1. College of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing 100081, China
2. The Key Laboratory for Special Fiber and Fiber Sensor of Hebei Province, School of Information Science and Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China
Abstract：A jellyfish detection algorithm based on improved Faster R-CNN is proposed. Firstly, a data set containing 7 species of jellyfishes is established. Secondly, on the premise of ensuring the accuracy, the number of branches C is set to 8 to solve the problem that ResNeXt (C=32) has a high amount of calculation for target detection. Finally, to solve the problems of low detection accuracy and small individuals unable to be recognized, expansion convolution is introduced into the residual network. The experimental results shown that compared with VGG16, ResNet101, ResNeXt (C=32) and ResNeXt (C=8), the mAP value of the proposed algorithm increase by 3.15%, 2.09%, 3.01% and 2.36%. F1-score increase by 2.53%, 1.99%, 2.01% and 2.31%. Loss function convergence value of the proposed algorithm approach to 0. Results of P-R curve, visual analysis and video detection show that the accuracy and detection number of jellyfish by the proposed algorithm is the best, the proposed algorithm has high detection accuracy and can meet the requirements of real-time monitoring.
Dong J, Liu C Y, Li W Q, et al. Morphology and structure of white nepheline jellyfish ［J］. Fisheries Science, 2005(2): 22-23.
Shi L J, Zhou Y, Cen G, et al. Automatic Detection of Internal Defects in Freshwater Nucle-free Pearls Based on OCT ［J］. Acta Metrologica Sinica, 2020, 41(10): 1226-1233.
［5］
Houghton J D R, Doyle T K, Davenport J, et al. Developing A Simple, Rapid Method for Identifying and Monitoring Jellyfish Aggregations from the Air ［J］. Marine Ecology Progress Series, 2006, 314(1): 159-170.
［7］
Kim H, Kim D, Jung S, et al. Development of a UAV-type jellyfish monitoring system using deep learning ［C］//Proceedings of 2015 IEEE International Conference on Ubiquitous Robots & Ambient Intelligence, Goyang, Korea, 2015.
［10］
Koo J, Jung S, Myung H. A jellyfish distribution management system using an unmanned aerial vehicle and unmanned surface vehicles ［C］//2017 IEEE OES International Symposium on Underwater Technology, Busan, Korea, 2017.
［12］
Vodopivec M, Mandeljc R, Makovec T, et al. Towards automated scyphistoma census in underwater imagery: A useful research and monitoring tool ［J］. Journal of Sea Research, 2018, 142(12): 147-156.
Li Y Q, Tang X X. Development and prospect of Marine ecology in China ［J］. Journal of Ocean University of China, 2020, 50(9): 1-9.
［4］
Colombo G A, Mianzan H, Madirolas A, et al. Acoustic characterization of gelatinous-plankton aggregations: Four case studies from the argentine continental shelf ［J］. ICES Symposium on Acoustics in Fisheries and Aquatic Ecology, 2003, 60(3): 650-657.
Wang J Y, Zhen Y, Wang G S, et al. Molecular biology identification methods and detection techniques for sea moon jellyfish based on mt-16SrDNA and mt-COI genes ［J］. Journal of Applied Ecology, 2013, 24(3): 847-852.
［8］
Kim S, Lee K, Yoon W D, et al. Vertical distribution of giant jellyfish, nemopilema nomurai using acoustics and optics ［J］. Ocean Science Journal, 2016, 51(1): 59-65.
［13］
Martin-Abadal M, Ruiz-Frau A, Hinz H, et al. Jellytoring: real-time jellyfish monitoring based on deep learning object detection ［J］. Sensors, 2020, 20(6): 1708.
Shao M S. Image Dehazing Based on Mixed Dark Channel Prior ［J］. Acta Metrologica Sinica, 2020, 41(7): 796-800.
［17］
Xu Y, Zeng X. Underwater image restoration based on red-dark channel prior and inverse filtering ［J］. Laser and Optoelectronics Progress, 2018, 55(2): 21-228.
Li H-X, Li J H, Li W H. A Visual Model Based on Attention Mechanism and Convolutional Neural Network ［J］. Acta Metrologica Sinica, 2021, 42(7): 840-845.
French G, Mackiewicz M, Fisher M, et al. JellyMonitor: automated detection of jellyfish in sonar images using neural networks ［C］//14th IEEE International Conference on Signal Processing, Beijing, China, 2018.
Li J X, Yu X L. Multi-scale Retinex image enhancement algorithm under foggy conditions ［J］. Computer Science, 2013, 40(3): 299-301.
Kim D, Shin J U, Kim H, et al. Development and experimental testing of an autonomous jellyfish detection and removal system robot ［J］. International Journal of Control, 2016, 14(1): 312-322.
Li X, Ding L, Li W, et al. FPGA accelerates deep residual learning for image recognition ［C］//IEEE Information Technology, Networking, Electronic and Automation Control Conference, Chengdu, China, 2017.
［16］
Galdran A, Pardo D, Picón A, et al. Automatic red-channel underwater image restoration ［J］. Journal of Visual Communication and Image Representation, 2015, 26: 132-145.
2023, Vol. 44 
