An adaptive topology learning approach is proposed to learn the topology of a practical camera network in an unsupervised way. The nodes are modeled by the Gaussian mixture model. The connectivity between nodes is jud...An adaptive topology learning approach is proposed to learn the topology of a practical camera network in an unsupervised way. The nodes are modeled by the Gaussian mixture model. The connectivity between nodes is judged by their cross-correlation function, which is also used to calculate their transition time distribution. The mutual information of the connected node pair is employed for transition probability calculation. A false link eliminating approach is proposed, along with a topology updating strategy to improve the learned topology. A real monitoring system with five disjoint cameras is built for experiments. Comparative results with traditional methods show that the proposed method is more accurate in topology learning and is more robust to environmental changes.展开更多
Image corner detection plays an important role in image analysis and recognition. This paper presents a novel corner detector based on the growing neural gas （GNG） network and this proposed detector is called GNG-C....Image corner detection plays an important role in image analysis and recognition. This paper presents a novel corner detector based on the growing neural gas （GNG） network and this proposed detector is called GNG-C. With the GNG network,image topology information can be learned and used to implement corner detection. The GNG-C approach can be described as consisting of the following steps. First,a canny edge detector is used to acquire the contour information of the input image. This edge information is used to train a modified GNG network. A special stopping criterion is defined to terminate network learning. Second,vectors formed between network nodes and their neighbors are used to measure curvatures. Third,dynamic regions of support （ROS） are determined based on these curvatures. These ROS are used to suppress curvature noise. The curvature values of the nodes are then analyzed to estimate the candidate corners. Finally,the candidates are distilled by a non-maxima suppression process to obtain the final set of corners. Experiments on both artificial and real images show that the proposed corner detection method is feasible and effective.展开更多
基金The National Natural Science Foundation of China(No.60972001)the Science and Technology Plan of Suzhou City(No.SS201223)
文摘An adaptive topology learning approach is proposed to learn the topology of a practical camera network in an unsupervised way. The nodes are modeled by the Gaussian mixture model. The connectivity between nodes is judged by their cross-correlation function, which is also used to calculate their transition time distribution. The mutual information of the connected node pair is employed for transition probability calculation. A false link eliminating approach is proposed, along with a topology updating strategy to improve the learned topology. A real monitoring system with five disjoint cameras is built for experiments. Comparative results with traditional methods show that the proposed method is more accurate in topology learning and is more robust to environmental changes.
基金supported by the National Natural Science Foundation of China (60972112)
文摘Image corner detection plays an important role in image analysis and recognition. This paper presents a novel corner detector based on the growing neural gas （GNG） network and this proposed detector is called GNG-C. With the GNG network,image topology information can be learned and used to implement corner detection. The GNG-C approach can be described as consisting of the following steps. First,a canny edge detector is used to acquire the contour information of the input image. This edge information is used to train a modified GNG network. A special stopping criterion is defined to terminate network learning. Second,vectors formed between network nodes and their neighbors are used to measure curvatures. Third,dynamic regions of support （ROS） are determined based on these curvatures. These ROS are used to suppress curvature noise. The curvature values of the nodes are then analyzed to estimate the candidate corners. Finally,the candidates are distilled by a non-maxima suppression process to obtain the final set of corners. Experiments on both artificial and real images show that the proposed corner detection method is feasible and effective.
