Radar and photoelectric rotary table based target detection method in movable unmanned platform

Abstract

The invention discloses a radar and photoelectric rotary table based target detection method in a movable unmanned platform, and mainly solves the problem of low information fusion degree in the priorart. The method comprises that 1) a global path of a search task is planned, and the unmanned platform moves along the path; 2) targets to be searched are detected and classified in the movement process; and 3) all suspected target points except one of the highest probability are inserted into the global path, and the target point of the highest probability is determined, if the target point of the highest probability is of medium similarity, the point is driven to in a linear path and the step 2) is returned to, and if the target point of the highest probability is of high similarity, the point is driven to in a spiral path and multi-frame detection is carried out till a determining condition is met, and the target point is determined to be a final target. The information fusion degree is improved, the stability is high, and the method can be applied to different types of unmanned platform to execute the target search task.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a target detection method, which is suitable for intelligent detection of a specific target in a movable unmanned platform. Background technique [0002] With the increasing development and integration of mechanical automation and electronic information processing technology, the mobile unmanned intelligent processing platform came out immediately. The mobile unmanned intelligent processing platform can avoid the inaccuracy, insecurity and instability of human operation, which has triggered more and more relevant institutions at home and abroad to carry out research and development. Therefore, related technologies emerge in endlessly and present diversified development. At present, there are various mobile unmanned platform devices on the market: such as unmanned vehicles, drones, unmanned boats, robots, etc.; in order to make these unmanned devices perceive ...

AI Technical Summary

Problems solved by technology

Although this method combines the data of various information collection devices and makes them work together, the target detection process of this method is relatively simple and lacks systematicness and robustness: if multiple suspected targets are found, there is no reasonable investigation one by one. It will increase the probability of missed detection of the target; and after the target area is found, the UAV's path planning also lacks a detailed description, which will cause the device to pass through a certain area repeatedly, increasing the target search time and unnecessary system Cost; the detection is only based on the physical characteristics of the target to perceive the suspected target, which is one-sided, which greatly increases the probability of false detection of the target

Images