Integrated imaging identification system and method based on dynamic vision sensor

Abstract

The invention provides an integrated imaging identification system and method based on a dynamic vision sensor, and aims to solve the technical problems of high system power consumption and low targetidentification accuracy in the prior art. The imaging identification method comprises the following steps: a lens collects a plurality of images; the dynamic vision sensor senses the change of the image gray scale; a processor in the data acquisition module analyzes the signals output by the dynamic vision sensor to obtain an address event data stream; a denoising sub-module in the target recognition module is used for denoising the address event data flow; a segmentation sub-module in the target identification module segments the address event data stream; an identification sub-module in thetarget identification module identifies the address event data flow; and the data visualization module acquires an imaging identification result.

Description

technical field [0001] The invention belongs to the field of computer vision, and relates to an integrated imaging recognition system and method based on a dynamic vision sensor, which can be used for imaging recognition of ground targets carried by space. Background technique [0002] Imaging recognition systems and methods based on traditional image sensors are currently widely used, and have played a huge role in security alerts, maritime detection, and road traffic analysis. However, these imaging recognition systems based on traditional image sensors have many defects. In short, A traditional image sensor is a sensor that integrates energy, and the integration process often lasts for tens of milliseconds, which prolongs the response time of the camera and makes it difficult for traditional image sensors to capture fast-moving targets. During the integration process, if the target moves relative to the traditional image sensor, it will cause the traditional image sensor ...

AI Technical Summary

Problems solved by technology

[0004] In their paper "A Reservoir-based ConvolutionalSpiking Neural Network for Gesture Recognition from DVS Input" (2020International Joint Conference on Neural Networks), Arun M.George et al. proposed a method of using spiking neural networks to output data from dynamic visual sensors. The method of target recognition, this method uses the pulse neural network to compress the output data of the dynamic visual sensor, and achieves a high target recognition accuracy rate. The disadvantage of this method is that this method introduces event preprocessing The layer recodes the output data of the dynamic visual sensor, and the calculation speed is slow. The spiking neural network used has a relatively large amount of calculation on non-neuromorphic hardware, and the target recognition speed is slow, so real-time target recognition cannot be realized. Effective supervised training method, in the application of object recognition, the performance of spiking neural network is not better than that of traditional convolutional neural network

[0005] In their paper "A Differentiable Recurrent Surface for Asynchronous Event-Based Data" (2020arXiv.org), Marco Cannici et al. proposed a feature extraction method for the output event stream of a dynamic visual sensor using a long-term short-term memory network, and convolution The method of neural network for target recognition on the feature extraction results, the disadvantage of this method is: in the process of feature extraction of the event stream output by the dynamic visual sensor, it is necessary to perform event-by-event feature extraction on the event stream, and it needs Introduce redundant information, thereby increasing the calculation amount of convolutional neural network for target recognition

Images