Device and method for detecting high-speed tiny target online in real time by simulating fly vision

Abstract

The invention discloses a device and method for detecting a high-speed tiny target online in real time by simulating fly vision. The method comprises the following steps of: acquiring scene video information by using a binocular camera, transmitting the scene video information into a DSP (digital signal processor) chip, and performing primary vision processing; performing large scene and small scene integration and target detection on primary motional information by using an FPGA (field programmable gate array) chip; and tracking a tiny target moving at high speed by taking an integration result of a large scene and a small scene as a target detection evidence. The device and method disclosed by the invention have the advantages that: the target detection is realized by virtue of a biological principle; the device and method have relatively strong antijamming capability and are applicable to the target detection under the condition of a low signal-to-noise ratio in various severe natural environments; a neuron integrating mechanism of a fly vision system has the characteristics of simple computing principle, high real-time performance and the like; the fly vision neuron is simple in tissue structure and can be easily realized by hardware; and the device can be installed on an automobile, panzer, airplane and other appliances which move at high speed, and has the capability of accurately detecting the high-speed tiny target on line in real time in a dynamically changing background.

Description

technical field [0001] The invention relates to a high-speed tiny target detection device and a detection method, belonging to the technical field of image processing and target detection. Background technique [0002] The detection of moving targets in video images has always been one of the core issues in computer vision research, and it has broad application prospects in military guidance, unmanned aircraft driving, and robot vision navigation. Among them, the detection of small targets moving at high speed under dynamic complex background is the difficulty in the problem of moving target detection. The key reasons why this kind of problem is difficult to deal with are: the tiny target itself lacks features that are easy to analyze and identify; the signal-to-noise ratio of the tiny target is low due to the complex background; the background model is difficult to estimate and predict in the moving state; The characteristics are uncertain. [0003] To solve the above pro...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the limitations of the current computer vision on the detection of high-speed moving micro-targets, such as complex calculation principles, large amount of calculation, poor anti-background interference ability, etc., especially under the conditions of dynamic and complex natural scenes, the background model cannot be accurately estimated, and For problems such as the lack of features of high-speed moving tiny targets, the present invention draws on the large and small scene integration mechanism of fly vision to simulate the process of flies from visual information acquisition to retinal primary motion information estimation to lobular plate high-order neuron information integration processing, and constructs a complex Under the background, the high-speed micro-target imitation fly vision online detection device and its working method use the parallel neural integration mechanism to realize the detection and tracking of micro-targets

Images