Remnant detection and tracking method

Abstract

The invention discloses a remnant detection and tracking method. The method comprises the following steps of carrying out pretreatment of graying, filtering and the like on an original monitoring video image sequence so as to acquire an initial video image sequence; carrying out background modeling on the initial video image sequence collected by a camera, extracting a foreground area through an obtained background modeling result, carrying out de-noising processing on the foreground area so as to acquire a foreground target; through a positive example picture and a negative example picture, carrying out offline training on a support vector machine so as to acquire a target remnant model and a human body model respectively, inputting each foreground target into the two models respectively so as to carry out determination, and outputting a target remnant; using a Meanshift algorithm to track the target remnant and acquiring position coordinates of the target remnant in each previous frame; reversely traversing the initial video image sequence and tracking the position coordinates of the target remnant in each frame before the current frame, carrying out statistics and analysis, and outputting an image containing the target remnant in the initial video image sequence.

Description

technical field [0001] The invention relates to the field of leftover detection, in particular to a method for detection and tracking of leftovers. Background technique [0002] Leftovers are static objects that are left unattended. In the intelligent video surveillance system, the detection of leftover objects has a wide range of applications in many fields, such as: real-time monitoring of suspicious objects or lost luggage in open places such as buildings, squares, and military control areas. [1] . Surveillance video is of great significance for obtaining evidence after an abnormal situation occurs. Once an abnormal situation occurs in these places, but the monitoring personnel fail to find it in time, they can only query the situation at that time by playing back the video. However, this monitoring mode based on manpower prevention and video playback after the event will not only waste a lot of manpower and material resources, but also often cause missed reports of abn...

AI Technical Summary

Problems solved by technology

[0004] Most of the current remnant object detection methods identify objects that have been stationary for a long enough time in the foreground area as relic objects, regardless of whether the foreground area is a stationary pedestrian or an object; at the same time, they also fail to consider the relationship between people and objects, which can easily cause False detection

Images