Salient object detection method based on video

Abstract

The invention discloses a salient object detection method based on video. The method comprises the following steps: performing super-pixel segmentation on a picture, and utilizing optical flow information and color information to obtain a preliminary salient object detection area; acquiring picture background information by using gradient information; fusing the preliminary object detection area and pruning the background to obtain a final salient object zone. According to the method, the similarity of pixels is detected by combining statistical motion information (i.e. the optical flow information) and static information (i.e. the color and gradient information) on the pixel level, foreground and background cues are fused in the result, and the purpose of detecting a salient object in video is finally fulfilled.

Description

technical field [0001] The invention relates to a video-based salient target detection method, in particular to a video salient target detection method based on foreground detection and background subtraction, and belongs to the technical field of image processing. Background technique [0002] Salient object detection is very important in the field of computer vision. Due to security needs, people pay more and more attention to the safety detection in video. In videos, it becomes especially important to detect salient objects to obtain information that people are interested in. In a video surveillance system, a salient target is an object that attracts people's attention at the first sight in the picture. Salient object detection is to find such objects in pictures or videos through algorithms to replace human visual functions, so as to prepare for subsequent higher-level video detection work. [0003] In recent years, many saliency detection methods focus on detecting f...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the shortcomings of existing video salient object detection methods, and provide a video-based salient object detection method, which combines statistical motion information, namely optical flow information, and static information, namely color and gradient information, at the pixel level To detect the similarity between pixels, the result combines foreground clues and background clues, and finally achieves the purpose of detecting salient objects in the video

Images