A novel cast shadow detection approach was proposed.A stereo vision system was used to capture images instead of traditional single camera.It was based on an assumption that cast shadows were on a special plane.The im...A novel cast shadow detection approach was proposed.A stereo vision system was used to capture images instead of traditional single camera.It was based on an assumption that cast shadows were on a special plane.The image obtained from one camera was inversely projected to the plane and then transformed to the view from another camera.The points on the plane shared the same position between original image and the transformed image.As a result,the cast shadows can be detected.In order to improve the efficiency of cast shadow detection and decrease computational complexity,the obvious object areas in CIELAB color space were removed and the potential shadow areas were obtained.Experimental results demonstrate that the proposed approach can detect cast shadows accurately even under various illuminations.展开更多
MGAC (Motion Geometric Active Contours), a new variational framework of geometric active contours to track multiple nonrigid moving objects in the clutter background in image sequences is presented. This framework, in...MGAC (Motion Geometric Active Contours), a new variational framework of geometric active contours to track multiple nonrigid moving objects in the clutter background in image sequences is presented. This framework, incorporating with the motion edge information, consists of motion detection and tracking stages. At the motion detection stage, the motion edge map provides an approximate edge map of the moving objects. Then, a tracking stage, merely using the static edge information, is considered to improve the motion detection result. Force field regularization method is used to extend the capture range of the edge attraction force field in both stages. Experiments demonstrate that the proposed framework is valid for tracking multiple nonrigid objects in the clutter background.展开更多
Automatic image classification is the first step toward semantic understanding of an object in the computer vision area.The key challenge of problem for accurate object recognition is the ability to extract the robust...Automatic image classification is the first step toward semantic understanding of an object in the computer vision area.The key challenge of problem for accurate object recognition is the ability to extract the robust features from various viewpoint images and rapidly calculate similarity between features in the image database or video stream.In order to solve these problems,an effective and rapid image classification method was presented for the object recognition based on the video learning technique.The optical-flow and RANSAC algorithm were used to acquire scene images from each video sequence.After the selection of scene images,the local maximum points on comer of object around local area were found using the Harris comer detection algorithm and the several attributes from local block around each feature point were calculated by using scale invariant feature transform （SIFT） for extracting local descriptor.Finally,the extracted local descriptor was learned to the three-dimensional pyramid match kernel.Experimental results show that our method can extract features in various multi-viewpoint images from query video and calculate a similarity between a query image and images in the database.展开更多
The author＇s practice-led research explores ＂the act of living.＂ In order to advance this idea, the author has acquired skills in investigation and expresses her thinking through a descriptive and explanatory visua...The author＇s practice-led research explores ＂the act of living.＂ In order to advance this idea, the author has acquired skills in investigation and expresses her thinking through a descriptive and explanatory visual language. The author＇s learning journey, while not unique, has not been an ordinary one. Initial academic failure to achieve in the school education system contributed to her choosing a life working on the land and harbouring the belief that she was unable to learn academically. Still, the author has gained a rich base of physical knowledge and experience through the traditional oral route including learning interpersonal communication through body language and vocal tonality. The author has used this intuitive knowledge to develop an arts practice where she explores the bio-cultural links between people and the lands they inhabit, creating works that aim to extend knowing through emphasising the experience and atmosphere of landscape. At this time, when our lives have become increasingly encoded and intellectually based, the author shares a belief with American philosopher Eugene Gendlin （b. 1926） that the ＂felt sense＂ can be developed in order to enable us to engage more fully with the world around us. The author explores this idea in her visual art but also realizes the need to express it in writing, both in order to reach a wider public and because of the possibilities offered by the written word to make public which is private and held deep within.展开更多
The 3D object visual tracking problem is studied for the robot vision system of the 220kV/330kV high-voltage live-line insulator cleaning robot. The SUSAN Edge based Scale Invariant Feature (SESIF) algorithm based 3D ...The 3D object visual tracking problem is studied for the robot vision system of the 220kV/330kV high-voltage live-line insulator cleaning robot. The SUSAN Edge based Scale Invariant Feature (SESIF) algorithm based 3D objects visual tracking is achieved in three stages: the first frame stage,tracking stage,and recovering stage. An SESIF based objects recognition algorithm is proposed to find initial location at both the first frame stage and recovering stage. An SESIF and Lie group based visual tracking algorithm is used to track 3D object. Experiments verify the algorithm's robustness. This algorithm will be used in the second generation of the 220kV/330kV high-voltage live-line insulator cleaning robot.展开更多
The robot＇ s eyes through the background difference method were used to find broke into the visual range of a moving object and track and monitor the moving object. On the basis of geometry and according to the dista...The robot＇ s eyes through the background difference method were used to find broke into the visual range of a moving object and track and monitor the moving object. On the basis of geometry and according to the distance and deflection angle of the robot eyes positioning, the objects were captured and tracked by robots eyes. Geometry method precision was low, but simple calculation processing was quick. Thus, it can effectively meet the robot eyes preliminary positioning of the fast moving target.展开更多
基金Project(40971219)supported by the Natural Science Foundation of ChinaProjects(201121202020005,T201221207)supported by the Fundamental Research Fund for the Central Universities,China
文摘A novel cast shadow detection approach was proposed.A stereo vision system was used to capture images instead of traditional single camera.It was based on an assumption that cast shadows were on a special plane.The image obtained from one camera was inversely projected to the plane and then transformed to the view from another camera.The points on the plane shared the same position between original image and the transformed image.As a result,the cast shadows can be detected.In order to improve the efficiency of cast shadow detection and decrease computational complexity,the obvious object areas in CIELAB color space were removed and the potential shadow areas were obtained.Experimental results demonstrate that the proposed approach can detect cast shadows accurately even under various illuminations.
文摘MGAC (Motion Geometric Active Contours), a new variational framework of geometric active contours to track multiple nonrigid moving objects in the clutter background in image sequences is presented. This framework, incorporating with the motion edge information, consists of motion detection and tracking stages. At the motion detection stage, the motion edge map provides an approximate edge map of the moving objects. Then, a tracking stage, merely using the static edge information, is considered to improve the motion detection result. Force field regularization method is used to extend the capture range of the edge attraction force field in both stages. Experiments demonstrate that the proposed framework is valid for tracking multiple nonrigid objects in the clutter background.
文摘Automatic image classification is the first step toward semantic understanding of an object in the computer vision area.The key challenge of problem for accurate object recognition is the ability to extract the robust features from various viewpoint images and rapidly calculate similarity between features in the image database or video stream.In order to solve these problems,an effective and rapid image classification method was presented for the object recognition based on the video learning technique.The optical-flow and RANSAC algorithm were used to acquire scene images from each video sequence.After the selection of scene images,the local maximum points on comer of object around local area were found using the Harris comer detection algorithm and the several attributes from local block around each feature point were calculated by using scale invariant feature transform （SIFT） for extracting local descriptor.Finally,the extracted local descriptor was learned to the three-dimensional pyramid match kernel.Experimental results show that our method can extract features in various multi-viewpoint images from query video and calculate a similarity between a query image and images in the database.
文摘The author＇s practice-led research explores ＂the act of living.＂ In order to advance this idea, the author has acquired skills in investigation and expresses her thinking through a descriptive and explanatory visual language. The author＇s learning journey, while not unique, has not been an ordinary one. Initial academic failure to achieve in the school education system contributed to her choosing a life working on the land and harbouring the belief that she was unable to learn academically. Still, the author has gained a rich base of physical knowledge and experience through the traditional oral route including learning interpersonal communication through body language and vocal tonality. The author has used this intuitive knowledge to develop an arts practice where she explores the bio-cultural links between people and the lands they inhabit, creating works that aim to extend knowing through emphasising the experience and atmosphere of landscape. At this time, when our lives have become increasingly encoded and intellectually based, the author shares a belief with American philosopher Eugene Gendlin （b. 1926） that the ＂felt sense＂ can be developed in order to enable us to engage more fully with the world around us. The author explores this idea in her visual art but also realizes the need to express it in writing, both in order to reach a wider public and because of the possibilities offered by the written word to make public which is private and held deep within.
基金National High Technology Research and Development Programof China (863program,No.2002AA42D110-2)
文摘The 3D object visual tracking problem is studied for the robot vision system of the 220kV/330kV high-voltage live-line insulator cleaning robot. The SUSAN Edge based Scale Invariant Feature (SESIF) algorithm based 3D objects visual tracking is achieved in three stages: the first frame stage,tracking stage,and recovering stage. An SESIF based objects recognition algorithm is proposed to find initial location at both the first frame stage and recovering stage. An SESIF and Lie group based visual tracking algorithm is used to track 3D object. Experiments verify the algorithm's robustness. This algorithm will be used in the second generation of the 220kV/330kV high-voltage live-line insulator cleaning robot.
文摘The robot＇ s eyes through the background difference method were used to find broke into the visual range of a moving object and track and monitor the moving object. On the basis of geometry and according to the distance and deflection angle of the robot eyes positioning, the objects were captured and tracked by robots eyes. Geometry method precision was low, but simple calculation processing was quick. Thus, it can effectively meet the robot eyes preliminary positioning of the fast moving target.
