Target detection and localization method and system based on depth data

Abstract

The present invention proposes a target detection and positioning method and system based on depth data, including: using the depth data collected by a depth data sensor to obtain a depth map, constructing a background model of the depth map, and obtaining the target foreground area under the perspective of the depth map, Carry out preliminary segmentation of the target foreground area; use the projection matrix to map the initially segmented target foreground area to the top-view perspective, and re-segment the target foreground area under the top-view perspective according to the position difference of the target in the horizontal space; extract the foreground area Depth features and training to get the target detection model, use the target detection model to detect and locate the sticky target; carry out the associated tracking of the three-dimensional coordinate position on the detection and positioning results on the top view, and then map the detection and positioning results to the coordinates of the original depth map, Get the final target detection result. The invention can quickly and robustly complete the accurate detection and positioning of the target in the case of severe occlusion and illumination changes.

Description

technical field [0001] The invention relates to the technical field of video monitoring, in particular to a method and system for detecting and locating objects based on depth data. Background technique [0002] With the continuous progress of society and the rapid development of economic construction, video surveillance is more and more used in various industries and aspects. The intelligent video analysis monitoring system can automatically identify different objects, find abnormal conditions in the monitoring screen, and can issue alarms and provide useful information in the fastest and best way, so as to assist security personnel to deal with crises more effectively. [0003] Target detection is a basic function of video analysis technology, which is of great significance to the realization of subsequent target tracking, target recognition and behavior analysis applications, especially in the field of real-time target event monitoring, its importance is self-evident. ...

AI Technical Summary

Problems solved by technology

However, this technical solution is still limited by the characteristics of two-dimensional images, the detection effect is affected by illumination changes and target occlusion, and the accuracy of detection results is limited

Images