Sea cucumber detection and binocular visual positioning method based on deep learning

Abstract

The invention provides a sea cucumber detection and binocular visual positioning method based on deep learning, and is suitable for a submarine sea cucumber fishing task of an underwater robot of ocean pasture. The method mainly comprises the following steps of calibrating binocular cameras to obtain internal and external parameters of the cameras; correcting the binocular cameras, so that imagingorigin coordinates of left and right views are consistent, optical axes of the two cameras are parallel, left and right imaging planes are coplanar, and bipolar lines are aligned; performing submarine image data collection by utilizing the calibrated binocular cameras; performing image enhancement on the collected image data through a dark channel priority algorithm based on white balance compensation; performing deep learning-based sea cucumber target detection on a submarine image subjected to the image enhancement; and performing a binocular stereo feature point matching algorithm on the image which is subjected to the image enhancement and the deep learning to obtain two-dimensional regression frame information of a target, thereby obtaining three-dimensional positioning coordinate information of the target. According to the method, accurate positioning of underwater sea cucumber treasures can be realized, and manual participation is not needed.

Description

technical field [0001] The invention belongs to the field of machine vision and underwater target detection, and in particular relates to a new method for sea cucumber detection and positioning based on deep learning. Background technique [0002] In recent years, due to the very high nutritional value of sea cucumbers, sea urchins, scallops, abalones and other marine benthic organisms, the demand for the production of marine organisms has been increasing worldwide, and my country's aquaculture industry has continued to develop. Bottom fishing technology is also becoming increasingly important. At present, the most common method of catching seafood is artificial diving fishing. Aiming at the problems of traditional fishing technology, research on the automatic detection method of underwater marine biological targets can improve the problems of high risk factor, short operation time and serious physical injury in manual fishing operations, so that Robots replace humans to co...

AI Technical Summary

Problems solved by technology

[0004] Due to the fogging of underwater sea cucumber imaging, the decrease of contrast, the color degradation, and the changeable shape of sea cucumbers, the traditional underwater sea cucumber detection technology often needs to manually screen and extract multiple features, which has the disadvantages of poor sea cucumber classification accuracy and low three-dimensional positioning time efficiency. question

Images