Object measurement in real underwater environments using improved stereo matching with semantic segmentation

Accurately measuring distances in underwater environments is critical for applications such as underwater exploration and maintenance of underwater structures, but is limited by underwater environmental factors. To address this challenge, semantic segmentation and visual stereo matching are promising methods to achieve this goal. In this paper, we proposed a combination of Retinex and Curvature filter for image enhancement, and a modified SGBM (Semi-Global Block Matching) method using dilated SAD(sum of absolute differences) window and the dynamic disparity range obtained using semantic segmentation results to accelerate stereo matching, while also providing insight into the content of the sensed scene. By using the method we proposed, the measurement error is significantly reduced, even in extreme environments with low visibility and complex backgrounds. It showed strong adaptability when dealing with irregular shape objects, and sped up the calculation speed of the algorithm by reducing the calculation area. In the comparison experiment, we found that the error of SGBM with our image enhancement was reduced to 22.8%. By using our stereo matching algorithm, the error was further reduced to 6.2%, demonstrating its superiority for underwater measurement tasks. Our approach offered an efficient solution for autonomous distance measurement in challenging underwater environments.