Efficient Convolution Operator(ECO)algorithms have achieved impressive performances in visual tracking.However,its feature extraction network of ECO is unconducive for capturing the correlation features of occluded an...Efficient Convolution Operator(ECO)algorithms have achieved impressive performances in visual tracking.However,its feature extraction network of ECO is unconducive for capturing the correlation features of occluded and blurred targets between long-range complex scene frames.More so,its fixed weight fusion strategy does not use the complementary properties of deep and shallow features.In this paper,we propose a new target tracking method,namely ECO++,using deep feature adaptive fusion in a complex scene,in the following two aspects:First,we constructed a new temporal convolution mode and used it to replace the underlying convolution layer in Conformer network to obtain an improved Conformer network.Second,we adaptively fuse the deep features,which output through the improved Conformer network,by combining the Peak to Sidelobe Ratio(PSR),frame smoothness scores and adaptive adjustment weight.Extensive experiments on the OTB-2013,OTB-2015,UAV123,and VOT2019 benchmarks demonstrate that the proposed approach outperforms the state-of-the-art algorithms in tracking accuracy and robustness in complex scenes with occluded,blurred,and fast-moving targets.展开更多
In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,th...In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,the high-level image information and the modality-specific features have not been sufficiently studied.The proposed correlation filter uses the fused saliency content map to improve filter training and extracts different features of modalities.The fused content map is intro-duced into the spatial regularization term of correlation filter to highlight the training samples in the content region.Furthermore,the fused content map can avoid the incompleteness of the con-tent region caused by challenging situations.Additionally,differ-ent features are extracted according to the modality characteris-tics and are fused by the designed response-level fusion stra-tegy.The alternating direction method of multipliers(ADMM)algorithm is used to solve the tracker training efficiently.Experi-ments on the large-scale benchmark datasets show the effec-tiveness of the proposed tracker compared to the state-of-the-art traditional trackers and the deep learning based trackers.展开更多
Laser powder-bed fusion(LPBF)of Zn-0.8Cu(wt.%)alloys exhibits significant advantages in the customization of biodegradable bone implants.However,the formability of LPBFed Zn alloy is not sufficient due to the spheroid...Laser powder-bed fusion(LPBF)of Zn-0.8Cu(wt.%)alloys exhibits significant advantages in the customization of biodegradable bone implants.However,the formability of LPBFed Zn alloy is not sufficient due to the spheroidization during the interaction of powder and laser beam,of which the mechanism is still not well understood.In this study,the evolution of morphology and grain structure of the LPBFed Zn-Cu alloy was investigated based on single-track deposition experiments.As the scanning speed increases,the grain structure of a single track of Zn-Cu alloy gradually refines,but the formability deteriorates,leading to the defect’s formation in the subsequent fabrication.The Zn-Cu alloys fabricated by optimum processing parameters exhibit a tensile strength of 157.13 MPa,yield strength of 106.48 MPa and elongation of 14.7%.This work provides a comprehensive understanding of the processing optimization of Zn-Cu alloy,achieving LPBFed Zn-Cu alloy with high density and excellent mechanical properties.展开更多
A distributed bearing-only target tracking algorithm based on variational Bayesian inference(VBI)under random measurement anomalies is proposed for the problem of adverse effect of random measurement anomalies on the ...A distributed bearing-only target tracking algorithm based on variational Bayesian inference(VBI)under random measurement anomalies is proposed for the problem of adverse effect of random measurement anomalies on the state estimation accuracy of moving targets in bearing-only tracking scenarios.Firstly,the measurement information of each sensor is complemented by using triangulation under the distributed framework.Secondly,the Student-t distribution is selected to model the measurement likelihood probability density function,and the joint posteriori probability density function of the estimated variables is approximately decoupled by VBI.Finally,the estimation results of each local filter are sent to the fusion center and fed back to each local filter.The simulation results show that the proposed distributed bearing-only target tracking algorithm based on VBI in the presence of abnormal measurement noise comprehensively considers the influence of system nonlinearity and random anomaly of measurement noise,and has higher estimation accuracy and robustness than other existing algorithms in the above scenarios.展开更多
To solve the mismatch between the candidate model and the reference model caused by the time change of the tracked head, a novel mean shift algorithm based on a fusion model is provided. A fusion model is employed to ...To solve the mismatch between the candidate model and the reference model caused by the time change of the tracked head, a novel mean shift algorithm based on a fusion model is provided. A fusion model is employed to describe the tracked head by sampling the models of the fore-head and the back-head under different situations. Thus the fusion head reference model is represented by the color distribution estimated from both the fore- head and the back-head. The proposed tracking system is efficient and it is easy to realize the goal of continual tracking of the head by using the fusion model. The results show that the new tracker is robust up to a 360°rotation of the head on a cluttered background and the tracking precision is improved.展开更多
A new distributed fusion method of radar/infrared （IR） tracking system based on separation and combination of the measurements is proposed by analyzing the influence of rate measurement. The rate information separat...A new distributed fusion method of radar/infrared （IR） tracking system based on separation and combination of the measurements is proposed by analyzing the influence of rate measurement. The rate information separated from the radar measurements together with measurements of IR form a pseudo vector of IR, and the corresponding filter is designed. The results indicate that the method not only makes a great improvement to the local tracker＇s performance, but also improves the global tracking precision efficiently.展开更多
The coalescence and missed detection are two key challenges in Multi-Target Tracking(MTT).To balance the tracking accuracy and real-time performance,the existing Random Finite Set(RFS)based filters are generally diffi...The coalescence and missed detection are two key challenges in Multi-Target Tracking(MTT).To balance the tracking accuracy and real-time performance,the existing Random Finite Set(RFS)based filters are generally difficult to handle the above problems simultaneously,such as the Track-Oriented marginal Multi-Bernoulli/Poisson(TOMB/P)and Measurement-Oriented marginal Multi-Bernoulli/Poisson(MOMB/P)filters.Based on the Arithmetic Average(AA)fusion rule,this paper proposes a novel fusion framework for the Poisson Multi-Bernoulli(PMB)filter,which integrates both the advantages of the TOMB/P filter in dealing with missed detection and the advantages of the MOMB/P filter in dealing with coalescence.In order to fuse the different PMB distributions,the Bernoulli components in different Multi-Bernoulli(MB)distributions are associated with each other by Kullback-Leibler Divergence(KLD)minimization.Moreover,an adaptive AA fusion rule is designed on the basis of the exponential fusion weights,which utilizes the TOMB/P and MOMB/P updates to solve these difficulties in MTT.Finally,by comparing with the TOMB/P and MOMB/P filters,the performance of the proposed filter in terms of accuracy and efficiency is demonstrated in three challenging scenarios.展开更多
The random noises of multi-sensor and the environment make observations uncertain and correlative, so the performance of fusion algorithms is reduced by using observations directly. To solve this problem, a multi-laye...The random noises of multi-sensor and the environment make observations uncertain and correlative, so the performance of fusion algorithms is reduced by using observations directly. To solve this problem, a multi-layer track fusion algorithm based on supporting degree matrix is proposed. Combined with the track fusion algorithm based on filtering step by step, it uses multi-sensor observations to establish supporting degree matrix and realize multi-layer fusion. Simulation results show its estimation precision is higher than the original algorithm and is increased by 20% around. Therefore, it solves the problem of target tracking further in the distributed track fusion system.展开更多
Radar and LiDAR are two environmental sensors commonly used in autonomous vehicles,Lidars are accurate in determining objects’positions but significantly less accurate as Radars on measuring their velocities.However,...Radar and LiDAR are two environmental sensors commonly used in autonomous vehicles,Lidars are accurate in determining objects’positions but significantly less accurate as Radars on measuring their velocities.However,Radars relative to Lidars are more accurate on measuring objects velocities but less accurate on determining their positions as they have a lower spatial resolution.In order to compensate for the low detection accuracy,incomplete target attributes and poor environmental adaptability of single sensors such as Radar and LiDAR,in this paper,an effective method for high-precision detection and tracking of surrounding targets of autonomous vehicles.By employing the Unscented Kalman Filter,Radar and LiDAR information is effectively fused to achieve high-precision detection of the position and speed information of targets around the autonomous vehicle.Finally,the real vehicle test under various driving environment scenarios is carried out.The experimental results show that the proposed sensor fusion method can effectively detect and track the vehicle peripheral targets with high accuracy.Compared with a single sensor,it has obvious advantages and can improve the intelligence level of autonomous cars.展开更多
To accurately identify the potential contact loss of the China railway track system(CRTS)III prefabricated slab track,a finite element model with contact loss of self-compacting concrete(SCC)under transient impact was...To accurately identify the potential contact loss of the China railway track system(CRTS)III prefabricated slab track,a finite element model with contact loss of self-compacting concrete(SCC)under transient impact was established.Then the vertical accelerations near impact points on the track slab surface were extracted to obtain damage-sensitive indices in the time and frequency domains.The indices were initially normalized to obtain independent items of evidence before the Dempster-Shafer(D-S)evidence theory was used to fuse these into one.Finally,a two-stage identification was performed to identify the damaged SCC area,comprising a rough identification(Stage I)and a precise identification(Stage II).The research results show that the damage indices extracted based on the transient impact response change abruptly at the damage location,and that can be used for damage identification.However,the use of a single index to determine the damage of the impact point may be misjudged.In Stage I,five damage indices of acceleration were fused to magnify the difference between the damaged point and undamaged point,thereby improving the accuracy of finding damage.In Stage II,in the area where more impact points were added,a fusion of three indices of acceleration response,that is,the absolute mean of the time domain,the maximum amplitude of the frequency domain,and the power density ratio,further narrowed down the area where damage exists.As a result,when the contact loss of SCC is greater than 50%along the thickness direction,the identification accuracy can be as high as 70%to 80%.The two-stage identification method proposed in this study can greatly improve the efficiency of interlayer damage detection of slab tracks and is expected to provide effective technical support for damage identification of track structures in the future.展开更多
Laser powder bed fusion(LPBF)technology is a high-precision metal additive manufacturing(AM)technology.Due to the high specific strength of high strength aluminum alloys,high strength aluminum alloys fabricated by LPB...Laser powder bed fusion(LPBF)technology is a high-precision metal additive manufacturing(AM)technology.Due to the high specific strength of high strength aluminum alloys,high strength aluminum alloys fabricated by LPBF have broad application prospects in the field of light weighting.However,high strength aluminum alloys have high hot cracking susceptibility.In this study,an analysis of the hot cracking susceptibility as a function of processing parameters is presented for single tracks of LPBF processed(LPBFed)high strength Al–Cu–Mg–Mn alloy.The hot cracking in single tracks of LPBFed Al–Cu–Mg–Mn alloy is solidification cracking based on the experimental observations of microstructure.Combining Rosenthal simulations and spreading behavior of a single droplet,the critical scanning speed of single track with balling phenomenon was obtained.It was found that when the laser power was 200 W,the scanning speed exceeded 440.1 mm/s,the droplet will not be able to spread completely,which is consistent with the experimental result of 500 mm/s.Through the calculation and analysis of the microstructure and the existence time of the molten pool,it was pointed out that the reduction in the liquid phase caused by the high scanning speed,the shortening of the solidification time and the high stress caused by the high-temperature gradient promoted the generation of hot cracking.In summary,this work contains a practical guide to optimize processing parameters of LPBFed Al–Cu–Mg–Mn alloys,which provides a basis for fabricating thin walls and cubic samples without hot cracking.展开更多
Onboard visual object tracking in unmanned aerial vehicles(UAVs)has attractedmuch interest due to its versatility.Meanwhile,due to high precision,Siamese networks are becoming hot spots in visual object tracking.Howev...Onboard visual object tracking in unmanned aerial vehicles(UAVs)has attractedmuch interest due to its versatility.Meanwhile,due to high precision,Siamese networks are becoming hot spots in visual object tracking.However,most Siamese trackers fail to balance the tracking accuracy and time within onboard limited computational resources of UAVs.To meet the tracking precision and real-time requirements,this paper proposes a Siamese dense pixel-level network for UAV object tracking named SiamDPL.Specifically,the Siamese network extracts features of the search region and the template region through a parameter-shared backbone network,then performs correlationmatching to obtain the candidate regionwith high similarity.To improve the matching effect of template and search features,this paper designs a dense pixel-level feature fusion module to enhance the matching ability by pixel-wise correlation and enrich the feature diversity by dense connection.An attention module composed of self-attention and channel attention is introduced to learn global context information and selectively emphasize the target feature region in the spatial and channel dimensions.In addition,a target localization module is designed to improve target location accuracy.Compared with other advanced trackers,experiments on two public benchmarks,which are UAV123@10fps and UAV20L fromthe unmanned air vehicle123(UAV123)dataset,show that SiamDPL can achieve superior performance and low complexity with a running speed of 100.1 fps on NVIDIA TITAN RTX.展开更多
Laser powder bed fusion(LPBF)has made significant progress in producing solid and porous metal parts with complex shapes and geometries.However,LPBF produced parts often have defects(e.g.,porosity,residual stress,and i...Laser powder bed fusion(LPBF)has made significant progress in producing solid and porous metal parts with complex shapes and geometries.However,LPBF produced parts often have defects(e.g.,porosity,residual stress,and incomplete melting)that hinder its large-scale industrial commercialization.The LPBF process involves complex heat transfer andfluidflow,and the melt pool is a critical component of the process.The melt pool stability is a critical factor in determining the microstructure,mechanical properties,and corrosion resistance of LPBF produced metal parts.Furthermore,optimizing process parameters for new materials and designed structures is challenging due to the complexity of the LPBF process.This requires numerous trial-and-error cycles to minimize defects and enhance properties.This review examines the behavior of the melt pool during the LPBF process,including its effects and formation mechanisms.This article summarizes the experimental results and simulations of melt pool and identifies various factors that influence its behavior,which facilitates a better understanding of the melt pool's behavior during LPBF.This review aims to highlight key aspects of the investigation of melt pool tracks and microstructural characterization,with the goal of enhancing a better understanding of the relationship between alloy powder-process-microstructure-properties in LPBF from both single-and multi-melt pool track perspectives.By identifying the challenges and opportunities in investigating single-and multi-melt pool tracks,this review could contribute to the advancement of LPBF processes,optimal process window,and quality optimization,which ultimately improves accuracy in process parameters and efficiency in qualifying alloy powders.展开更多
The paper analyses the improvement of track loss in clutter with multisensor data fusion.By a determination of the transition probability density function for the fusion prediction error, one can study the mechanism o...The paper analyses the improvement of track loss in clutter with multisensor data fusion.By a determination of the transition probability density function for the fusion prediction error, one can study the mechanism of track loss analytically. With nearest-neighbor association algorithm. The paper we studies the fused tracking performance parameters, such as mean time to lose fused track and the cumulative probability of lost fused track versus the normalized clutter density, for track continuation and track initiation, respectively. A comparison of the results obtained with the case of a single sensor is presented. These results show that the fused tracks of multisensor reduce the possibility of track loss and improve the tracking performance. The analysis is of great importance for further understanding the action of data fusion.展开更多
Single passive sensor tracking algorithms have four disadvantages: bad stability, longdynamic time, big bias and sensitive to initial conditions. So the corresponding fusion algorithm results in bad performance. A new...Single passive sensor tracking algorithms have four disadvantages: bad stability, longdynamic time, big bias and sensitive to initial conditions. So the corresponding fusion algorithm results in bad performance. A new error analysis method for two passive sensor tracking system is presented and the error equations are deduced in detail. Based on the equations, we carry out theoretical computation and Monte Carlo computer simulation. The results show the correctness of our error computation equations. With the error equations, we present multiple 'two station'fusion algorithm using adaptive pseudo measurement equations. This greatly enhances the tracking performance and makes the algorithm convergent very fast and not sensitive to initial conditions.Simulation results prove the correctness of our new algorithm.展开更多
To solve the problem of low robustness of trackers under significant appearance changes in complex background,a novel moving target tracking method based on hierarchical deep features weighted fusion and correlation f...To solve the problem of low robustness of trackers under significant appearance changes in complex background,a novel moving target tracking method based on hierarchical deep features weighted fusion and correlation filter is proposed.Firstly,multi-layer features are extracted by a deep model pre-trained on massive object recognition datasets.The linearly separable features of Relu3-1,Relu4-1 and Relu5-4 layers from VGG-Net-19 are especially suitable for target tracking.Then,correlation filters over hierarchical convolutional features are learned to generate their correlation response maps.Finally,a novel approach of weight adjustment is presented to fuse response maps.The maximum value of the final response map is just the location of the target.Extensive experiments on the object tracking benchmark datasets demonstrate the high robustness and recognition precision compared with several state-of-the-art trackers under the different conditions.展开更多
In recent visual tracking research,correlation filter(CF)based trackers become popular because of their high speed and considerable accuracy.Previous methods mainly work on the extension of features and the solution o...In recent visual tracking research,correlation filter(CF)based trackers become popular because of their high speed and considerable accuracy.Previous methods mainly work on the extension of features and the solution of the boundary effect to learn a better correlation filter.However,the related studies are insufficient.By exploring the potential of trackers in these two aspects,a novel adaptive padding correlation filter(APCF)with feature group fusion is proposed for robust visual tracking in this paper based on the popular context-aware tracking framework.In the tracker,three feature groups are fused by use of the weighted sum of the normalized response maps,to alleviate the risk of drift caused by the extreme change of single feature.Moreover,to improve the adaptive ability of padding for the filter training of different object shapes,the best padding is selected from the preset pool according to tracking precision over the whole video,where tracking precision is predicted according to the prediction model trained by use of the sequence features of the first several frames.The sequence features include three traditional features and eight newly constructed features.Extensive experiments demonstrate that the proposed tracker is superior to most state-of-the-art correlation filter based trackers and has a stable improvement compared to the basic trackers.展开更多
When evaluating the track fusion algorithm,common accuracy indexes may fail to evaluate the fusion accuracy correctly when the state estimation and the real target cannot be one-to-one,and fail to effectively distingu...When evaluating the track fusion algorithm,common accuracy indexes may fail to evaluate the fusion accuracy correctly when the state estimation and the real target cannot be one-to-one,and fail to effectively distinguish the performance of the algorithm when the state estimation is similar.Therefore,it is necessary to construct a high-resolution evaluation index,which can evaluate the track fusion algorithm more accurately,reasonably and comprehensively.Firstly,the advant ages and disadvantages of the optimal subpattern assignment(OSPA)dis tance as the accuracy index to evaluate the track fusion algorithm are analyzed.Then,its deficiencies are improved by using the Hellinger distance instead of the original Euclidean distance,and the distance is index transformed.Finally,a new evaluation index for track fusion algorithms is proposed,which is the OSPA distance based on Hellinger distance and index transformation.The simulation results show that the new index can not only correctly evaluate the fusion precision,but also consider the state uncertainty,making that can evaluate the track fusion algorithm more sensitively,and effectively solves the sensitivity of the index to the cut-off parameter c through index transformation.展开更多
Multi-laser-target tracking is an important subject in the field of signal processing of laser warners. A clustering method is applied to the measurement of laser warner, and the space-time fusion for measurements in ...Multi-laser-target tracking is an important subject in the field of signal processing of laser warners. A clustering method is applied to the measurement of laser warner, and the space-time fusion for measurements in the same cluster is accomplished. Real-time tracking of multi-laser-target and real-time picking of multi-laser-signal are introduced using data fusion of the measurements. A prototype device of the algorithm is built up. The results of experiments show that the algorithm is very effective.展开更多
基金supported by the National Key R&D Plan"Intelligent Robots"Key Project of P.R.China(Grant No.2018YFB1308602)the National Natural Science Foundation of P.R.China(Grant No.61173184)+3 种基金the Chongqing Natural Science Foundation of P.R.China(Grant No.cstc2018jcyj AX0694)Research Project of Chongqing Big Data Application and Development Administration Bureau(No.22-30)Basic and Advanced Research Projects of CSTC(No.cstc2019jcyj-zdxmX0008)the Science and Technology Research Program of Chongqing Municipal Education Commission(Grant No.KJZD-K201900605)。
文摘Efficient Convolution Operator(ECO)algorithms have achieved impressive performances in visual tracking.However,its feature extraction network of ECO is unconducive for capturing the correlation features of occluded and blurred targets between long-range complex scene frames.More so,its fixed weight fusion strategy does not use the complementary properties of deep and shallow features.In this paper,we propose a new target tracking method,namely ECO++,using deep feature adaptive fusion in a complex scene,in the following two aspects:First,we constructed a new temporal convolution mode and used it to replace the underlying convolution layer in Conformer network to obtain an improved Conformer network.Second,we adaptively fuse the deep features,which output through the improved Conformer network,by combining the Peak to Sidelobe Ratio(PSR),frame smoothness scores and adaptive adjustment weight.Extensive experiments on the OTB-2013,OTB-2015,UAV123,and VOT2019 benchmarks demonstrate that the proposed approach outperforms the state-of-the-art algorithms in tracking accuracy and robustness in complex scenes with occluded,blurred,and fast-moving targets.
基金supported by the National Natural Science Foundation of China(62073036,62076031)Beijing Natural Science Foundation(4242049).
文摘In challenging situations,such as low illumination,rain,and background clutter,the stability of the thermal infrared(TIR)spectrum can help red,green,blue(RGB)visible spectrum to improve tracking performance.However,the high-level image information and the modality-specific features have not been sufficiently studied.The proposed correlation filter uses the fused saliency content map to improve filter training and extracts different features of modalities.The fused content map is intro-duced into the spatial regularization term of correlation filter to highlight the training samples in the content region.Furthermore,the fused content map can avoid the incompleteness of the con-tent region caused by challenging situations.Additionally,differ-ent features are extracted according to the modality characteris-tics and are fused by the designed response-level fusion stra-tegy.The alternating direction method of multipliers(ADMM)algorithm is used to solve the tracker training efficiently.Experi-ments on the large-scale benchmark datasets show the effec-tiveness of the proposed tracker compared to the state-of-the-art traditional trackers and the deep learning based trackers.
基金Project(2022YFC2406000)supported by the National Key R&D Program,ChinaProject(2022GDASZH-2022010107)supported by the Guangdong Academy of Science,China+4 种基金Project(2019BT02C629)supported by the Guangdong Special Support Program,ChinaProject(2022GDASZH-2022010203-003)supported by the GDAS’project of Science and Technology Development,ChinaProjects(2023B1212120008,2023B1212060045)supported by the Guangdong Province Science and Technology Plan Projects,ChinaProject(2023TQ07Z559)supported by the Special Support Foundation of Guangdong Province,ChinaProject(52105293)supported by the National Natural Science Foundation of China。
文摘Laser powder-bed fusion(LPBF)of Zn-0.8Cu(wt.%)alloys exhibits significant advantages in the customization of biodegradable bone implants.However,the formability of LPBFed Zn alloy is not sufficient due to the spheroidization during the interaction of powder and laser beam,of which the mechanism is still not well understood.In this study,the evolution of morphology and grain structure of the LPBFed Zn-Cu alloy was investigated based on single-track deposition experiments.As the scanning speed increases,the grain structure of a single track of Zn-Cu alloy gradually refines,but the formability deteriorates,leading to the defect’s formation in the subsequent fabrication.The Zn-Cu alloys fabricated by optimum processing parameters exhibit a tensile strength of 157.13 MPa,yield strength of 106.48 MPa and elongation of 14.7%.This work provides a comprehensive understanding of the processing optimization of Zn-Cu alloy,achieving LPBFed Zn-Cu alloy with high density and excellent mechanical properties.
基金Supported by the Science and Technology Key Project of Science and Technology Department of Henan Province(No.252102211041)the Key Research and Development Projects of Henan Province(No.231111212500).
文摘A distributed bearing-only target tracking algorithm based on variational Bayesian inference(VBI)under random measurement anomalies is proposed for the problem of adverse effect of random measurement anomalies on the state estimation accuracy of moving targets in bearing-only tracking scenarios.Firstly,the measurement information of each sensor is complemented by using triangulation under the distributed framework.Secondly,the Student-t distribution is selected to model the measurement likelihood probability density function,and the joint posteriori probability density function of the estimated variables is approximately decoupled by VBI.Finally,the estimation results of each local filter are sent to the fusion center and fed back to each local filter.The simulation results show that the proposed distributed bearing-only target tracking algorithm based on VBI in the presence of abnormal measurement noise comprehensively considers the influence of system nonlinearity and random anomaly of measurement noise,and has higher estimation accuracy and robustness than other existing algorithms in the above scenarios.
基金The National Natural Science Foundation of China(No.60672094,60673188,U0735004)the National High Technology Research and Development Program of China(863 Program)(No.2008AA01Z303)the National Basic Research Program of China (973 Program)(No.2009CB320804)
文摘To solve the mismatch between the candidate model and the reference model caused by the time change of the tracked head, a novel mean shift algorithm based on a fusion model is provided. A fusion model is employed to describe the tracked head by sampling the models of the fore-head and the back-head under different situations. Thus the fusion head reference model is represented by the color distribution estimated from both the fore- head and the back-head. The proposed tracking system is efficient and it is easy to realize the goal of continual tracking of the head by using the fusion model. The results show that the new tracker is robust up to a 360°rotation of the head on a cluttered background and the tracking precision is improved.
基金supported by the National Natural Science Foundation of China (60574022).
文摘A new distributed fusion method of radar/infrared （IR） tracking system based on separation and combination of the measurements is proposed by analyzing the influence of rate measurement. The rate information separated from the radar measurements together with measurements of IR form a pseudo vector of IR, and the corresponding filter is designed. The results indicate that the method not only makes a great improvement to the local tracker＇s performance, but also improves the global tracking precision efficiently.
基金supported by the National Natural Science Foundation of China(No.61871301)。
文摘The coalescence and missed detection are two key challenges in Multi-Target Tracking(MTT).To balance the tracking accuracy and real-time performance,the existing Random Finite Set(RFS)based filters are generally difficult to handle the above problems simultaneously,such as the Track-Oriented marginal Multi-Bernoulli/Poisson(TOMB/P)and Measurement-Oriented marginal Multi-Bernoulli/Poisson(MOMB/P)filters.Based on the Arithmetic Average(AA)fusion rule,this paper proposes a novel fusion framework for the Poisson Multi-Bernoulli(PMB)filter,which integrates both the advantages of the TOMB/P filter in dealing with missed detection and the advantages of the MOMB/P filter in dealing with coalescence.In order to fuse the different PMB distributions,the Bernoulli components in different Multi-Bernoulli(MB)distributions are associated with each other by Kullback-Leibler Divergence(KLD)minimization.Moreover,an adaptive AA fusion rule is designed on the basis of the exponential fusion weights,which utilizes the TOMB/P and MOMB/P updates to solve these difficulties in MTT.Finally,by comparing with the TOMB/P and MOMB/P filters,the performance of the proposed filter in terms of accuracy and efficiency is demonstrated in three challenging scenarios.
基金Supported by the Aviation Science Funds (20090580013)the Fundamental Research Funds for the Central Universities (ZYGX2009J092)
文摘The random noises of multi-sensor and the environment make observations uncertain and correlative, so the performance of fusion algorithms is reduced by using observations directly. To solve this problem, a multi-layer track fusion algorithm based on supporting degree matrix is proposed. Combined with the track fusion algorithm based on filtering step by step, it uses multi-sensor observations to establish supporting degree matrix and realize multi-layer fusion. Simulation results show its estimation precision is higher than the original algorithm and is increased by 20% around. Therefore, it solves the problem of target tracking further in the distributed track fusion system.
基金Supported by National Natural Science Foundation of China(Grant Nos.U20A20333,61906076,51875255,U1764257,U1762264),Jiangsu Provincial Natural Science Foundation of China(Grant Nos.BK20180100,BK20190853)Six Talent Peaks Project of Jiangsu Province(Grant No.2018-TD-GDZB-022)+1 种基金China Postdoctoral Science Foundation(Grant No.2020T130258)Jiangsu Provincial Key Research and Development Program of China(Grant No.BE2020083-2).
文摘Radar and LiDAR are two environmental sensors commonly used in autonomous vehicles,Lidars are accurate in determining objects’positions but significantly less accurate as Radars on measuring their velocities.However,Radars relative to Lidars are more accurate on measuring objects velocities but less accurate on determining their positions as they have a lower spatial resolution.In order to compensate for the low detection accuracy,incomplete target attributes and poor environmental adaptability of single sensors such as Radar and LiDAR,in this paper,an effective method for high-precision detection and tracking of surrounding targets of autonomous vehicles.By employing the Unscented Kalman Filter,Radar and LiDAR information is effectively fused to achieve high-precision detection of the position and speed information of targets around the autonomous vehicle.Finally,the real vehicle test under various driving environment scenarios is carried out.The experimental results show that the proposed sensor fusion method can effectively detect and track the vehicle peripheral targets with high accuracy.Compared with a single sensor,it has obvious advantages and can improve the intelligence level of autonomous cars.
基金This work is supported by the National Key R&D Program of China(Nos.2021YFF0502100 and 2021YFB2600900)the National Natural Science Foundation of China(Nos.52022085 and 52278461)the Sichuan Provincial Youth Science and Technology Innovation Team(No.2022JDTD0015),China.
文摘To accurately identify the potential contact loss of the China railway track system(CRTS)III prefabricated slab track,a finite element model with contact loss of self-compacting concrete(SCC)under transient impact was established.Then the vertical accelerations near impact points on the track slab surface were extracted to obtain damage-sensitive indices in the time and frequency domains.The indices were initially normalized to obtain independent items of evidence before the Dempster-Shafer(D-S)evidence theory was used to fuse these into one.Finally,a two-stage identification was performed to identify the damaged SCC area,comprising a rough identification(Stage I)and a precise identification(Stage II).The research results show that the damage indices extracted based on the transient impact response change abruptly at the damage location,and that can be used for damage identification.However,the use of a single index to determine the damage of the impact point may be misjudged.In Stage I,five damage indices of acceleration were fused to magnify the difference between the damaged point and undamaged point,thereby improving the accuracy of finding damage.In Stage II,in the area where more impact points were added,a fusion of three indices of acceleration response,that is,the absolute mean of the time domain,the maximum amplitude of the frequency domain,and the power density ratio,further narrowed down the area where damage exists.As a result,when the contact loss of SCC is greater than 50%along the thickness direction,the identification accuracy can be as high as 70%to 80%.The two-stage identification method proposed in this study can greatly improve the efficiency of interlayer damage detection of slab tracks and is expected to provide effective technical support for damage identification of track structures in the future.
基金This work was financially supported by the National Natural Science Foundation of China(Grant Nos.61575074,51805184 and 61475056)the Self-Research and Development Plan of Naval University of Engineering(Nos.2022505010 and 2022501140)the Plan for Strengthening Basic Disciplines of College of Ship and Ocean.The authors thank the Analytical and Testing Center of HUST for EBSD measurement.
文摘Laser powder bed fusion(LPBF)technology is a high-precision metal additive manufacturing(AM)technology.Due to the high specific strength of high strength aluminum alloys,high strength aluminum alloys fabricated by LPBF have broad application prospects in the field of light weighting.However,high strength aluminum alloys have high hot cracking susceptibility.In this study,an analysis of the hot cracking susceptibility as a function of processing parameters is presented for single tracks of LPBF processed(LPBFed)high strength Al–Cu–Mg–Mn alloy.The hot cracking in single tracks of LPBFed Al–Cu–Mg–Mn alloy is solidification cracking based on the experimental observations of microstructure.Combining Rosenthal simulations and spreading behavior of a single droplet,the critical scanning speed of single track with balling phenomenon was obtained.It was found that when the laser power was 200 W,the scanning speed exceeded 440.1 mm/s,the droplet will not be able to spread completely,which is consistent with the experimental result of 500 mm/s.Through the calculation and analysis of the microstructure and the existence time of the molten pool,it was pointed out that the reduction in the liquid phase caused by the high scanning speed,the shortening of the solidification time and the high stress caused by the high-temperature gradient promoted the generation of hot cracking.In summary,this work contains a practical guide to optimize processing parameters of LPBFed Al–Cu–Mg–Mn alloys,which provides a basis for fabricating thin walls and cubic samples without hot cracking.
基金funded by the National Natural Science Foundation of China(Grant No.52072408),author Y.C.
文摘Onboard visual object tracking in unmanned aerial vehicles(UAVs)has attractedmuch interest due to its versatility.Meanwhile,due to high precision,Siamese networks are becoming hot spots in visual object tracking.However,most Siamese trackers fail to balance the tracking accuracy and time within onboard limited computational resources of UAVs.To meet the tracking precision and real-time requirements,this paper proposes a Siamese dense pixel-level network for UAV object tracking named SiamDPL.Specifically,the Siamese network extracts features of the search region and the template region through a parameter-shared backbone network,then performs correlationmatching to obtain the candidate regionwith high similarity.To improve the matching effect of template and search features,this paper designs a dense pixel-level feature fusion module to enhance the matching ability by pixel-wise correlation and enrich the feature diversity by dense connection.An attention module composed of self-attention and channel attention is introduced to learn global context information and selectively emphasize the target feature region in the spatial and channel dimensions.In addition,a target localization module is designed to improve target location accuracy.Compared with other advanced trackers,experiments on two public benchmarks,which are UAV123@10fps and UAV20L fromthe unmanned air vehicle123(UAV123)dataset,show that SiamDPL can achieve superior performance and low complexity with a running speed of 100.1 fps on NVIDIA TITAN RTX.
基金the Australian Government Research Training Program Scholarship,and the Australian Research Council through Discovery Projects(DP110101653,DP130103592)。
文摘Laser powder bed fusion(LPBF)has made significant progress in producing solid and porous metal parts with complex shapes and geometries.However,LPBF produced parts often have defects(e.g.,porosity,residual stress,and incomplete melting)that hinder its large-scale industrial commercialization.The LPBF process involves complex heat transfer andfluidflow,and the melt pool is a critical component of the process.The melt pool stability is a critical factor in determining the microstructure,mechanical properties,and corrosion resistance of LPBF produced metal parts.Furthermore,optimizing process parameters for new materials and designed structures is challenging due to the complexity of the LPBF process.This requires numerous trial-and-error cycles to minimize defects and enhance properties.This review examines the behavior of the melt pool during the LPBF process,including its effects and formation mechanisms.This article summarizes the experimental results and simulations of melt pool and identifies various factors that influence its behavior,which facilitates a better understanding of the melt pool's behavior during LPBF.This review aims to highlight key aspects of the investigation of melt pool tracks and microstructural characterization,with the goal of enhancing a better understanding of the relationship between alloy powder-process-microstructure-properties in LPBF from both single-and multi-melt pool track perspectives.By identifying the challenges and opportunities in investigating single-and multi-melt pool tracks,this review could contribute to the advancement of LPBF processes,optimal process window,and quality optimization,which ultimately improves accuracy in process parameters and efficiency in qualifying alloy powders.
文摘The paper analyses the improvement of track loss in clutter with multisensor data fusion.By a determination of the transition probability density function for the fusion prediction error, one can study the mechanism of track loss analytically. With nearest-neighbor association algorithm. The paper we studies the fused tracking performance parameters, such as mean time to lose fused track and the cumulative probability of lost fused track versus the normalized clutter density, for track continuation and track initiation, respectively. A comparison of the results obtained with the case of a single sensor is presented. These results show that the fused tracks of multisensor reduce the possibility of track loss and improve the tracking performance. The analysis is of great importance for further understanding the action of data fusion.
文摘Single passive sensor tracking algorithms have four disadvantages: bad stability, longdynamic time, big bias and sensitive to initial conditions. So the corresponding fusion algorithm results in bad performance. A new error analysis method for two passive sensor tracking system is presented and the error equations are deduced in detail. Based on the equations, we carry out theoretical computation and Monte Carlo computer simulation. The results show the correctness of our error computation equations. With the error equations, we present multiple 'two station'fusion algorithm using adaptive pseudo measurement equations. This greatly enhances the tracking performance and makes the algorithm convergent very fast and not sensitive to initial conditions.Simulation results prove the correctness of our new algorithm.
文摘To solve the problem of low robustness of trackers under significant appearance changes in complex background,a novel moving target tracking method based on hierarchical deep features weighted fusion and correlation filter is proposed.Firstly,multi-layer features are extracted by a deep model pre-trained on massive object recognition datasets.The linearly separable features of Relu3-1,Relu4-1 and Relu5-4 layers from VGG-Net-19 are especially suitable for target tracking.Then,correlation filters over hierarchical convolutional features are learned to generate their correlation response maps.Finally,a novel approach of weight adjustment is presented to fuse response maps.The maximum value of the final response map is just the location of the target.Extensive experiments on the object tracking benchmark datasets demonstrate the high robustness and recognition precision compared with several state-of-the-art trackers under the different conditions.
基金supported by the National KeyResearch and Development Program of China(2018AAA0103203)the National Natural Science Foundation of China(62073036,62076031)the Beijing Natural Science Foundation(4202071)。
文摘In recent visual tracking research,correlation filter(CF)based trackers become popular because of their high speed and considerable accuracy.Previous methods mainly work on the extension of features and the solution of the boundary effect to learn a better correlation filter.However,the related studies are insufficient.By exploring the potential of trackers in these two aspects,a novel adaptive padding correlation filter(APCF)with feature group fusion is proposed for robust visual tracking in this paper based on the popular context-aware tracking framework.In the tracker,three feature groups are fused by use of the weighted sum of the normalized response maps,to alleviate the risk of drift caused by the extreme change of single feature.Moreover,to improve the adaptive ability of padding for the filter training of different object shapes,the best padding is selected from the preset pool according to tracking precision over the whole video,where tracking precision is predicted according to the prediction model trained by use of the sequence features of the first several frames.The sequence features include three traditional features and eight newly constructed features.Extensive experiments demonstrate that the proposed tracker is superior to most state-of-the-art correlation filter based trackers and has a stable improvement compared to the basic trackers.
基金the Natural Science Foundation of Hebei Province(No.F2017506006)。
文摘When evaluating the track fusion algorithm,common accuracy indexes may fail to evaluate the fusion accuracy correctly when the state estimation and the real target cannot be one-to-one,and fail to effectively distinguish the performance of the algorithm when the state estimation is similar.Therefore,it is necessary to construct a high-resolution evaluation index,which can evaluate the track fusion algorithm more accurately,reasonably and comprehensively.Firstly,the advant ages and disadvantages of the optimal subpattern assignment(OSPA)dis tance as the accuracy index to evaluate the track fusion algorithm are analyzed.Then,its deficiencies are improved by using the Hellinger distance instead of the original Euclidean distance,and the distance is index transformed.Finally,a new evaluation index for track fusion algorithms is proposed,which is the OSPA distance based on Hellinger distance and index transformation.The simulation results show that the new index can not only correctly evaluate the fusion precision,but also consider the state uncertainty,making that can evaluate the track fusion algorithm more sensitively,and effectively solves the sensitivity of the index to the cut-off parameter c through index transformation.
基金University Doctor Subject Foundation of China (20060699024)
文摘Multi-laser-target tracking is an important subject in the field of signal processing of laser warners. A clustering method is applied to the measurement of laser warner, and the space-time fusion for measurements in the same cluster is accomplished. Real-time tracking of multi-laser-target and real-time picking of multi-laser-signal are introduced using data fusion of the measurements. A prototype device of the algorithm is built up. The results of experiments show that the algorithm is very effective.
