Publications
Sort:
Open Access Issue
Research on nighttime intelligent monitoring method for deep-sea cage fish school based on water surface infrared images
South China Fisheries Science 2024, 20(1): 81-88
Published: 05 February 2024
Abstract PDF (2.3 MB) Collect
Downloads:0

Obtaining fish school information on its size and behavior through fish school monitoring is an important way to improve the efficiency of deep sea aquaculture and reduce costs. In this study, an intelligent fish school monitoring method is proposed by using infrared cameras mounted on a net cage for data collection, in addition to the latest deep learning techniques for model training. The method involves three functional modules: fish detection, fish segmentation and fish pose determination. Firstly, fish images were collected by infrared cameras and manually annotated to build datasets, while an improved faster RCNN model that uses Mobilenetv2 and FPN network as feature extractors to improve detection accuracy is adopted to output bounding boxes of individual fish. Secondly, the top 20% of brightness pixels in the block map were selected as segmentation prompt points, and the image was segmented using Segment Anything Model to generate fish segmentation results. Finally, the fish pose information was determined by applying elliptical fitting using fish segmentation results. After 100 epochs of training, the average precision (AP) of the improved Faster RCNN model reached 84.5%, and the detection time per image was 0.042 s. The results indicate that the proposed method can achieve automatic monitoring of fish school on infrared images and extract effective information.

Open Access Issue
Construction of a dynamics simulation system for net cleaning robot based on Gazebo
South China Fisheries Science 2024, 20(1): 1-10
Published: 05 February 2024
Abstract PDF (2.5 MB) Collect
Downloads:0

Deep-sea cage aquaculture is an important marine aquaculture mode. Regular cleaning of cage nets is a critical step to ensure aquaculture quality and safety. Currently, nets are commonly cleaned manually, which is time-consuming and labor-intensive. As deep-sea cages grow larger, their manual cleaning become more difficult. Net washing robots provide a safer and more convenient way to clean nets for deep-sea cages. However, it is challenging to design controllers with strong disturbance resistance and low energy consumption for net washing robots, as the forces are difficult to model and the states are hard to observe during net cleaning and underwater shuttling. Moreover, conducting comprehensive experiments and data recording requires high costs and much time. To address these problems, we constructed a simulation system for a net washing robot based on the physical simulation environment Gazebo, considering the presence of thrusters and washing discs. Besides, we analyzed the effects of various hydrodynamic characteristics in underwater environment, such as added mass and damping, and factors like flow field environment on the washing robot. The established net washing robot can obtain complete data on the underwater operation of the net washing robot, verify control performance, and compare model performance more easily, thereby assisting in the controller development of washing robots.

Total 2