Unmanned ship perception fusion algorithm based on deep learning

Abstract

The invention provides an unmanned ship perception fusion algorithm based on deep learning, and the algorithm comprises the steps: 1, carrying out target detection of a single-frame image collected bya camera, and obtaining machine vision data; 2, filtering and clustering the data input by the laser radar, and clustering discrete points into target information to obtain radar data; 3, performingdata association on the radar data and the machine vision data; after the step 1 and the step 2 respectively process the data of the camera and the radar, matching observation targets of the radar data and the machine vision data, establishing a data association model of the radar data and the machine vision data to obtain an association matrix of the radar and the vision measurement target, and screening out a target with a relatively high association degree through the association matrix of the radar and the vision measurement target so as to realize sensing of the target. According to the method, the advantages of the radar sensor and the visual sensor can be fused, enough target information is provided for unmanned ship environment perception, and the method has certain robustness andcan adapt to certain interference.

Description

technical field [0001] The invention relates to the field of perception fusion of unmanned boats, in particular to a deep learning-based algorithm for perception fusion of unmanned boats. Background technique [0002] Unmanned Surface Vehicle (USV) is a kind of surface unmanned system that has autonomous capabilities and can perform specific tasks. Unmanned boats play an important role in both military and civilian applications. With future conflicts largely taking place in littoral regions of the globe, it may no longer be wise to put soldiers at risk against an enemy with increasingly effective weapon systems. USVs will provide the Navy with additional combat power, especially in situations where loss of life is unacceptable. USVs can be deployed in waters unacceptable to manned ships, including high-risk environments or areas contaminated by nuclear, biological or chemical agents. They are reliable, fast, highly maneuverable, and can perform a variety of missions, incl...

AI Technical Summary

Problems solved by technology

X-band radar and millimeter-wave radar are all-weather radars, which have the advantages of large detection range and long detection distance, and can provide good early warning and tracking for long-distance large objects; the advantage of laser radar is its high detection accuracy, but multi-line laser Radar has a high price, and its working performance is not stable, and it is easily affected by factors such as weather and visibility; the biggest advantage of visible light cameras is that it can identify objects and obtain a high-level understanding of the environment, but like lidar, it is affected by The influence of the environment is greater, and as the visibility decreases, its measurement range, measurement distance, and measurement accuracy will decrease; infrared detection can use temperature differences to detect targets under the condition of reduced visibility, but its accuracy is also affected by the environment. impact, and the detection distance is relatively short; ultrasonic detection can adapt to all kinds of bad weather, the disadvantage is that the detection distance is very limited

Images