Design and Testing of Unmanned Boat System for In-situ Counting of Sea Cucumbers in Pond Aquaculture

LIU Xiaoyang, WANG Wenliang, ZHENG Xinyu, CHEN Jiaying, CHEN Qijun, ZHAO Yonggang, LING Yuanshan

Abstract

Aiming to address the issues of high risk, high cost, and low efficiency in existing underwater sea cucumber observation and counting methods, an autonomous unmanned surface vehicle (USV) system for sea cucumber multi-target tracking and counting in pond aquaculture environments was designed. The system adopted a hierarchical and modular architecture, enhancing flexibility, stability, and maintainability. The hardware included a hull, an underwater perception system, and an onboard control box, featuring a quick-release and foldable design with a swivel buckle mechanism for easy transportation and installation. Additionally, the system integrated an autonomous underwater video capture module, combined with altitude-holding and trajectory-tracking algorithms to ensure stable and autonomous video acquisition. A sea cucumber detection and counting algorithm based on YOLO v10 and ByteTrack enabled fast and accurate counting. Experimental results demonstrated that the USV and underwater perception module remained stable under Level 3 wind and waves, with a pitch angle range of -18° to 18°. The counting algorithm achieved a normalized mean absolute error (NMAE) of 0.1111, while the trajectory planning maintained an average error of 0.47m. The altitude-holding algorithm converged within 10s. Field tests in aquaculture environments confirmed that the system was stable and reliable, meeting the daily operational requirements of pond aquaculture.

 

Keywords: USV for in-situ sea cucumber counting, underwater photography, aquaculture, multi-target tracking

 

Download Full Text:

PDF


References


YANG Hongsheng. Construction of marine ranching in China: retrospect and prospect [J]. Journal of Fisheries of China, 2016, 40(7); 1133 - 1 140.

LI Daoliang, LIU Chang. Research applications and future prospects of artificial intelligence in aquaculture [J]. Smart Agriculture, 2020, 2(3): 1 -20.

TROBBIANI G A, VENERUS L A. A novel method to obtain accurate length estimates of carnivorous reef fishes from a single video camera [J] . Neotropical Ichthyology, 2015, 13(1): 93 — 102.

DORMAN S R, HARVEY E S, NEW MAN S J. Bait effects in sampling coral reef fish assemblages with Stereo-BRUVs[J]. PLoS One, 2012, 7(7) : e41538.

TIAN Lujun, WU Mengxuan, JIA Peng, et al. Study on light field distribution and imaging performance of underwater video surveillance systems[J]. Oil Field Equipment, 2024, 53(2): 19 -25.

CHE Yanhe, LIU Chang, SHENG Zhibin, et al. Research on low-visibility undenvater camera system for shallow-water aquaculture [J]. Fishery Modernization, 2020, 47(5): 15 -22.

XU Pengfei, CHEN Meiya, KAI Yan, et al. Research progress on remotely operated vehicle technology for undenvater inspection of large hydropower stations[J]. Journal of Tsinghua University (Science and Technology) , 2023, 63(7) : 1032 - 1040.

SUN Gongwu, SU Yixin, MAO Ying, et al. Fuzzy logic-based multi-stage thrust allocation strategy for hybrid propulsion ROVs [J]. Robot, 2023, 45(4) : 472 -482. (in Chinese)

HUANG Zhaojun, ZENG Mingru. Intelligent control methods for small tethered remotely operated undenvater vehicles [J]. Research and Exploration in Laboratory, 2024, 43 (7) : 34 -38,53.

HUANG Haoqian, ZHENG Kangjian, MA Jingtian. Model predictive-based sliding mode control method for AUV trajectory tracking [J]. Journal of Chinese Inertial Technology, 2024, 32(2) ; 205 -212. (in Chinese)

WANG Jinpeng, HE Meng, ZHEN Qianguang, et al. Camellia oleifera fruits static and dynamic detection counting based on improved COF — YOLO v8n[J ]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55(4) ; 193 -203.

WANG Ling, ZHANG Qi, FENG Tianci, et al. Wheat grain counting method based on YOLO v7 - ST model [J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54( 10) ; 188 - 197,204. (in Chinese)

BAO Wenxia, XIE Wenjie, HU Gensheng, et al. Wheat ear counting method from UAV images based on TPH — YOLO [J]. Transactions of the CSAE, 2023, 39( 1 ) : 155 -161. (in Chinese)

FAN Songwei, LIN Xiangyu, ZHOU Ping. Automatic shrimp fry counting using improved convolutional neural network [J]. Fisher)' Modernization, 2020, 47(6) ; 35 —41.

AN Zhiqiang, LI Zhijun, LIU Shuo, et al. Multi-category seafood counting method by integrating YOLOv7 and BYTE multi¬object tracking [J] . Transactions of the CSAE, 2023 , 39(9) ; 183 - 189.

ZHANG Lu, HUANG Lin, LI Beibei, et al. Fish population counting method based on multi-scale fusion and anchor-free YOLOv3 [J ]. Transactions of the Chinese Society for Agricultural Machinery, 2021 , 52(Supp. ) : 237 -244. (in Chinese)

NING Jun, MA Yifan, LI Wei, et al. Adaptive fuzzy tracking control for unmanned surface vessels with state/input quantization [J]. Journal of South China University of Technology (Natural Science Edition) , 2024, 52(5) : 52 —61. (in Chinese)

YU Те, LIU Jiapeng, WU Chao, et al. Cooperative motion control strategy for USV and AUV based on nonlinear disturbance observer. Journal of Shanghai Jiao Tong University, 2023, 57 (Supp. 1 ) ; 114 - 123. ( in Chinese)


Refbacks

  • There are currently no refbacks.