Two-camera target association method based on small intersecting field of view

Abstract

The invention discloses a small cross view field-based double-camera target associating method. The small cross view field-based double-camera target associating method comprises the following steps of, firstly, calibrating a camera C1 and a camera C2; secondly, obtaining the image sequence of a moving target through the camera C1 and the camera C2, and correcting the image sequence; thirdly, segmenting out moving target images from the corrected image sequence through a mixed Gaussian model; fourthly, matching a template with source images through a similarity calculating method, obtaining the matched areas of the target in the source images, and comparing the two matched areas to determine that the two targets are the same target and to complete target association. By means of the small cross view field between the two cameras, namely, due to the fact that, when the target passes by the view fields of the two cameras, two image sequences at the same sampling time or multiple sampling times can simultaneously contain all the or a part of information of the target, the small cross view field-based double-camera target associating method can ensure data transmission and a relatively large detecting view field between the two cameras and effectively solve the problem of target tracking under the condition that the target is lost, pops up, changes in large magnitude, is interfered by noise or the like.

Description

technical field [0001] The invention belongs to the technical field of optical detection and relates to a two-camera target association method based on a small intersecting field of view. Background technique [0002] In a multi-camera array optical detection system, the data association between cameras is the core of the continuous detection and tracking of the entire optical system target. Research on high-precision and robust target association methods is an important means to improve the target tracking effect of the optical array detection system. In the existing methods, geometric correlation constraints such as real road condition information or target shape are added, and the target is recorded in the form of continuous labels, which has certain application limitations. In general, multi-camera target association is to cover a large overlapping area between cameras, and perform template matching in the overlapping area for target association, which will result in sma...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a two-camera target association method based on a small cross field of view to solve the problem of target error association under the conditions of target loss, sudden appearance, large maneuver change, noise interference, etc. in the prior art

Images