This paper addresses a sensor-based simultaneous localization and mapping （SLAM） algorithm for camera tracking in a virtual studio environment. The traditional camera tracking methods in virtual studios are vision-b...This paper addresses a sensor-based simultaneous localization and mapping （SLAM） algorithm for camera tracking in a virtual studio environment. The traditional camera tracking methods in virtual studios are vision-based or sensor-based. However, the chroma keying process in virtual studios requires color cues, such as blue background, to segment foreground objects to be inserted into images and videos. Chroma keying limits the application of vision-based tracking methods in virtual studios since the background cannot provide enough feature information. Furthermore, the conventional sensor-based tracking approaches suffer from the jitter, drift or expensive computation due to the characteristics of individual sensor system. Therefore, the SLAM techniques from the mobile robot area are first investigated and adapted to the camera tracking area. Then, a sensor-based SLAM extension algorithm for two dimensional （2D） camera tracking in virtual studio is described. Also, a technique called map adjustment is proposed to increase the accuracy＇ and efficiency of the algorithm. The feasibility and robustness of the algorithm is shown by experiments. The simulation results demonstrate that the sensor-based SLAM algorithm can satisfy the fundamental 2D camera tracking requirement in virtual studio environment.展开更多
In this paper, we proposed an optimized real-time hybrid cooperative multi-camera tracking system for large-scale au-tomate surveillance based on embedded smart cameras including stationary cameras and moving pan/tilt...In this paper, we proposed an optimized real-time hybrid cooperative multi-camera tracking system for large-scale au-tomate surveillance based on embedded smart cameras including stationary cameras and moving pan/tilt/zoom (PTZ) cameras embedded with TI DSP TMS320DM6446 for intelligent visual analysis. Firstly, the overlapping areas and projection relations between adjacent cameras' field of view (FOV) is calculated. Based on the relations of FOV ob-tained and tracking information of each single camera, a homography based target handover procedure is done for long-term multi-camera tracking. After that, we fully implemented the tracking system on the embedded platform de-veloped by our group. Finally, to reduce the huge computational complexity, a novel hierarchical optimization method is proposed. Experimental results demonstrate the robustness and real-time efficiency in dynamic real-world environ-ments and the computational burden is significantly reduced by 98.84%. Our results demonstrate that our proposed sys-tem is capable of tracking targets effectively and achieve large-scale surveillance with clear detailed close-up visual features capturing and recording in dynamic real-life environments.展开更多
An adaptive human tracking method across spatially separated surveillance cameras with non-overlapping fields of views （FOVs） is proposed. The method relies on the two cues of the human appearance model and spatio-t...An adaptive human tracking method across spatially separated surveillance cameras with non-overlapping fields of views （FOVs） is proposed. The method relies on the two cues of the human appearance model and spatio-temporal information between cameras. For the human appearance model, an HSV color histogram is extracted from different human body parts （head, torso, and legs）, then a weighted algorithm is used to compute the similarity distance of two people. Finally, a similarity sorting algorithm with two thresholds is exploited to find the correspondence. The spatio- temporal information is established in the learning phase and is updated incrementally according to the latest correspondence. The experimental results prove that the proposed human tracking method is effective without requiring camera calibration and it becomes more accurate over time as new observations are accumulated.展开更多
Mobile target tracking is a necessary function of some emerging application domains, such as virtual reality, smart home and intelligent healthcare. However, existing portable devices for target tracking are resource ...Mobile target tracking is a necessary function of some emerging application domains, such as virtual reality, smart home and intelligent healthcare. However, existing portable devices for target tracking are resource intensive and high-cost. Camera tracking is an effective location tracking way for those emerging applications which can reuse the existing ubiquitous video monitoring system. This paper proposes a dynamic community-based camera collaboration(D3C) framework for target location and tracking. The contributions of D3C mainly include that(1) nonlinear perspective projection model is selected as the camera sensing model and sequential Monte Carlo is employed to predict the target location;(2) a dynamic collaboration scheme is proposed, it is based on the local community-detection theory deriving from social network analysis. The performance of proposed approach is validated by both synthetic datasets and real-world application. The experiment results show that D3C meets the versatility, real-time and fault tolerance requirements of target tracking applications.展开更多
Most sensors or cameras discussed in the sensor network community are usually 3D homogeneous, even though their2 D coverage areas in the ground plane are heterogeneous. Meanwhile, observed objects of camera networks a...Most sensors or cameras discussed in the sensor network community are usually 3D homogeneous, even though their2 D coverage areas in the ground plane are heterogeneous. Meanwhile, observed objects of camera networks are usually simplified as 2D points in previous literature. However in actual application scenes, not only cameras are always heterogeneous with different height and action radiuses, but also the observed objects are with 3D features（i.e., height）. This paper presents a sensor planning formulation addressing the efficiency enhancement of visual tracking in 3D heterogeneous camera networks that track and detect people traversing a region. The problem of sensor planning consists of three issues：（i） how to model the 3D heterogeneous cameras;（ii） how to rank the visibility, which ensures that the object of interest is visible in a camera＇s field of view;（iii） how to reconfigure the 3D viewing orientations of the cameras. This paper studies the geometric properties of 3D heterogeneous camera networks and addresses an evaluation formulation to rank the visibility of observed objects. Then a sensor planning method is proposed to improve the efficiency of visual tracking. Finally, the numerical results show that the proposed method can improve the tracking performance of the system compared to the conventional strategies.展开更多
The aim of this study is to propose a novel system that has an ability to detect intra-fractional motion during radiotherapy treatment in real-time using three-dimensional surface taken by a depth camera, Microsoft Ki...The aim of this study is to propose a novel system that has an ability to detect intra-fractional motion during radiotherapy treatment in real-time using three-dimensional surface taken by a depth camera, Microsoft Kinect v1. Our approach introduces three new aspects for three-dimensional surface tracking in radiotherapy treatment. The first aspect is a new algorithm for noise reduction of depth values. Ueda’s algorithm was implemented and enabling a fast least square regression of depth values. The second aspect is an application for detection of patient’s motion at multiple points in thracoabdominal regions. The third aspect is an estimation of three-dimensional surface from multiple depth values. For evaluation of noise reduction by Ueda’s algorithm, two respiratory patterns are measured by the Kinect as well as a laser range meter. The resulting cross correlation coefficients between the laser range meter and the Kinect were 0.982 for abdominal respiration and 0.995 for breath holding. Moreover, the mean cross correlation coefficients between the signals of our system and the signals of Anzai with respect to participant’s respiratory motion were 0.90 for thoracic respiration and 0.93 for abdominal respiration, respectively. These results proved that the performance of the developed system was comparable to existing motion monitoring devices. Reconstruction of three-dimensional surface also enabled us to detect the irregular motion and breathing arrest by comparing the averaged depth with predefined threshold values.展开更多
The paper presents a web based vision system using a networked IP camera for tracking objects of interest. Three critical issues are addressed in this paper. First is the detection of moving objects in the foreground;...The paper presents a web based vision system using a networked IP camera for tracking objects of interest. Three critical issues are addressed in this paper. First is the detection of moving objects in the foreground;second is the control of pan-tilt-zoom (PTZ) IP cameras based on object location;and third is the collaboration of multiple cameras over the network to track objects of interests independently. The developed system utilized a network of PTZ cameras along with a number of software tools for this implementation. The system was able to track a single and multiple objects successfully. The difficulties in the detection of moving objects are also analyzed while multiple cameras are collaborating over a network utilizing PTZ cameras.展开更多
To track human across non-overlapping cameras in depression angles for applications such as multi-airplane visual human tracking and urban multi-camera surveillance,an adaptive human tracking method is proposed,focusi...To track human across non-overlapping cameras in depression angles for applications such as multi-airplane visual human tracking and urban multi-camera surveillance,an adaptive human tracking method is proposed,focusing on both feature representation and human tracking mechanism.Feature representation describes individual by using both improved local appearance descriptors and statistical geometric parameters.The improved feature descriptors can be extracted quickly and make the human feature more discriminative.Adaptive human tracking mechanism is based on feature representation and it arranges the human image blobs in field of view into matrix.Primary appearance models are created to include the maximum inter-camera appearance information captured from different visual angles.The persons appeared in camera are first filtered by statistical geometric parameters.Then the one among the filtered persons who has the maximum matching scale with the primary models is determined to be the target person.Subsequently,the image blobs of the target person are used to update and generate new primary appearance models for the next camera,thus being robust to visual angle changes.Experimental results prove the excellence of the feature representation and show the good generalization capability of tracking mechanism as well as its robustness to condition variables.展开更多
为提高无人车障碍物检测跟踪的精度和稳定性,首先针对YOLO v5(You only look once version 5,YOLO v5)网络存在的语义信息和候选框信息丢失的问题,引入深度可分离空洞空间金字塔结构与目标框加权融合算法完成对网络的优化;其次针对单阶...为提高无人车障碍物检测跟踪的精度和稳定性,首先针对YOLO v5(You only look once version 5,YOLO v5)网络存在的语义信息和候选框信息丢失的问题,引入深度可分离空洞空间金字塔结构与目标框加权融合算法完成对网络的优化;其次针对单阶段障碍物点云聚类精度低的问题,设计一种考虑点云距离与外轮廓连续性的两阶段障碍物点云聚类方法并完成三维包围盒的建立;最后将注意力机制引入MobileNet使网络更加聚焦于目标对象特有的视觉特征,并综合利用视觉特征和三维点云信息共同构建关联性度量指标,提高匹配精度。利用KITTI数据集对构建的障碍物目标检测、跟踪与测速算法进行仿真测试,并搭建实车平台进行真实环境试验,验证所提算法的有效性和真实环境可迁移性。展开更多
针对当前视觉同时定位与建图(Simultaneous Localization and Mapping,SLAM)面对如纹理稀疏、光照变化强烈及图像模糊等挑战性场景时,普遍存在的前端特征跟踪鲁棒性不足的问题,提出了一个鲁棒的多相机定位系统,并对关键技术进行了深入...针对当前视觉同时定位与建图(Simultaneous Localization and Mapping,SLAM)面对如纹理稀疏、光照变化强烈及图像模糊等挑战性场景时,普遍存在的前端特征跟踪鲁棒性不足的问题,提出了一个鲁棒的多相机定位系统,并对关键技术进行了深入的研究与优化。该系统设计了一种优于主流方案的前端跟踪算法,通过融合惯性测量单元(Inertial Measurement Unit,IMU)测量数据实现特征点重投影预测,并对跟踪的灰度图进行动态校正,有效提升了复杂场景下特征跟踪的成功率和稳定性。此外,该系统利用多相机观测信息构建了具备3层自适应置信度加权算法的状态估计器,并将卷积神经网络运用于交叉回环检测,有效提高了回环检测的成功率与准确率。通过一系列公开数据集的实验,验证了该多相机定位算法在精度和稳定性方面已达到最先进技术水平,且在本地环境中的测试结果也证实了该系统在实际应用中的可行性与有效性。展开更多
Three-dimensional(3D)modeling is an important topic in computer graphics and computer vision.In recent years,the introduction of consumer-grade depth cameras has resulted in profound advances in 3D modeling.Starting w...Three-dimensional(3D)modeling is an important topic in computer graphics and computer vision.In recent years,the introduction of consumer-grade depth cameras has resulted in profound advances in 3D modeling.Starting with the basic data structure,this survey reviews the latest developments of 3D modeling based on depth cameras,including research works on camera tracking,3D object and scene reconstruction,and high-quality texture reconstruction.We also discuss the future work and possible solutions for 3D modeling based on the depth camera.展开更多
针对在无人机高速运动场景下,相关滤波跟踪算法存在边界效应和滤波器退化等问题,提出了一种融合相机运动补偿的自适应时空正则化的无人机跟踪相关滤波算法。首先,在相关滤波器中设计了一种自适应空间正则化方法来缓解边界效应;其次,为...针对在无人机高速运动场景下,相关滤波跟踪算法存在边界效应和滤波器退化等问题,提出了一种融合相机运动补偿的自适应时空正则化的无人机跟踪相关滤波算法。首先,在相关滤波器中设计了一种自适应空间正则化方法来缓解边界效应;其次,为防止滤波器退化,设计了基于高置信度样本的时间正则化方法及优化更新策略,同时利用交替方向乘子法(Alternating Direction Method of Multipliers,ADMM)优化目标函数的求解,保证了算法的运行效率;然后,设计了快速尺度滤波器,实现目标尺度的快速估计;最后,提出了一种鲁棒性的跟踪不确定性规则及基于相机运动补偿的重检测器,使得目标丢失后可及时恢复。实验结果表明,提出的算法在无人机数据集上的精确度和成功率分别可达0.739和0.634,与ECO_HC(Efficient Convolution Operators-Hand Crafted)算法相比分别提升了1.65%和6.9%,与同类主流算法相比,有效地提升了跟踪时的精确度和成功率,经历快速运动、目标遮挡等情况时应用该算法的无人机也表现出良好的跟踪性能。展开更多
文摘This paper addresses a sensor-based simultaneous localization and mapping （SLAM） algorithm for camera tracking in a virtual studio environment. The traditional camera tracking methods in virtual studios are vision-based or sensor-based. However, the chroma keying process in virtual studios requires color cues, such as blue background, to segment foreground objects to be inserted into images and videos. Chroma keying limits the application of vision-based tracking methods in virtual studios since the background cannot provide enough feature information. Furthermore, the conventional sensor-based tracking approaches suffer from the jitter, drift or expensive computation due to the characteristics of individual sensor system. Therefore, the SLAM techniques from the mobile robot area are first investigated and adapted to the camera tracking area. Then, a sensor-based SLAM extension algorithm for two dimensional （2D） camera tracking in virtual studio is described. Also, a technique called map adjustment is proposed to increase the accuracy＇ and efficiency of the algorithm. The feasibility and robustness of the algorithm is shown by experiments. The simulation results demonstrate that the sensor-based SLAM algorithm can satisfy the fundamental 2D camera tracking requirement in virtual studio environment.
文摘In this paper, we proposed an optimized real-time hybrid cooperative multi-camera tracking system for large-scale au-tomate surveillance based on embedded smart cameras including stationary cameras and moving pan/tilt/zoom (PTZ) cameras embedded with TI DSP TMS320DM6446 for intelligent visual analysis. Firstly, the overlapping areas and projection relations between adjacent cameras' field of view (FOV) is calculated. Based on the relations of FOV ob-tained and tracking information of each single camera, a homography based target handover procedure is done for long-term multi-camera tracking. After that, we fully implemented the tracking system on the embedded platform de-veloped by our group. Finally, to reduce the huge computational complexity, a novel hierarchical optimization method is proposed. Experimental results demonstrate the robustness and real-time efficiency in dynamic real-world environ-ments and the computational burden is significantly reduced by 98.84%. Our results demonstrate that our proposed sys-tem is capable of tracking targets effectively and achieve large-scale surveillance with clear detailed close-up visual features capturing and recording in dynamic real-life environments.
基金The National Natural Science Foundation of China(No. 60972001 )the Science and Technology Plan of Suzhou City(No. SG201076)
文摘An adaptive human tracking method across spatially separated surveillance cameras with non-overlapping fields of views （FOVs） is proposed. The method relies on the two cues of the human appearance model and spatio-temporal information between cameras. For the human appearance model, an HSV color histogram is extracted from different human body parts （head, torso, and legs）, then a weighted algorithm is used to compute the similarity distance of two people. Finally, a similarity sorting algorithm with two thresholds is exploited to find the correspondence. The spatio- temporal information is established in the learning phase and is updated incrementally according to the latest correspondence. The experimental results prove that the proposed human tracking method is effective without requiring camera calibration and it becomes more accurate over time as new observations are accumulated.
基金supported by National Natural Science Foundation of China (Grant No. 61501048) National High-tech R&D Program of China (863 Program) (Grant No. 2013AA102301)+1 种基金The Fundamental Research Funds for the Central Universities (Grant No. 2017RC12) China Postdoctoral Science Foundation funded project (Grant No.2016T90067, 2015M570060)
文摘Mobile target tracking is a necessary function of some emerging application domains, such as virtual reality, smart home and intelligent healthcare. However, existing portable devices for target tracking are resource intensive and high-cost. Camera tracking is an effective location tracking way for those emerging applications which can reuse the existing ubiquitous video monitoring system. This paper proposes a dynamic community-based camera collaboration(D3C) framework for target location and tracking. The contributions of D3C mainly include that(1) nonlinear perspective projection model is selected as the camera sensing model and sequential Monte Carlo is employed to predict the target location;(2) a dynamic collaboration scheme is proposed, it is based on the local community-detection theory deriving from social network analysis. The performance of proposed approach is validated by both synthetic datasets and real-world application. The experiment results show that D3C meets the versatility, real-time and fault tolerance requirements of target tracking applications.
基金supported by the National Natural Science Foundationof China(61100207)the National Key Technology Research and Development Program of the Ministry of Science and Technology of China(2014BAK14B03)+1 种基金the Fundamental Research Funds for the Central Universities(2013PT132013XZ12)
文摘Most sensors or cameras discussed in the sensor network community are usually 3D homogeneous, even though their2 D coverage areas in the ground plane are heterogeneous. Meanwhile, observed objects of camera networks are usually simplified as 2D points in previous literature. However in actual application scenes, not only cameras are always heterogeneous with different height and action radiuses, but also the observed objects are with 3D features（i.e., height）. This paper presents a sensor planning formulation addressing the efficiency enhancement of visual tracking in 3D heterogeneous camera networks that track and detect people traversing a region. The problem of sensor planning consists of three issues：（i） how to model the 3D heterogeneous cameras;（ii） how to rank the visibility, which ensures that the object of interest is visible in a camera＇s field of view;（iii） how to reconfigure the 3D viewing orientations of the cameras. This paper studies the geometric properties of 3D heterogeneous camera networks and addresses an evaluation formulation to rank the visibility of observed objects. Then a sensor planning method is proposed to improve the efficiency of visual tracking. Finally, the numerical results show that the proposed method can improve the tracking performance of the system compared to the conventional strategies.
文摘The aim of this study is to propose a novel system that has an ability to detect intra-fractional motion during radiotherapy treatment in real-time using three-dimensional surface taken by a depth camera, Microsoft Kinect v1. Our approach introduces three new aspects for three-dimensional surface tracking in radiotherapy treatment. The first aspect is a new algorithm for noise reduction of depth values. Ueda’s algorithm was implemented and enabling a fast least square regression of depth values. The second aspect is an application for detection of patient’s motion at multiple points in thracoabdominal regions. The third aspect is an estimation of three-dimensional surface from multiple depth values. For evaluation of noise reduction by Ueda’s algorithm, two respiratory patterns are measured by the Kinect as well as a laser range meter. The resulting cross correlation coefficients between the laser range meter and the Kinect were 0.982 for abdominal respiration and 0.995 for breath holding. Moreover, the mean cross correlation coefficients between the signals of our system and the signals of Anzai with respect to participant’s respiratory motion were 0.90 for thoracic respiration and 0.93 for abdominal respiration, respectively. These results proved that the performance of the developed system was comparable to existing motion monitoring devices. Reconstruction of three-dimensional surface also enabled us to detect the irregular motion and breathing arrest by comparing the averaged depth with predefined threshold values.
文摘The paper presents a web based vision system using a networked IP camera for tracking objects of interest. Three critical issues are addressed in this paper. First is the detection of moving objects in the foreground;second is the control of pan-tilt-zoom (PTZ) IP cameras based on object location;and third is the collaboration of multiple cameras over the network to track objects of interests independently. The developed system utilized a network of PTZ cameras along with a number of software tools for this implementation. The system was able to track a single and multiple objects successfully. The difficulties in the detection of moving objects are also analyzed while multiple cameras are collaborating over a network utilizing PTZ cameras.
基金funded by the Natural Science Foundation of Jiangsu Province(No.BK2012389)the National Natural Science Foundation of China(Nos.71303110,91024024)the Foundation of Graduate Innovation Center in NUAA(Nos.kfjj201471,kfjj201473)
文摘To track human across non-overlapping cameras in depression angles for applications such as multi-airplane visual human tracking and urban multi-camera surveillance,an adaptive human tracking method is proposed,focusing on both feature representation and human tracking mechanism.Feature representation describes individual by using both improved local appearance descriptors and statistical geometric parameters.The improved feature descriptors can be extracted quickly and make the human feature more discriminative.Adaptive human tracking mechanism is based on feature representation and it arranges the human image blobs in field of view into matrix.Primary appearance models are created to include the maximum inter-camera appearance information captured from different visual angles.The persons appeared in camera are first filtered by statistical geometric parameters.Then the one among the filtered persons who has the maximum matching scale with the primary models is determined to be the target person.Subsequently,the image blobs of the target person are used to update and generate new primary appearance models for the next camera,thus being robust to visual angle changes.Experimental results prove the excellence of the feature representation and show the good generalization capability of tracking mechanism as well as its robustness to condition variables.
文摘为提高无人车障碍物检测跟踪的精度和稳定性,首先针对YOLO v5(You only look once version 5,YOLO v5)网络存在的语义信息和候选框信息丢失的问题,引入深度可分离空洞空间金字塔结构与目标框加权融合算法完成对网络的优化;其次针对单阶段障碍物点云聚类精度低的问题,设计一种考虑点云距离与外轮廓连续性的两阶段障碍物点云聚类方法并完成三维包围盒的建立;最后将注意力机制引入MobileNet使网络更加聚焦于目标对象特有的视觉特征,并综合利用视觉特征和三维点云信息共同构建关联性度量指标,提高匹配精度。利用KITTI数据集对构建的障碍物目标检测、跟踪与测速算法进行仿真测试,并搭建实车平台进行真实环境试验,验证所提算法的有效性和真实环境可迁移性。
基金National Natural Science Foundation of China(61732016).
文摘Three-dimensional(3D)modeling is an important topic in computer graphics and computer vision.In recent years,the introduction of consumer-grade depth cameras has resulted in profound advances in 3D modeling.Starting with the basic data structure,this survey reviews the latest developments of 3D modeling based on depth cameras,including research works on camera tracking,3D object and scene reconstruction,and high-quality texture reconstruction.We also discuss the future work and possible solutions for 3D modeling based on the depth camera.
文摘针对在无人机高速运动场景下,相关滤波跟踪算法存在边界效应和滤波器退化等问题,提出了一种融合相机运动补偿的自适应时空正则化的无人机跟踪相关滤波算法。首先,在相关滤波器中设计了一种自适应空间正则化方法来缓解边界效应;其次,为防止滤波器退化,设计了基于高置信度样本的时间正则化方法及优化更新策略,同时利用交替方向乘子法(Alternating Direction Method of Multipliers,ADMM)优化目标函数的求解,保证了算法的运行效率;然后,设计了快速尺度滤波器,实现目标尺度的快速估计;最后,提出了一种鲁棒性的跟踪不确定性规则及基于相机运动补偿的重检测器,使得目标丢失后可及时恢复。实验结果表明,提出的算法在无人机数据集上的精确度和成功率分别可达0.739和0.634,与ECO_HC(Efficient Convolution Operators-Hand Crafted)算法相比分别提升了1.65%和6.9%,与同类主流算法相比,有效地提升了跟踪时的精确度和成功率,经历快速运动、目标遮挡等情况时应用该算法的无人机也表现出良好的跟踪性能。
