With the problem of robot motion control in dynamic environment represented by mobile obstacles,working pieces and external mechanisms considered, a relevant control actions design procedure has been pro-posed to prov...With the problem of robot motion control in dynamic environment represented by mobile obstacles,working pieces and external mechanisms considered, a relevant control actions design procedure has been pro-posed to provide coordination of robot motions with respect to the moving external objects so that an extension ofrobot spatial motion techniques and active robotic strategies based on approaches of nonlinear control theory canbe achieved.展开更多
Background difference method[l] is one of the effective paths of improving robot＇ s vision reaction ability, and robots use background difference method to find the moving object in vision range and conduct tracking ...Background difference method[l] is one of the effective paths of improving robot＇ s vision reaction ability, and robots use background difference method to find the moving object in vision range and conduct tracking monitoring of moving objects. Then it uses support vector to conduct learning fitting of moving object, which can effectively predict the moving trend of moving object, and then it fabricates corresponding decision programs to conduct intercept capture of moving objects.展开更多
Effective and robust recognition and tracking of objects are the key problems in visual surveillance systems. Most existing object recognition methods were designed with particular objects in mind. This study presents...Effective and robust recognition and tracking of objects are the key problems in visual surveillance systems. Most existing object recognition methods were designed with particular objects in mind. This study presents a general moving objects recognition method using global features of targets. Targets are extracted with an adaptive Gaussian mixture model and their silhouette images are captured and unified. A new objects silhouette database is built to provide abundant samples to train the subspace feature. This database is more convincing than the previous ones. A more effective dimension reduction method based on graph embedding is used to obtain the projection eigenvector. In our experiments, we show the effective performance of our method in addressing the moving objects recognition problem and its superiority compared with the previous methods.展开更多
基金Sponsored by Russian Foundation of Basic Research (Grant No. 97-01-00432)
文摘With the problem of robot motion control in dynamic environment represented by mobile obstacles,working pieces and external mechanisms considered, a relevant control actions design procedure has been pro-posed to provide coordination of robot motions with respect to the moving external objects so that an extension ofrobot spatial motion techniques and active robotic strategies based on approaches of nonlinear control theory canbe achieved.
文摘Background difference method[l] is one of the effective paths of improving robot＇ s vision reaction ability, and robots use background difference method to find the moving object in vision range and conduct tracking monitoring of moving objects. Then it uses support vector to conduct learning fitting of moving object, which can effectively predict the moving trend of moving object, and then it fabricates corresponding decision programs to conduct intercept capture of moving objects.
基金Project (No. 60805001) partially supported by the National NaturalScience Foundation of China
文摘Effective and robust recognition and tracking of objects are the key problems in visual surveillance systems. Most existing object recognition methods were designed with particular objects in mind. This study presents a general moving objects recognition method using global features of targets. Targets are extracted with an adaptive Gaussian mixture model and their silhouette images are captured and unified. A new objects silhouette database is built to provide abundant samples to train the subspace feature. This database is more convincing than the previous ones. A more effective dimension reduction method based on graph embedding is used to obtain the projection eigenvector. In our experiments, we show the effective performance of our method in addressing the moving objects recognition problem and its superiority compared with the previous methods.
