Underwater Image Processing and Object Detection Based on Deep CNN Method

Abstract

Due to the importance of underwater exploration in the development and utilization of deep-sea resources, underwater autonomous operation is more and more important to avoid the dangerous high-pressure deep-sea environment. For underwater autonomous operation, the intelligent computer vision is the most important technology. In an underwater environment, weak illumination and low-quality image enhancement, as a preprocessing procedure, is necessary for underwater vision. In this paper, a combination of max-RGB method and shades of gray method is applied to achieve the enhancement of underwater vision, and then a CNN (Convolutional Neutral Network) method for solving the weakly illuminated problem for underwater images is proposed to train the mapping relationship to obtain the illumination map. After the image processing, a deep CNN method is proposed to perform the underwater detection and classification, according to the characteristics of underwater vision, two improved schemes are applied to modify the deep CNN structure. In the first scheme, a 1∗1 convolution kernel is used on the 26∗26 feature map, and then a downsampling layer is added to resize the output to equal 13∗13. In the second scheme, a downsampling layer is added firstly, and then the convolution layer is inserted in the network, the result is combined with the last output to achieve the detection. Through comparison with the Fast RCNN, Faster RCNN, and the original YOLO V3, scheme 2 is verified to be better in detecting underwater objects. The detection speed is about 50 FPS (Frames per Second), and mAP (mean Average Precision) is about 90%. The program is applied in an underwater robot; the real-time detection results show that the detection and classification are accurate and fast enough to assist the robot to achieve underwater working operation.

Application of computer vision in fish intelligent feeding system—A review

“…Each of these aspects has an impact on the establishment of a smart feeding system (Jia, 2019). Underwater image preprocessing enhances image contrast while preserving underwater image details, which can provide powerful input for subsequent research (Han, Yao et al, 2020). Fish growth status can be expressed using changes in fish body length and weight.…”

“…Fish lives in the water, which is very different from the air that humans have been in contact with for a long time. After underwater image processing, an underwater image is restored to the well‐known water image of the greatest extent, making subsequent processing more convenient (Han, Yao et al, 2020). Subsequent processing methods can also be carried out by means of additional water image processing, and the effect is improved and more familiar.…”

“…Therefore, similarities should be sought in the process of method transplantation and should not be tried blindly. Expanding the monitoring area, not limiting the method of a fixed environment, innovating and implementing methods can provide greater research space for future research (Junyu et al., 2018; Han, Yao et al, 2020). Among the methods we have summarized, there are relatively few documents related to the detection of fish weight and length.…”

“…Take Islam's research experiment results as an example, and compare the processing effects of different algorithms in underwater image enhancement research in Table 1. Han et al's research on underwater image processing and target detection uses a deep CNN‐based method (Han, Yao et al, 2020). In this paper, a combination of max‐RGB method and shades of grey method is applied to achieve the enhancement of underwater vision, and then, a CNN (Convolutional Neural Network) method for solving the weakly illuminated problem for underwater images is proposed to train the mapping relationship to obtain the illumination map.…”

“…According to dual‐target setting, two‐dimensional coordinates are converted to three‐dimensional coordinates. Han et al’s research is not only about detecting underwater organisms, but also including more accurate classification (Han, Yao et al, 2020). After the image processing, a deep CNN method is proposed to perform the underwater detection and classification, and according to the characteristics of underwater vision, two improved schemes are applied to modify the deep CNN structure.…”