices.The experimental results demonstrated satisfactory performance,with an average macro F1-score of 87.3%for continuous site-specific monitoring,an average accuracy of 86.2%for activity recognition,and the successful operation of multi-vision productivity monitoring through a web-based platform in real time.The findings can contribute to supporting site managers to understand real-time earthmoving operations while achieving better construction project and information management.
基金supported by the National Natural Science Foundation of China(Nos.62027810 and 61733004)the National Key Research and Development Program of China(No.2020YFB1712600)+1 种基金the Hunan Science and Technology Program of Hunan Province,China(Nos.2017XK2102 and 2018GK2022)supported by the Changsha Science and Technology Innovation Fund,China(No.kq2402079).
文摘The increase in precision agriculture has promoted the development of picking robot technology,and the visual recognition system at its core is crucial for improving the level of agricultural automation.This paper reviews the progress of visual recognition tech-nology for picking robots,including image capture technology,target detection algorithms,spatial positioning strategies and scene un-derstanding.This article begins with a description of the basic structure and function of the vision system of the picking robot and em-phasizes the importance of achieving high-efficiency and high-accuracy recognition in the natural agricultural environment.Sub-sequently,various image processing techniques and vision algorithms,including color image analysis,three-dimensional depth percep-tion,and automatic object recognition technology that integrates machine learning and deep learning algorithms,were analysed.At the same time,the paper also highlights the challenges of existing technologies in dynamic lighting,occlusion problems,fruit maturity di-versity,and real-time processing capabilities.This paper further discusses multisensor information fusion technology and discusses methods for combining visual recognition with a robot control system to improve the accuracy and working rate of picking.At the same time,this paper also introduces innovative research,such as the application of convolutional neural networks(CNNs)for accurate fruit detection and the development of event-based vision systems to improve the response speed of the system.At the end of this paper,the future development of visual recognition technology for picking robots is predicted,and new research trends are proposed,including the refinement of algorithms,hardware innovation,and the adaptability of technology to different agricultural conditions.The purpose of this paper is to provide a comprehensive analysis of visual recognition technology for researchers and practitioners in the field of agricul-tural robotics,including current achievements,existing challenges and future development prospects.
