Finite-stage machine-based method for detecting abandoned object

Abstract

The invention discloses a finite-stage machine-based method for detecting an abandoned object. The finite-stage machine-based method comprises the steps of: firstly, establishing a Gaussian mixture background model, respectively establishing a short-time background model and a long-time background model according to different learning rates; secondly, establishing a finite-stage machine for each pixel; with results obtained by detection of two different background models with different updating speeds as inputs and a pixel classifying result output by each finite-stage machine as one binary image, carrying out communicated region analysis on the obtained binary image to obtain the shape and contour of the abandoned object by using a region growth method, and working out a rectangular box enclosing the abandoned object; and finally, timing the obtained rectangular box of the abandoned object, and detecting the abandoned object and alarming when a threshold is reached. According to the finite-stage machine-based method, under the condition that the abandoned object is absorbed by two backgrounds, the abandoned object can be always detected according to the pixel history, less false-alarms and wrong-alarms exist in an actual scene, and a good detection effect can also be obtained in an occasion with intensive pedestrian flow without depending on tracking information.

Description

Technical field [0001] The present invention relates to a video remnant detection method, and more particularly to a method for establishing an extended finite state machine to classify each pixel of an image based on a dual background model to detect remnants. Background technique [0002] In recent years, with the spread of terrorism, public safety incidents at home and abroad have occurred frequently, especially when explosives in public places have caused heavy casualties. Video remnants detection is a technical means for criminals to quickly alarm when people are not prepared to place dangerous goods in public places such as terminals and railway stations. At the same time, leftover detection can also be used to detect parking incidents in traffic scenes. [0003] At present, video remnants detection methods mainly use background subtraction to detect remnants. A Gaussian model is established for each pixel in the still camera video image to obtain the background, and the ba...

AI Technical Summary

Problems solved by technology

Once there are many targets in the scene, the influence of mutual occlusion and shadows, and the tracking of remnants is wrong, it will interfere with the background model, and it is difficult to restore, resulting in false alarms and false alarms

Images