The shadows similar to the vehicle and the spots caused by vehicle lamps need to be accurately detected in the vehicle segmentation involved in the video-based traffic parameter measurement. Generally, the road surfac...The shadows similar to the vehicle and the spots caused by vehicle lamps need to be accurately detected in the vehicle segmentation involved in the video-based traffic parameter measurement. Generally, the road surface is different from the vehicle surface in the gray-level architecture. An invariant gray-level architecture-the extremum image in the changing illumination environment is derived and a novel algorithm is presented for detecting shadows and spots. The gray-level structure that is not sensitive to the illumination is employed in the algorithm and the road surface mistaken as vehicles can be removed.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The shadows similar to the vehicle and the spots caused by vehicle lamps need to be accurately detected in the vehicle segmentation involved in the video-based traffic parameter measurement. Generally, the road surface is different from the vehicle surface in the gray-level architecture. An invariant gray-level architecture-the extremum image in the changing illumination environment is derived and a novel algorithm is presented for detecting shadows and spots. The gray-level structure that is not sensitive to the illumination is employed in the algorithm and the road surface mistaken as vehicles can be removed.
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).
