Intelligent marking, searching and replaying method and device for surveillance videos of shared lanes

Abstract

The invention relates to a video detection technology and discloses an intelligent marking, searching and replaying method and device for surveillance videos of shared lanes. According to the invention, when a moving target is detected, the judgment on the type of the target is triggered, and corresponding information is detected according to the target type and is written to a position corresponding to a trigger frame in a video bitstream, therefore, the search of semantic features can be performed conveniently on targets in various types on the shared lanes, and corresponding video frames are positioned fast according to the search result. By virtue of the method and the device, the problem that the videos and the target characteristic information are inconvenient to search and store when being separated from each other is solved; and the trigger begins once a predetermined condition is met, and the video is recorded synchronously, thus, the miss trigger of moving targets can be be avoided, and a storage space required to store captured pictures can be saved as well.

Description

technical field [0001] The invention relates to a video detection technology, in particular to a hybrid lane monitoring video intelligent marking, retrieval and playback technology. Background technique [0002] At present, in road monitoring, common methods include simple video recording of the monitoring area, or the method of capturing pictures after an event is detected. Captured pictures are easy to retrieve, but the trigger rate is difficult to guarantee 100%, and the corresponding target cannot be retrieved based on target feature information such as time for missing trigger targets. The method of recording video while saving captured pictures can solve the needs of video and picture retrieval, but after recording and then capturing pictures, the data volume of pictures takes up additional storage space. In order to save the image storage space, the description information can be added to the surveillance video by describing the captured image information. [0003] ...

AI Technical Summary

Problems solved by technology

However, in intelligent traffic monitoring, these structured information cannot intuitively describe the characteristics of the target. It is necessary to further classify the target, estimate the speed, identify the color and license plate information, so as to better reflect the visual state of the triggering target. In addition, the structured description The amount of information is much larger than that of visual feature information

[0004] The inventors of the present invention have found that in the existing monitoring and video recording system for mixed lanes, the target feature information obtained through intelligent image processing is stored as an independent file, and this independent file may be modified or deleted. The file needs to additionally load the corresponding feature information file

Images