Visual motion segmentation(VMS)is an important and key part of many intelligent crowd systems.It can be used to figure out the flow behavior through a crowd and to spot unusual life-threatening incidents like crowd st...Visual motion segmentation(VMS)is an important and key part of many intelligent crowd systems.It can be used to figure out the flow behavior through a crowd and to spot unusual life-threatening incidents like crowd stampedes and crashes,which pose a serious risk to public safety and have resulted in numerous fatalities over the past few decades.Trajectory clustering has become one of the most popular methods in VMS.However,complex data,such as a large number of samples and parameters,makes it difficult for trajectory clustering to work well with accurate motion segmentation results.This study introduces a spatial-angular stacked sparse autoencoder model(SA-SSAE)with l2-regularization and softmax,a powerful deep learning method for visual motion segmentation to cluster similar motion patterns that belong to the same cluster.The proposed model can extract meaningful high-level features using only spatial-angular features obtained from refined tracklets(a.k.a‘trajectories’).We adopt l2-regularization and sparsity regularization,which can learn sparse representations of features,to guarantee the sparsity of the autoencoders.We employ the softmax layer to map the data points into accurate cluster representations.One of the best advantages of the SA-SSAE framework is it can manage VMS even when individuals move around randomly.This framework helps cluster the motion patterns effectively with higher accuracy.We put forward a new dataset with itsmanual ground truth,including 21 crowd videos.Experiments conducted on two crowd benchmarks demonstrate that the proposed model can more accurately group trajectories than the traditional clustering approaches used in previous studies.The proposed SA-SSAE framework achieved a 0.11 improvement in accuracy and a 0.13 improvement in the F-measure compared with the best current method using the CUHK dataset.展开更多
The neural correlates of the motion priming were examined in normal young subjects using event-related brain potentials (ERPs) and functional magnetic resonance imaging (fMRI). Visual motion perception can be uncon-sc...The neural correlates of the motion priming were examined in normal young subjects using event-related brain potentials (ERPs) and functional magnetic resonance imaging (fMRI). Visual motion perception can be uncon-sciously biased in favor of a particular direction by a pre-ceding motion in that direction. Motion priming first in-volved an enhancement of ERP amplitude about 100 ms fol-lowing the onset of motion. The amplitudes of ERP compo-nents after 350 ms were also increased. The fMRI results suggest that the early-latency effect reflects modulation of neural responses in extrastriate cortex. Higher-level visual processing areas, including cortical regions MT/MST and the intraparietal cortices were also activated. The findingsprovide direct evidence that unconscious priming of motion perception is the result of interaction of direction-selective neural responses to motion stimuli. The results cannot be accounted for by refractoriness of neural responses, but in-stead support a theory of motion展开更多
Understanding the process of adaptation is a key mission in modern evolutionary biology.Animals living at high elevations face challenges in energy meta bolism due to several environmental constraints(e.g., oxygen sup...Understanding the process of adaptation is a key mission in modern evolutionary biology.Animals living at high elevations face challenges in energy meta bolism due to several environmental constraints(e.g., oxygen supply, food availa bility,and movement time). Animal behavioral processes are intimately related to energy meta bolism, and therefore, behavioral modifica tions are expected to be an important mechanism for high-elevation adaptation. We tested this behavioral adaptation hypothesis using va ria tions of motion visual displays in toad-headed agamid lizards of the genus Phr ynocephalus. We predicted tha t complexity of visual motion displays would decrease with the increase of elevation, because motion visual displays are energetically costly. Displays of 12 Phr ynocephalus species were collected with elevations ranging from sea level to 4600 m. We quantified display complexity using the number of display components, display duration, pathways of display components, as well as display speed for each species. Association between display complexity and elevation was analyzed using the phylogenetic generalized least squares(PGLS)model. We found that both the number of display components and the average value of tail coil speed were negatively correlated with elevation, suggesting that toad-headed lizards living at high-elevation areas reduced their display complexity to cope with the environmental constraints. Our research provides direct evidence for high-elevation adaptation from a behavioral aspect and illustrates the potential impacts of environment heterogeneity on motion visual display diversification.展开更多
The objective of this study is to experimentally visualize traveling vortices in the boundary layer on a rotating disk under orbital motion. The orbital radius is half of the disk’s diameter (200 mm) and the maximum ...The objective of this study is to experimentally visualize traveling vortices in the boundary layer on a rotating disk under orbital motion. The orbital radius is half of the disk’s diameter (200 mm) and the maximum speed of orbital motion is 500 revolutions per minute. The Reynolds number in the pure-rotation case is 2.77 × 105. The characteristics of two types of traveling vortices are visualized by a smoke-wire method. The first type is transition vortices. In the pure-rotation case, they arise at circumferentially equal intervals, and are not traveling but stationary relative to the rotational disk. The result of visualization of this type shows that the intervals between transient vortices change in a circumferential direction, or in an orbital radial direction, on the rotating disk under orbital motion. The second type is new arc-shaped vortices that correspond to low-frequency disturbances. As orbital speed increases, the radial traveling velocities of the low-frequency disturbances increase and the intervals between low-frequency disturbances decrease.展开更多
Simulators play an important role in training surgery residents to perform laparoscopy surgery. Some of these simulators have the capability to track tool motion to assess performance. However, most have not utilized ...Simulators play an important role in training surgery residents to perform laparoscopy surgery. Some of these simulators have the capability to track tool motion to assess performance. However, most have not utilized the data to analyze trainee performance in a meaningful way. The alpha shape method can be used to construct a geometric surface based on motion data to enable visualization of the performance, while the surface derivative (surface/time to completion)—efficiency—can be used as a metric to evaluate complex surgical performance. The utility of the alpha shape method was demonstrated in a pick-and-place task, where the motion path of laparoscopic graspers was recorded by a position sensor, miniBIRD 500?. An alpha shape method was used to measure the surface area of the 3D points in space occupied by the tool tips during task performance. Results show that the surface derivative measure alone may be able to model the speed-accuracy tradeoff function, thereby simplifying the analysis and evaluation of complex motion in surgical performance.展开更多
In this paper,we present a novel algorithm for odometry estimation based on ceiling vision.The main contribution of this algorithm is the introduction of principal direction detection that can greatly reduce error acc...In this paper,we present a novel algorithm for odometry estimation based on ceiling vision.The main contribution of this algorithm is the introduction of principal direction detection that can greatly reduce error accumulation problem in most visual odometry estimation approaches.The principal direction is defned based on the fact that our ceiling is flled with artifcial vertical and horizontal lines which can be used as reference for the current robot s heading direction.The proposed approach can be operated in real-time and it performs well even with camera s disturbance.A moving low-cost RGB-D camera（Kinect）,mounted on a robot,is used to continuously acquire point clouds.Iterative closest point（ICP） is the common way to estimate the current camera position by registering the currently captured point cloud to the previous one.However,its performance sufers from data association problem or it requires pre-alignment information.The performance of the proposed principal direction detection approach does not rely on data association knowledge.Using this method,two point clouds are properly pre-aligned.Hence,we can use ICP to fne-tune the transformation parameters and minimize registration error.Experimental results demonstrate the performance and stability of the proposed system under disturbance in real-time.Several indoor tests are carried out to show that the proposed visual odometry estimation method can help to signifcantly improve the accuracy of simultaneous localization and mapping（SLAM）.展开更多
The relative pose between inertial and visual sensors equipped in autonomous robots is calibrated in two steps. In the first step, the sensing system is moved along a line, the orientations in the relative pose are co...The relative pose between inertial and visual sensors equipped in autonomous robots is calibrated in two steps. In the first step, the sensing system is moved along a line, the orientations in the relative pose are computed from at least five corresponding points in the two images captured before and after the movement. In the second step, the translation parameters in the relative pose are obtained with at least two corresponding points in the two images captured before and after one step motion. Experiments are conducted to verify the effectiveness of the proposed method.展开更多
基金This research work is supported by the Deputyship of Research&Innovation,Ministry of Education in Saudi Arabia(Grant Number 758).
文摘Visual motion segmentation(VMS)is an important and key part of many intelligent crowd systems.It can be used to figure out the flow behavior through a crowd and to spot unusual life-threatening incidents like crowd stampedes and crashes,which pose a serious risk to public safety and have resulted in numerous fatalities over the past few decades.Trajectory clustering has become one of the most popular methods in VMS.However,complex data,such as a large number of samples and parameters,makes it difficult for trajectory clustering to work well with accurate motion segmentation results.This study introduces a spatial-angular stacked sparse autoencoder model(SA-SSAE)with l2-regularization and softmax,a powerful deep learning method for visual motion segmentation to cluster similar motion patterns that belong to the same cluster.The proposed model can extract meaningful high-level features using only spatial-angular features obtained from refined tracklets(a.k.a‘trajectories’).We adopt l2-regularization and sparsity regularization,which can learn sparse representations of features,to guarantee the sparsity of the autoencoders.We employ the softmax layer to map the data points into accurate cluster representations.One of the best advantages of the SA-SSAE framework is it can manage VMS even when individuals move around randomly.This framework helps cluster the motion patterns effectively with higher accuracy.We put forward a new dataset with itsmanual ground truth,including 21 crowd videos.Experiments conducted on two crowd benchmarks demonstrate that the proposed model can more accurately group trajectories than the traditional clustering approaches used in previous studies.The proposed SA-SSAE framework achieved a 0.11 improvement in accuracy and a 0.13 improvement in the F-measure compared with the best current method using the CUHK dataset.
基金This work was supported by the National Natural Science Foundation of China (Grant No. 30070262) Multi-disciplinary Research Program of the Chinese Academy of Sciences (CAS) (Grant No. KJCX1-07) the Hundred Talents Program of CAS and American NIH (AG
文摘The neural correlates of the motion priming were examined in normal young subjects using event-related brain potentials (ERPs) and functional magnetic resonance imaging (fMRI). Visual motion perception can be uncon-sciously biased in favor of a particular direction by a pre-ceding motion in that direction. Motion priming first in-volved an enhancement of ERP amplitude about 100 ms fol-lowing the onset of motion. The amplitudes of ERP compo-nents after 350 ms were also increased. The fMRI results suggest that the early-latency effect reflects modulation of neural responses in extrastriate cortex. Higher-level visual processing areas, including cortical regions MT/MST and the intraparietal cortices were also activated. The findingsprovide direct evidence that unconscious priming of motion perception is the result of interaction of direction-selective neural responses to motion stimuli. The results cannot be accounted for by refractoriness of neural responses, but in-stead support a theory of motion
基金supported by grants from the National Natural Science Foundation of China(grant numbers:31872233,31572273)to Y.QI。
文摘Understanding the process of adaptation is a key mission in modern evolutionary biology.Animals living at high elevations face challenges in energy meta bolism due to several environmental constraints(e.g., oxygen supply, food availa bility,and movement time). Animal behavioral processes are intimately related to energy meta bolism, and therefore, behavioral modifica tions are expected to be an important mechanism for high-elevation adaptation. We tested this behavioral adaptation hypothesis using va ria tions of motion visual displays in toad-headed agamid lizards of the genus Phr ynocephalus. We predicted tha t complexity of visual motion displays would decrease with the increase of elevation, because motion visual displays are energetically costly. Displays of 12 Phr ynocephalus species were collected with elevations ranging from sea level to 4600 m. We quantified display complexity using the number of display components, display duration, pathways of display components, as well as display speed for each species. Association between display complexity and elevation was analyzed using the phylogenetic generalized least squares(PGLS)model. We found that both the number of display components and the average value of tail coil speed were negatively correlated with elevation, suggesting that toad-headed lizards living at high-elevation areas reduced their display complexity to cope with the environmental constraints. Our research provides direct evidence for high-elevation adaptation from a behavioral aspect and illustrates the potential impacts of environment heterogeneity on motion visual display diversification.
文摘The objective of this study is to experimentally visualize traveling vortices in the boundary layer on a rotating disk under orbital motion. The orbital radius is half of the disk’s diameter (200 mm) and the maximum speed of orbital motion is 500 revolutions per minute. The Reynolds number in the pure-rotation case is 2.77 × 105. The characteristics of two types of traveling vortices are visualized by a smoke-wire method. The first type is transition vortices. In the pure-rotation case, they arise at circumferentially equal intervals, and are not traveling but stationary relative to the rotational disk. The result of visualization of this type shows that the intervals between transient vortices change in a circumferential direction, or in an orbital radial direction, on the rotating disk under orbital motion. The second type is new arc-shaped vortices that correspond to low-frequency disturbances. As orbital speed increases, the radial traveling velocities of the low-frequency disturbances increase and the intervals between low-frequency disturbances decrease.
文摘Simulators play an important role in training surgery residents to perform laparoscopy surgery. Some of these simulators have the capability to track tool motion to assess performance. However, most have not utilized the data to analyze trainee performance in a meaningful way. The alpha shape method can be used to construct a geometric surface based on motion data to enable visualization of the performance, while the surface derivative (surface/time to completion)—efficiency—can be used as a metric to evaluate complex surgical performance. The utility of the alpha shape method was demonstrated in a pick-and-place task, where the motion path of laparoscopic graspers was recorded by a position sensor, miniBIRD 500?. An alpha shape method was used to measure the surface area of the 3D points in space occupied by the tool tips during task performance. Results show that the surface derivative measure alone may be able to model the speed-accuracy tradeoff function, thereby simplifying the analysis and evaluation of complex motion in surgical performance.
文摘In this paper,we present a novel algorithm for odometry estimation based on ceiling vision.The main contribution of this algorithm is the introduction of principal direction detection that can greatly reduce error accumulation problem in most visual odometry estimation approaches.The principal direction is defned based on the fact that our ceiling is flled with artifcial vertical and horizontal lines which can be used as reference for the current robot s heading direction.The proposed approach can be operated in real-time and it performs well even with camera s disturbance.A moving low-cost RGB-D camera（Kinect）,mounted on a robot,is used to continuously acquire point clouds.Iterative closest point（ICP） is the common way to estimate the current camera position by registering the currently captured point cloud to the previous one.However,its performance sufers from data association problem or it requires pre-alignment information.The performance of the proposed principal direction detection approach does not rely on data association knowledge.Using this method,two point clouds are properly pre-aligned.Hence,we can use ICP to fne-tune the transformation parameters and minimize registration error.Experimental results demonstrate the performance and stability of the proposed system under disturbance in real-time.Several indoor tests are carried out to show that the proposed visual odometry estimation method can help to signifcantly improve the accuracy of simultaneous localization and mapping（SLAM）.
基金supported by National Natural Science Foundation of China (Nos. 60805038 and 60725309)Beijing Natural Science Foundation (No. 4082032)
文摘The relative pose between inertial and visual sensors equipped in autonomous robots is calibrated in two steps. In the first step, the sensing system is moved along a line, the orientations in the relative pose are computed from at least five corresponding points in the two images captured before and after the movement. In the second step, the translation parameters in the relative pose are obtained with at least two corresponding points in the two images captured before and after one step motion. Experiments are conducted to verify the effectiveness of the proposed method.
