首页>
外国专利>
Model-less background estimation for foreground detection in video sequences
Model-less background estimation for foreground detection in video sequences
展开▼
机译:视频序列中前景检测的无模型背景估计
展开▼
页面导航
摘要
著录项
相似文献
摘要
A camera outputs video as a sequence of video frames having pixel values in a first (e.g., relatively low dimensional) color space, where the first color space has a first number of channels. An image-processing device maps the video frames to a second (e.g., relatively higher dimensional) color representation of video frames. The mapping causes the second color representation of video frames to have a greater number of channels relative to the first number of channels. The image-processing device extracts a second color representation of a background frame of the scene. The image-processing device can then detect foreground objects in a current frame of the second color representation of video frames by comparing the current frame with the second color representation of a background frame. The image-processing device then outputs an identification of the foreground objects in the current frame of the video.
展开▼