Target matching method among multiple cameras based on multi-feature fusion and incremental learning

Abstract

The invention discloses a target matching method among multiple cameras based on multi-feature fusion and incremental learning. The method comprises the steps that a feature model of a target relates to an SIFT (Scale Invariant Feature Transform) feature of an extracted target; the feature is quantized on an established hierarchical vocabulary tree to form a hierarchical vocabulary tree histogram feature; a color histogram feature is extracted; a preliminary fusion feature is obtained according to the two histogram features; kernel PCA (Principal Component Analysis) dimensionality reduction is conducted on the fusion feature; a nonlinear fusion feature is extracted; classification and identification of the target are that a multi-target nonlinear fusion feature is sent into a multi-class SVM (Support Vector Machine) classifier for the classification and the identification; on-line updating of a target model is accomplished by conducting the incremental learning on the multi-class SVM classifier; and when a new target appears in visual fields of the cameras, and the appearance and the shape of the target are changed greatly, the target model is updated continuously by the incremental SVM learning. The method fuses the vocabulary tree histogram feature of the target with the color histogram feature, and increases an identification rate of the target significantly.

Description

technical field [0001] The invention belongs to the field of intelligent video monitoring in computer vision, and is suitable for a target matching method based on multi-feature fusion and incremental learning for non-overlapping multi-camera video monitoring. Background technique [0002] In large-scale video surveillance sites (such as airports, subway stations, squares, etc.), for continuous tracking of targets in a multi-camera environment with no overlapping domains, target matching between multiple cameras is a key step. Here, target matching refers to a process in which the system automatically assigns corresponding target labels to multiple targets when multiple targets enter the field of view of another camera from one camera field of view. Traditional multi-camera target matching methods include feature-based target matching and tracking-based target matching. However, in a non-overlapping video surveillance environment, the cameras are relatively independent, and ...

AI Technical Summary

Problems solved by technology

Traditional color histogram features are easily affected by illumination changes and the optical characteristics of the camera itself, and the ability to recognize multiple types of targets is not strong

Although the SIFT feature has strong adaptability to the deformation and illumination changes of the image target, and the positioning accuracy is relatively high, when the SIFT feature is directly used for target matching, the target SIFT feature points extracted from each frame of video image The number is relatively large, some as many as thousands of feature points, and each feature point is a 128-dimensional feature vector, so when the SIFT feature is used for classification and recognition, the matching speed will be slower and the real-time performance will not be high.