A multi-target tracking system and tracking method based on fusion detection technology

Abstract

The invention discloses a multi-target tracking method based on fusion detection technology. The method firstly models the surveillance video and pictures, outputs the category and location information of the concerned target stably and accurately, and tracks them. Specifically, first classify and locate the target in the picture through the target detector, and then use the tracker based on motion modeling to continuously predict the target trajectory, and then input the detection area and motion prediction area into the shape feature acquisition network to obtain their respective Based on the matching features of the target position and matching features, the data association between the two and the correction of the final tracking result box are completed. This method can detect target information accurately and quickly. At the same time, the motion prediction position and matching feature network make full use of the target motion and shape features, and the result of multi-target tracking is more accurate through matching and frame correction.

Description

technical field [0001] The invention belongs to the technical field of intelligent identification, and in particular relates to a multi-target tracking method based on fusion detection technology. Background technique [0002] The multi-target tracking method has a wide range of applications in engineering, for example, it plays a key role in the monitoring of road traffic and the identification of violations of laws and regulations. Given the relevant video, traditional tracking methods need to manually initialize the target box for tracking. With the development of deep learning, tracking techniques based on neural network detection are also increasing. [0003] Most of the detection methods currently used in detection algorithms use one-stage or two-stage target detection algorithms. The one-stage target detection algorithm is to directly map the features to the coordinate information and category information of the target, and the two-stage target detector first performs...

AI Technical Summary

Problems solved by technology

This type of method has proved its effectiveness to a certain extent, but this kind of design process means that the performance of tracking depends on the detection results unilaterally, and at the same time, obtaining distinguishable visual features introduces a complex mechanism and a huge amount of calculation. This makes the tracking results limited, but also lacks in efficiency

Images