Target tracking method and panoramic camera

Abstract

The invention provides a target tracking method and a panoramic camera. The panoramic image of a certain frame in a panoramic video is selected as an initial frame panoramic image. The initial frame panoramic image and the panoramic image of each later frame are divided into N sub-images. M tracking targets are selected from N sub-images into which the initial frame panoramic image is divided. Theinitial frame panoramic image is used as the first frame of panoramic image. A step is carried out on each frame of panoramic image after the first frame of panoramic image in sequence. According tothe step, each tracked target in N sub-images in the i-th frame of panoramic image is tracked to acquire at least one tracked target which is successfully tracked in N sub-images in the (i+1)-th frameof panoramic image. According to the target tracking method and a panoramic camera, the real-time performance of target tracking can be improved.

Description

technical field [0001] The invention relates to the technical field of panoramic video, in particular to a target tracking method and a panoramic camera. Background technique [0002] Panoramic video is composed of some time-related panoramic image sequences, from which a real panoramic scene can be obtained, and video frames can be positioned through time. The global motion of the cube panorama video of a still scene is usually dominated by horizontal motion, covering a 360-degree scene range. For a continuous multi-frame panorama image, the target object will move from one face of the cube panorama to the adjacent face. Because it may have a dynamic background, it is not suitable to use the method of background difference to detect and track dynamic objects, and the method of using background difference to detect and track dynamic objects has limited effects, so it is not applicable to many situations, so it is necessary to design a Fast and Efficient Method for Object Tr...

AI Technical Summary

Problems solved by technology

In the tracking process, the model of the target object is established, and the probability of the tracking target appearing in different areas is established according to the front and rear frames, and the position with a higher probability is used as the new position of the target; using the above method, it is first necessary to obtain the panoramic video image and then project it to obtain Preset the projection image of the field of view, and then track the probability of the target appearing in different areas in the front and rear frames to determine the new position of the tracking target. There are many calculation steps and a large amount of calculation. The amount will increase exponentially, which leads to the problem of low tracking efficiency of panoramic video

Images