A real-time non-tracking monitoring video remnant detection method

Abstract

According to the real-time non-tracking monitoring video remnant detection method provided by the invention, manual feature extraction and deep learning recognition are combined, and non-tracking remnant detection is realized. The method comprises the following steps: firstly, on the basis of a frame difference method, counting continuous frame sequence change conditions of a foreground region toobtain an initial static target region; Then, we will make Two kinds of manual design characteristics of a gradient direction straight directional diagram and hue- Saturation-lightness combineto carryout suspicious object pre-judgment, and a pseudo static target area caused by influences of illumination changes and the like is eliminated. And finally, known objects and pedestrians are excluded bycombining a deep learning technology, so that final confirmation is carried out on suspicious objects, and non-tracking detection of the remaining objects is realized. According to the method, pseudotargets generated by illumination change and pedestrian retention in a scene can be eliminated, remaining objects can be accurately detected, the single-frame processing time is shorter than that ofother two methods, and the requirement for real-time alarming can be met.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a real-time non-tracking surveillance video remnant detection method. Background technique [0002] Relics are objects that appear in the scene and stay in the scene for a certain period of time. In some public places (squares, airports, railway stations, etc.), by monitoring suspicious remnants and issuing alarms, the occurrence of public safety incidents can be effectively reduced, the personal and property safety of the public can be protected, and the long-term stability of the society can be maintained. Therefore, remnants detection plays a very important role in intelligent video surveillance system. Remnant object detection not only needs to distinguish between foreground objects and stationary foreground objects, but also to judge whether the stationary foreground objects are pedestrians and illuminated. The current methods mostly use the method of ...

AI Technical Summary

Problems solved by technology

This method only uses deep learning to determine the final leftover luggage. It does not take into account that changes in lighting will cause changes in objects, and it may not be able to identify whether it is luggage when passing the deep learning test.

Images