A statistical multimodal background model was described for moving object detection in video surveillance. The solution to some of the problems such as illumination changes, initialization of model with moving objects...A statistical multimodal background model was described for moving object detection in video surveillance. The solution to some of the problems such as illumination changes, initialization of model with moving objects, and shadows suppression was provided. The background samples were chosen by thresholding inter-frame differences, and the Gaussian kernel density estimation was used to estimate the probability density function of background intensity. Pixel's neighbor information was considered to remove noise due to camera jitter and small motion in the scene. The hue-max-min-diff color information was used to detect and suppress moving cast shadows. The effectiveness of the proposed method in the foreground segmentation was demonstrated in the traffic surveillance application.展开更多
Video object segmentation is important for video surveillance, object tracking, video object recognition and video editing. An adaptive video segmentation algorithm based on hidden conditional random fields (HCRFs) is...Video object segmentation is important for video surveillance, object tracking, video object recognition and video editing. An adaptive video segmentation algorithm based on hidden conditional random fields (HCRFs) is proposed, which models spatio-temporal constraints of video sequence. In order to improve the segmentation quality, the weights of spatio-temporal con- straints are adaptively updated by on-line learning for HCRFs. Shadows are the factors affecting segmentation quality. To separate foreground objects from the shadows they cast, linear transform for Gaussian distribution of the background is adopted to model the shadow. The experimental results demonstrated that the error ratio of our algorithm is reduced by 23% and 19% respectively, compared with the Gaussian mixture model (GMM) and spatio-temporal Markov random fields (MRFs).展开更多
文摘A statistical multimodal background model was described for moving object detection in video surveillance. The solution to some of the problems such as illumination changes, initialization of model with moving objects, and shadows suppression was provided. The background samples were chosen by thresholding inter-frame differences, and the Gaussian kernel density estimation was used to estimate the probability density function of background intensity. Pixel's neighbor information was considered to remove noise due to camera jitter and small motion in the scene. The hue-max-min-diff color information was used to detect and suppress moving cast shadows. The effectiveness of the proposed method in the foreground segmentation was demonstrated in the traffic surveillance application.
基金Project supported by the National Natural Science Foundation of China (Nos. 60473106, 60273060 and 60333010)the Ministry of Education of China (No. 20030335064)the Education Depart-ment of Zhejiang Province, China (No. G20030433)
文摘Video object segmentation is important for video surveillance, object tracking, video object recognition and video editing. An adaptive video segmentation algorithm based on hidden conditional random fields (HCRFs) is proposed, which models spatio-temporal constraints of video sequence. In order to improve the segmentation quality, the weights of spatio-temporal con- straints are adaptively updated by on-line learning for HCRFs. Shadows are the factors affecting segmentation quality. To separate foreground objects from the shadows they cast, linear transform for Gaussian distribution of the background is adopted to model the shadow. The experimental results demonstrated that the error ratio of our algorithm is reduced by 23% and 19% respectively, compared with the Gaussian mixture model (GMM) and spatio-temporal Markov random fields (MRFs).
