Deep-sea seabed obstacle measurement system and identification method based on deep learning

Abstract

The invention discloses a deep-sea seabed obstacle identification method based on deep learning, and the method comprises the following steps: calibrating a camera, and obtaining the internal and external parameters of the camera; collecting and preprocessing an image data set, and carrying out mold offline training and evaluating; collecting a submarine topographic image, and measuring the distance from the camera to an obstacle; processing the collected image based on a deep learning semantic segmentation technology, and obtaining feature parameters of the obstacle; fusing the internal and external parameters obtained through calibration and the measured distance parameters through a data fusion module, converting the characteristic parameters of the obstacle into actual parameters of the obstacle, and therefore basic information of the obstacle is obtained. According to the identification method, the deep learning technology, camera calibration, laser ranging and other methods are fused to obtain the actual characteristic parameters of the obstacle, so that the mobile deep sea sampling equipment can carry out driving trafficability analysis, automatic obstacle avoidance and path planning research.

Description

technical field [0001] The invention relates to a deep-sea submarine obstacle measurement system and identification method based on deep learning. Background technique [0002] The ocean contains extremely rich mineral resources such as polymetallic nodules, cobalt-rich crusts, and polymetallic sulfides. According to current preliminary surveys, 15% of the deep sea area contains polymetallic nodule resources, with a total reserve of about 3 trillion tons. It mainly occurs on the surface of the seabed at a water depth of 3000m to 6000m; the seabed of about 6.35 million square kilometers (accounting for 1.7% of the seabed area) is covered by cobalt-rich crusts. Based on this calculation, the total amount of cobalt is about 1 billion tons, mainly Distributed on the seabed at a water depth of about 400m to 4000m, with a maximum thickness of about 24cm; polymetallic sulfides (also known as hydrothermal sulfides) are heavy metal mineral resources in the seabed that have attracted ...

AI Technical Summary

Problems solved by technology

However, the shapes and surface textures of deep-sea submarine obstacles are different, and the conventional pattern recognition method cannot realize the identification of obstacles, and it is also difficult to measure the actual characteristic information of obstacles.

Images