Method for acquiring characteristic size of remote video monitored target on basis of depth fingerprint

Abstract

The invention discloses a method for acquiring a characteristic size of a remote video monitored target on the basis of a depth fingerprint, which comprises the following steps of: acquiring a plurality of slice images of a region of interest of a monitored scene of a target video monitoring system by a gated imaging technique, overlapping the slice images to obtain a depth fingerprint of the region of interest and implanting the depth fingerprint into the target video monitoring system; when the monitored target appears in the region of interest, extracting the monitored target from the background, matching the monitored target with the depth fingerprint, and determining fingerprint lines which are subordinate to foot characteristic lines of the monitored target, wherein space distance information of the fingerprint lines is target distance information; and after acquiring the target distance information, inverting information of the characteristic size of the target from the length of a characteristic segment of the target to be measured, which takes a pixel as the unit, in a monitoring image according to a mopping relation between a three-dimensional space and a two-dimensionalimage plane under the condition of a perspective projection model. By the method, the problem that a conventional remote video monitoring system is difficult to acquire the information of the characteristic size of the target is solved.

Description

Technical field [0001] The present invention relates to video depth fingerprint technology in the technical field of video surveillance, and in particular to a method for acquiring the feature size of a remote video surveillance target based on deep fingerprints. Background technique [0002] Video surveillance has been widely used in today's society, but at present it is mainly for close-range video surveillance indoors or in communities. With the development and advancement of technology, long-distance video surveillance technology has gradually matured, and has been applied to maritime resource management, maritime anti-narcotics and anti-smuggling, maritime search and rescue, border and coastal defense monitoring, traffic monitoring, nuclear power plants and oil storage bases and other important places monitoring , Especially in severe weather. Many cities in our country are actively promoting the "Safe City" project, and the country is piloting the "3111" project on a large...

AI Technical Summary

Problems solved by technology

Monocular vision technology only uses one camera, which has a simple structure, but the method of focusing or defocusing to obtain target distance information results in poor operability and is not suitable for the monitoring network system that has been widely installed at present; the principle of binocular vision detection method is similar to that of human Binoculars, using binocular stereo inconsistency, using two cameras with the same performance to obtain two images of the same scene, and calculate the stereo disparity of the same spatial point in the two images (the measured point in space is imaged on the image plane of the two cameras point position difference), the depth information of the point can be obtained, but due to the problem of image stereo matching, it is too complicated, so its application is also limited, and both of these two technologies need to redesign the existing monitoring network. layout, increased cost

[0005] Other image processing techniques require reference objects in the monitoring scene (AntonioCriminisi et al., A new approach to botain height measurements from video, Proc.SPIE, Vol.3576, 227-238(1999)), or by After setting the reference point to calibrate the camera in the surveillance scene, the feature size of the target is obtained through image processing (Joong Lee et al., Effective height measurement method of surveillance camera image, Forensic Science International, Vol.177, 17-23 (2007)), for no Scenes with reference objects or complex scenes will not work effectively

Images