Abstract To fast detect underwater fish in unrestricted underwater environment based on underwater video collected by underwater robots, a real-time detection algorithm for underwater fish based on improved you only look once(YOLO) and transfer learning is proposed. Firstly, an underwater-YOLO for the embedding computer system of underwater robots is designed to overcome the shortcomings of traditional YOLO. Then, transfer learning strategy is employed to train the underwater-YOLO network and alleviate the limitation of known underwater fish samples. A preprocessing algorithm based on contrast limited adaptive histogram equalization is proposed to overcome the problem of underwater image degradation. Finally, a video frame selection method for foreground computation of underwater-YOLO based on structure similarity between inter-frames is proposed to increase the detection frame rate. The experimental results show that the proposed algorithm achieves the goal of real-time detection of underwater fish in unconstrained underwater environment. Compared with the traditional YOLO,the proposed underwater-YOLO generates better detection performance in complex scenes with small fish and overlapped fishes.
Fund:05202), National Natural Science Foundation of China(No.61132005), National Marine Technology Program for Public Welfare of China (No.201605002)
About author:: (LI Qingzhong, Ph.D., professor. His research interests include image processing, signal processing and pattern recognition.) (NIU Jiong, Ph.D. candidate, engineer. His research interests include high frequency radar signal processing and high frequency radar marine environment monitoring technology.)
[1] QIAO X, BAO J H, ZENG L H, et al. An Automatic Active Contour Method for Sea Cucumber Segmentation in Natural Underwater Environments. Computers and Electronics in Agriculture, 2017, 135: 134-142. [2] LI Q Z, ZHANG Y, ZANG F N. Fast Multicamera Video Stitching for Underwater Wide Field-of-View Observation. Journal of Electronic Imaging, 2014, 23(2): 367-368. [3] BONIN-FONT F, OLIVER G, WIRTH S, et al. Visual Sensing for Autonomous Underwater Exploration and Intervention Tasks. Ocean Engineering, 2015, 93(1): 25-44. [4] MAHMOOD A, BENNAMOUN M, AN S J, et al. Deep Image Re-presentations for Coral Image Classification. IEEE Journal of Oceanic Engineering, 2019, 44(1): 121-131. [5] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 580-587. [6] GIRSHICK R. Fast R-CNN // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2015: 1440-1448. [7] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 6(1): 1137-1149. [8] REDMON J, DIVVALA S, GIRSHICK R, et al. You Only Look Once: Unified, Real-Time Object Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 779-788. [9] REDMON J, FARHADI A. YOLO9000: Better, Faster, Stronger // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 6517-6525. [10] REDMON J, FARHADI A. Yolov3: An Incremental Improvement[C/OL]. [2018-10-11].https://arxiv.org/pdf/1804.02767.pdf. [11] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: Common Objects in Context // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2014: 740-755. [12] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single Shot Multibox Detector // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 21-37. [13] HSIAO Y H, CHEN C C, LIN S I, et al. Real-World Underwater Fish Recognition and Identification, Using Sparse Representation. Ecological Informatics, 2014, 23: 13-21. [14] CUTTER G, STIERHOFF K, ZENG J M. Automated Detection of Rockfish in Unconstrained Underwater Videos Using Haar Cascades and a New Image Dataset: Labeled Fishes in the Wild // Proc of the IEEE Winter Applications and Computer Vision Workshops. Washington, USA: IEEE, 2015: 57-62. [15] SEESE N, MYERS A, SMITH K, et al. Adaptive Foreground Extraction for Deep Fish Classification // Proc of the 2nd Workshop on Computer Vision for Analysis of Underwater Imagery. Washington, USA: IEEE, 2016: 19-24. [16] LI X, TANG Y H, GAO T W. Deep But Lightweight Neural Networks for Fish Detection // Proc of the OCEANS 2017. Washington, USA: IEEE, 2017. DOI: 10.1109/OCEANSE.2017.8084961. [17] SUNG M, YU S C, GIRDHAR Y. Vision Based Real-Time Fish Detection Using Convolutional Neural Network // Proc of the OCEANS 2017. Washington, USA: IEEE, 2017. DOI: 10.1109/OCEANSE.2017.8084889. [18] LONG J, SHELHAMER E, DARRELL T. Fully Convolutional Net-works for Semantic Segmentation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 3431-3440. [19] PAN S J, YANG Q. A Survey on Transfer Learning. IEEE Trans-actions on Knowledge and Data Engineering, 2010, 22(10): 1345- 1359. [20] YOSINSKI J, CLUNE J, BENGIO Y, et al. How Transferable Are Features in Deep Neural Networks? // Proc of the 27th Internatio-nal Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2014: 3320-3328. [21] RUSSAKOVSKY O, DENG J, SU H, et al. Imagenet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 2015, 115(3): 211-252.
[22] LI X, SHANG M, HAO J, et al. Accelerating Fish Detection and Recognition by Sharing CNNs with Objectness Learning // Proc of the OCEANS 2016. Washington, USA: IEEE, 2016. DOI: 10.1109/OCEANSAP.2016.7485476.
2019, Vol. 32 
