Pulse neural network target tracking method and system based on event camera

Abstract

The invention belongs to the field of target tracking, and particularly relates to a pulse neural network target tracking method and system based on an event camera, and the method comprises the steps: obtaining an asynchronous event data flow in a target high-dynamic scene through the event camera; dividing the asynchronous event data stream into event frame images with millisecond-level time resolution; a target image is used as a template image, a complete image is used as a search image, a twin network based on a pulse neural network is trained, the network comprises a feature extractor and a cross-correlation calculator, and after feature mapping of the image is extracted through the feature extractor, the cross-correlation calculator is used for calculating a feature mapping result; and performing interpolation up-sampling on a feature mapping result by using the trained network to obtain the position of the target in the original image so as to realize target tracking. According to the invention, the transmission delay of image data and the calculation delay of a target tracking algorithm are reduced, and the precision of target tracking in a high-dynamic scene is improved.

Description

technical field [0001] The invention relates to the field of target tracking, in particular to an event camera-based pulse neural network target tracking method and system. Background technique [0002] The recognition and tracking of moving targets is a hot issue in the field of computer vision, and has a wide range of applications in human-computer interaction, video tracking, visual navigation, robotics, and military guidance. At present, there are two mainstream technical routes for target tracking based on correlation filtering and deep learning. [0003] The method based on correlation filtering is fast, but the feature extraction ability is limited, and the effect is poor when facing the problem of scale transformation and target loss. The method based on deep learning has good feature expression ability and higher tracking accuracy, but it is accompanied by an increase in the amount of calculation, which is limited in real-time tracking and is greatly affected by li...

AI Technical Summary

Problems solved by technology

[0003] The method based on correlation filtering is fast, but the feature extraction ability is limited, and the effect is poor in the face of scale transformation and target loss.

The method based on deep learning has good feature expression ability and higher tracking accuracy, but it is accompanied by an increase in the amount of calculation, which is limited in real-time tracking and is greatly affected by light, so it is not suitable for high-speed tracking. dynamic scene

Images