Abstract
Recently, the information analysis technology of underwater has developed rapidly, which is beneficial to underwater resource exploration, underwater aquaculture, etc. Dangerous and laborious manual work is replaced by deep learning-based computer vision technology, which has gradually become the mainstream. The binocular cameras based visual analysis method can not only collect seabed images but also construct the 3D scene information. The parallax of the binocular image was used to calculate the depth information of the underwater object. A binocular camera based refined analysis method for underwater creature body length estimation was constructed. A fully convolutional network (FCN) was used to segment the corresponding underwater object in the image to obtain the object position. A fish’s body direction estimation algorithm is proposed according to the segmentation image. The semi-global block matching (SGBM) algorithm was used to calculate the depth of the object region and estimate the object body length according to the left and right views of the object. The algorithm has certain advantages in time and accuracy for interest object analysis by the combination of FCN and SGBM. Experiment results show that this method effectively reduces unnecessary information, improves efficiency and accuracy compared to the original SGBM algorithm.
Highlights
Ocean exploration and underwater information analysis play a major role in preventing various marine disasters, protecting the ocean’s ecological environment, and developing and utilizing ocean resources [1]
These methods for fish body length estimation are mainly based on caught fish, and it cannot be applied well to the underwater environment without restricted conditions
This paper proposes a body length estimation method based on binocular vision
Summary
Ocean exploration and underwater information analysis play a major role in preventing various marine disasters, protecting the ocean’s ecological environment, and developing and utilizing ocean resources [1]. Information 2020, 11, 476 with Convolution Neural Network features (R-CNN) is used to localize and segment each fish in the images. Salman et al [5] used a region-based convolutional neural network to detect freely moving fish in the unconstrained underwater environment. Abdullah et al [15] estimated the length of dead fish by combining the optical principles and image processing techniques. These methods for fish body length estimation are mainly based on caught fish, and it cannot be applied well to the underwater environment without restricted conditions. Combining the object segmentation algorithm fully convolutional network (FCN) with the stereo matching algorithm semi-global block matching (SGBM), the three-dimensional depth estimation of the interest object is realized, and the object body length calculation method is constructed to realize the underwater object body length estimation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
