Multi-camera system target matching method based on deep-convolution neural network

Abstract

Disclosed is a multi-camera system target matching method based on a deep-convolution neural network. The multi-camera system target matching method based on the deep-convolution neural network comprises initializing multiple convolution kernels on the basis of a local protective projection method, performing downsampling on images through a maximum value pooling method, and through layer-by-layer feature transformation, extracting histogram features higher in robustness and representativeness; performing classification and identification through a multi-category support vector machine (SVM) classifier; when a target enters one camera field of view from another camera field of view, performing feature extraction on the target and marking a corresponding target tag. The multi-camera system target matching method based on the deep-convolution neural network achieves accurate identification of the target in a multi-camera cooperative monitoring area and can be used for target handoff, tracking and the like.

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 a deep convolutional neural network in a multi-camera collaborative video monitoring system. Background technique [0002] In large-scale video surveillance places, such as airports, subway stations, squares, etc., for the tracking of targets in a multi-camera collaborative monitoring system, target matching between multiple cameras is a key step. For large-scale video surveillance scenes, camera calibration is difficult and complex, and it is difficult to reason about the spatial relationship, temporal relationship, and time difference between each other. Therefore, the currently widely used target matching method between multiple cameras is mainly feature-based target matching. , the effectiveness of feature selection directly affects the accuracy of matching results. However, the extraction of robust features ...

AI Technical Summary

Problems solved by technology

For large-scale video surveillance scenes, camera calibration is difficult and complex, and it is difficult to reason about the spatial relationship, temporal relationship, and time difference between each other. Therefore, the currently widely used target matching method between multiple cameras is mainly feature-based target matching. , the effectiveness of feature selection directly affects the accuracy of matching results

However, the extraction of robust features that can effectively represent the target is a difficult problem

Currently commonly used features include color, texture, etc. These features are difficult to maintain good robustness in all monitoring scenarios

Images