Visual sensor network multi-target tracking method, device and system

Abstract

The embodiment of the invention discloses a visual sensor network multi-target tracking method, device and system. The method comprises the following steps of using an edge calculation node to receivethe pedestrian target data obtained by detecting a pedestrian target from an acquired image by a visual sensor node; according to the pedestrian target data, constructing the pedestrian target cohesion model, and correlating the detection response of the same pedestrian target to form the target trajectory; tracking the pedestrian target corresponding to the target trajectory, obtaining the tracking result, and sending the tracking result to the cloud computing center, thereby realizing the effective reduction of the background pixel pollution, while segmenting the boundary between adjacent targets, greatly reducing the amount of data transmission. By using the edge calculation node to construct the pedestrian target cohesion model to form target trajectory and tracking the pedestrian target corresponding to the target trajectory, and sending the tracking results to the cloud computing center, the search space can be effectively reduced, the accuracy of data association can be improved, and the user's privacy can be protected at the same time.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image processing, and in particular to a multi-target tracking method, device and system for a visual sensor network. Background technique [0002] Intelligent security has attracted widespread attention in international and domestic academic and industrial circles. In 2006, the city of Chicago in the United States launched a virtual prevention plan. The system connected tens of thousands of public cameras in Chicago to implement extensive monitoring 24 hours a day. In March 2014, the Central Committee of the Communist Party of China and the State Council issued the "National New Urbanization Plan (2014-2020)", clearly "promoting the construction of smart cities", and formally included smart cities in the national strategic planning, and smart security is the prerequisite for the construction of smart cities . Visual Sensor Networks (Visual Sensor Networks, VSN) integrate image sen...

AI Technical Summary

Problems solved by technology

With the expansion of the network scale, the explosive growth of raw image data that needs to be uploaded to the cloud will easily cause long network delays. This centralized computing architecture is difficult to meet the needs of real-time applications

In addition, this computing architecture needs to directly upload the original image data, which significantly increases the risk of personal privacy leakage

Images