With technological advancements,consumer demands for textile functionality and intelligence have increased substantially.Next-generation E-textiles should enable multidirectional force sensing while ensuring high leve...With technological advancements,consumer demands for textile functionality and intelligence have increased substantially.Next-generation E-textiles should enable multidirectional force sensing while ensuring high levels of wearer comfort.However,existing electronic textiles are insufficient to simultaneously monitor the direction and degree of strain,and sweat accumulation can lead to poor comfort.Here,inspired by the asymmetric gradient structure of human skin,Janus double-layer woven electronic textile(JDET)was designed.Through material-structure-function biomimetic design,bidirectional bending recognition and moisture management function are integrated into the device.A high-sensitivity strain sensing unit(GF=1402.94)was constructed using a single wrapped yarn and conductive materials.Combined with a double-layer fabric structure design,a plain weave layer woven with hydrophilic sensing yarn and a twill weave layer woven with hydrophobic polyester yarn formed a dual gradient structure of fabric wettability and porosity,resulting in excellent unidirectional moisture transport capability.The asymmetric design of the sensing layer enables JDET to selectively identify bending directions(-180°-180°),and has good stability(>8000 s)in bending cycle testing.In addition,JDET has been successfully applied to human motion monitoring and Morse code interaction systems.This asymmetric gradient structure design of textiles provides ideas for the design of the next generation of intelligent electronic textiles.展开更多
An active perception methodology is proposed to locally predict the observability condition in a reasonable horizon and suggest an observability-constrained motion direction for the next step to ensure an accurate and...An active perception methodology is proposed to locally predict the observability condition in a reasonable horizon and suggest an observability-constrained motion direction for the next step to ensure an accurate and consistent state estimation performance of vision-based navigation systems. The methodology leverages an efficient EOG-based observability analysis and a motion primitive-based path sampling technique to realize the local observability prediction with a real-time performance. The observability conditions of potential motion trajectories are evaluated,and an informed motion direction is selected to ensure the observability efficiency for the state estimation system. The proposed approach is specialized to a representative optimizationbased monocular vision-based state estimation formulation and demonstrated through simulation and experiments to evaluate the ability of estimation degradation prediction and efficacy of motion direction suggestion.展开更多
During natural viewing,we often recognize multiple objects,detect their motion,and select one object as the target to track.It remains to be determined how such behavior is guided by the integration of visual form and...During natural viewing,we often recognize multiple objects,detect their motion,and select one object as the target to track.It remains to be determined how such behavior is guided by the integration of visual form and motion perception.To address this,we studied how monkeys made a choice to track moving targets with different forms by smooth pursuit eye movements in a two-target task.We found that pursuit responses were biased toward the motion direction of a target with a hole.By computing the relative weighting,we found that the target with a hole exhibited a larger weight for vector computation.The global hole feature dominated other form properties.This dominance failed to account for changes in pursuit responses to a target with different forms moving singly.These findings suggest that the integration of visual form and motion perception can reshape the competition in sensorimotor networks to guide behavioral selection.展开更多
Traditional autonomous driving research decomposes the problem into five distinct subtasks:perception,tracking,prediction,planning,and control.Despite the recent significant progress,the paradigm faces challenges due ...Traditional autonomous driving research decomposes the problem into five distinct subtasks:perception,tracking,prediction,planning,and control.Despite the recent significant progress,the paradigm faces challenges due to limitations in computational capacity and the propagation of cumulative errors,resulting in unsatisfactory outcomes in real-world scenarios.Recently,researchers have shifted their focus toward a novel paradigm:end-to-end methods for perception and prediction(PnP).This approach integrates concepts from multi-object tracking and joint perception and prediction models,promoting synergistic enhancements across various tasks to achieve superior performance.In this paper,we conduct a comprehensive survey of the PnP research,aiming to encompass the entirety of the work in this area.First,we introduce the PnP pipeline and provide an overview of our survey.We then delve into PnP methods by modality,including LiDAR,camera,and multi-modal data,offering detailed insights into their architectures.Furthermore,we discuss the future directions of this field in new scenarios.展开更多
This paper presents a novel algorithm for automatically detecting global shakiness in casual videos. Per-frame amplitude is computed by the geometry of motion, based on the kinematic model defined by inter-frame geome...This paper presents a novel algorithm for automatically detecting global shakiness in casual videos. Per-frame amplitude is computed by the geometry of motion, based on the kinematic model defined by inter-frame geometric transformations. Inspired by motion perception, we investigate the just-noticeable amplitude of shaky motion perceived by the human visual system. Then, we use the thresholding contrast strategy on the statistics of per-frame amplitudes to determine the occurrence of perceived shakiness. For testing the detection accuracy, a dataset of video clips is constructed with manual shakiness label as the ground truth. The experiments demonstrate that our algorithm can obtain good detection accuracy that is in concordance with subjective judgement on the videos in the dataset.展开更多
Motion perception is one of the most important aspects of the biological visual system, from which people get a lot of information of the natural world. In this paper, trying to simulate the neurons in MT (motion area...Motion perception is one of the most important aspects of the biological visual system, from which people get a lot of information of the natural world. In this paper, trying to simulate the neurons in MT (motion area in visual cortex) which respond selectively both in direction and speed, the authors propose a novel multiplicative inhibitory velocity detector (MIVD) model, whose spatiotemporal joint parameter K determines its optimal velocity. Based on the Response Amplitude Disparity (RAD) property of MIVD, two multi-velocity fusion neural networks (a simple one and an active one) are built to detect the velocity of 1-Dimension motion. The experiments show that the active MIVD Neural Network with a feedback fusion method has a relatively better result.展开更多
基金supported by the National Natural Science Foundation of China(No.Grant52173218)the Natural Science Foundation Project of Shanghai“science and technology innovation action plan”(Nos.22ZR1400500 and 20ZR1400200)+1 种基金the Key Research and Development Program of the Science and Technology Bureau of Ningbo City(Grant No.2023Z082)supported by“the Fundamental Research Funds for the Central Universities”(CUSF-DH-T-2024043).
文摘With technological advancements,consumer demands for textile functionality and intelligence have increased substantially.Next-generation E-textiles should enable multidirectional force sensing while ensuring high levels of wearer comfort.However,existing electronic textiles are insufficient to simultaneously monitor the direction and degree of strain,and sweat accumulation can lead to poor comfort.Here,inspired by the asymmetric gradient structure of human skin,Janus double-layer woven electronic textile(JDET)was designed.Through material-structure-function biomimetic design,bidirectional bending recognition and moisture management function are integrated into the device.A high-sensitivity strain sensing unit(GF=1402.94)was constructed using a single wrapped yarn and conductive materials.Combined with a double-layer fabric structure design,a plain weave layer woven with hydrophilic sensing yarn and a twill weave layer woven with hydrophobic polyester yarn formed a dual gradient structure of fabric wettability and porosity,resulting in excellent unidirectional moisture transport capability.The asymmetric design of the sensing layer enables JDET to selectively identify bending directions(-180°-180°),and has good stability(>8000 s)in bending cycle testing.In addition,JDET has been successfully applied to human motion monitoring and Morse code interaction systems.This asymmetric gradient structure design of textiles provides ideas for the design of the next generation of intelligent electronic textiles.
文摘An active perception methodology is proposed to locally predict the observability condition in a reasonable horizon and suggest an observability-constrained motion direction for the next step to ensure an accurate and consistent state estimation performance of vision-based navigation systems. The methodology leverages an efficient EOG-based observability analysis and a motion primitive-based path sampling technique to realize the local observability prediction with a real-time performance. The observability conditions of potential motion trajectories are evaluated,and an informed motion direction is selected to ensure the observability efficiency for the state estimation system. The proposed approach is specialized to a representative optimizationbased monocular vision-based state estimation formulation and demonstrated through simulation and experiments to evaluate the ability of estimation degradation prediction and efficacy of motion direction suggestion.
基金supported by the Beijing Natural Science Foundation(Z210009)the National Science and Technology Innovation 2030 Major Program(STI2030-Major Projects 2022ZD0204800)+1 种基金the National Natural Science Foundation of China(32070987,31722025,31730039)the Chinese Academy of Sciences Key Program of Frontier Sciences(QYZDB-SSW-SMC019).
文摘During natural viewing,we often recognize multiple objects,detect their motion,and select one object as the target to track.It remains to be determined how such behavior is guided by the integration of visual form and motion perception.To address this,we studied how monkeys made a choice to track moving targets with different forms by smooth pursuit eye movements in a two-target task.We found that pursuit responses were biased toward the motion direction of a target with a hole.By computing the relative weighting,we found that the target with a hole exhibited a larger weight for vector computation.The global hole feature dominated other form properties.This dominance failed to account for changes in pursuit responses to a target with different forms moving singly.These findings suggest that the integration of visual form and motion perception can reshape the competition in sensorimotor networks to guide behavioral selection.
基金supported by the National Natural Science Foundation of China(Nos.62076026,62303046,62222302,62372453)in part by the open research fund of the State Key Laboratory of Multimodal Artificial Intelligence Systems,China.
文摘Traditional autonomous driving research decomposes the problem into five distinct subtasks:perception,tracking,prediction,planning,and control.Despite the recent significant progress,the paradigm faces challenges due to limitations in computational capacity and the propagation of cumulative errors,resulting in unsatisfactory outcomes in real-world scenarios.Recently,researchers have shifted their focus toward a novel paradigm:end-to-end methods for perception and prediction(PnP).This approach integrates concepts from multi-object tracking and joint perception and prediction models,promoting synergistic enhancements across various tasks to achieve superior performance.In this paper,we conduct a comprehensive survey of the PnP research,aiming to encompass the entirety of the work in this area.First,we introduce the PnP pipeline and provide an overview of our survey.We then delve into PnP methods by modality,including LiDAR,camera,and multi-modal data,offering detailed insights into their architectures.Furthermore,we discuss the future directions of this field in new scenarios.
基金This work was partially supported by the National Natural Science Foundation of China under Grant No. 61602015, the Open Funding Project of State Key Laboratory of Virtual Reality Technology and Systems at Beihang University under Grant No. BUAAVR-16KF-06, Beijing Natural Science Foundation under Grant No. 4162019, and the Research Foundation for Young Scholars of Beijing Technology and Business University.
文摘This paper presents a novel algorithm for automatically detecting global shakiness in casual videos. Per-frame amplitude is computed by the geometry of motion, based on the kinematic model defined by inter-frame geometric transformations. Inspired by motion perception, we investigate the just-noticeable amplitude of shaky motion perceived by the human visual system. Then, we use the thresholding contrast strategy on the statistics of per-frame amplitudes to determine the occurrence of perceived shakiness. For testing the detection accuracy, a dataset of video clips is constructed with manual shakiness label as the ground truth. The experiments demonstrate that our algorithm can obtain good detection accuracy that is in concordance with subjective judgement on the videos in the dataset.
基金This research is partially supported by the Trans-Century Talents Foundation of the State Education Commission of China and the
文摘Motion perception is one of the most important aspects of the biological visual system, from which people get a lot of information of the natural world. In this paper, trying to simulate the neurons in MT (motion area in visual cortex) which respond selectively both in direction and speed, the authors propose a novel multiplicative inhibitory velocity detector (MIVD) model, whose spatiotemporal joint parameter K determines its optimal velocity. Based on the Response Amplitude Disparity (RAD) property of MIVD, two multi-velocity fusion neural networks (a simple one and an active one) are built to detect the velocity of 1-Dimension motion. The experiments show that the active MIVD Neural Network with a feedback fusion method has a relatively better result.
