Multi-dimensional deep-sea fish recognition algorithm
1. Institute of Deep-sea Science and Engineering, Chinese Academy of Sciences, Sanya, Hainan 572000, China； 2. School of Ocean and Earth Science, Tongji University, Shanghai 200092, China
Abstract：To solve the difficulty of fish recognition and detection due to the nonuniformly distributed deep-sea light,the multi-dimensional deep-sea fish recognition algorithm was proposed based on visual cognition. The traditional GMM was optimized to initially determine the changing area from time dimension and construct the target features from space dimension for extracting the moving target completely. The fish recognition framework based on deep learning was established from spatio-temporal correlation dimension. The results show that the proposed algorithm can accurately extract moving objects under variously complex conditions. The AOM is more than 80%, which is better than that of current mainstream algorithms.
李晨1， 刘怡丹1,2， 孙科林1， 李勃1， 全向前1， 刘凯斌1. 多维度深海鱼类识别算法[J]. 江苏大学学报（自然科学版）, 2021, 42(3): 303-308.
LI Chen1, LIU Yidan1,2, SUN Kelin1, LI Bo1, QUAN Xiangqian1, LIU Kaibin1. Multi-dimensional deep-sea fish recognition algorithm[J]. Journal of Jiangsu University(Natural Science Eidtion)
, 2021, 42(3): 303-308.
VERMA G, GAUTAM S, AGARWAL R, et al. Implementation of smart video surveillance system using motion detection technique\[C\]∥Sensors and Image Processing, 2018: 65-72.
［2］
ELLINGSEN V M, ASPLUND J, OHLSON M. Spatial and temporal patterns in seed predation as revealed by reciprocal experiments and video surveillance in neighbouring beech and spruce forests\[J\]. Scandinavian Journal of Forest Research, 2017, 32(2): 105-114.
［3］
VAN EEKEREN A W M, SCHUTTE K, VAN VLIET L J. Multiframe super-resolution reconstruction of small moving objects\[J\]. IEEE Transactions on image processing, 2010, 19(11): 2901-2912.
［4］
HALL E C, WILLETT R M. Foreground and background reconstruction in Poisson video\[C\]∥Image Processing (ICIP), 2013 20th IEEE International Confe-rence, 2013: 2484-2488.
［5］
GUO F, WANG W, SHEN J, et al. Video saliency detection using object proposals［J］. IEEE transactions on cybernetics, 2017，48(11)：3159-3170.
［6］
WANG H, GAO J, YU L, et al. Combined improved Frequency-Tuned with GMM algorithm for moving target detection\[C\]∥Mechatronics and Automation (ICMA), 2017 IEEE International Conference, 2017: 1848-1852.
［7］
CHU G, ZHANG W. Video object segmentation algorithm based on background reconstruction\[C\]∥Computer Design and Applications (ICCDA), 2010 International Conference, 2010: 411-413.
LI Z L, BAO R, LIU W M. Moving object detection method based on complex fuzzy logic system \[J\]. Journal of Jiangsu University (Natural Science Edition), 2017, 38(6): 677-681.（in Chinese）
［9］
DING X, HE L, CARIN L. Bayesian robust principal component analysis\[J\]. IEEE Transactions on Image Processing, 2011, 20(12): 3419-3430.
ZENG Q R, LI P F, JI Y D, et al.An enhanced Cucker-Smale flocking model including the target directed inte-raction \[J\]. Journal of Sichuan University (Natural Science Edition), 2020, 57(5): 841-846. （in Chinese）
［11］
LI E, BO Z, CHEN M, et al. Ghost imaging of a mo-ving target with an unknown constant speed\[J\]. Applied Physics Letters, doi：10.1063/1.4885764.
［12］
CHEN C L, LI H, WEI Y, et al. A local contrast me-thod for small infrared target detection\[J\]. IEEE Tran-sactions Geoscience and Remote Sensing, 2014, 52(1): 574-581.
［13］
XIA H, SONG S, HE L. A modified Gaussian mixture background model via spatiotemporal distribution with shadow detection\[J\]. Signal, Image and Video Proces-sing, 2016, 10(2): 343-350.
［14］
ERICHSON N B, DONOVAN C. Randomized low-rank dynamic mode decomposition for motion detection\[J\]. Computer Vision and Image Understanding, 2016, 146: 40-50.
［15］
LIU X, XUE F. Moving target detection based on adaptive edge extraction algorithm\[C\]∥2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA), 2018: 1206-1211.
［16］
CHAREF A, OHSHIMO S, AOKI I, et al. Classification of fish schools based on evaluation of acoustic descriptor characteristics\[J\]. Fisheries Science, 2010, 76(1): 1-11.
［17］
ROBERTS P L D, JAFFE J S, TRIVEDI M M. Multi-view, broadband acoustic classification of marine fish: a machine learning framework and comparative analysis\[J\]. IEEE Journal of Oceanic Engineering, 2011, 36(1): 90-104.
［18］
DABBA A, TARI A, ZOUACHE D. Multiobjective artificial fish swarm algorithm for multiple sequence alignment\[J\]. Information Systems and Operational Research, 2020，58(1)：38-59.
［19］
KARTIKA D S Y, HERUMURTI D. Koi fish classification based on HSV color space\[C\]∥2016 International Conference on Information & Communication Technology and Systems， 2016: 96-100.
［20］
GOYAL K，SINGHAI J. Texture-based self-adaptive moving object detection technique for complex scenes \[J\]. Computers & Electrical Engineering, 2018，70：275-283.
［21］
OGUNLANA S O, OLABODE O, OLUWADARE S A A, et al. Fish classification using support vector machine\[J\]. African Journal of Computing & ICT, 2015, 8(2): 75-82.
［22］
THARWAT A, HEMEDAN A A, HASSANIEN A E, et al. A biometric-based model for fish species classification\[J\]. Fisheries Research, 2018, 204: 324-336.
［23］
STEPHENSON F, LEATHWICK J R, FRANCIS M P, et al. A New Zealand demersal fish classification using Gradient Forest models\[J\]. New Zealand Journal of Marine and Freshwater Research, 2020, 54(1): 60-85.
HU X D, LI Q S. WSN data fusion based on neural network optimized by artificial fish swarm algorithm\[J\]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2018,30(5): 614-619.（in Chinese）
［25］
STAUFFER C, GRIMSONWE L. Adaptive background mixture models for real-time tracking\[C\]∥Processing the IEEE Conference on Computer Vision and Pattern Recognition, 1999： 2246-2252.
［26］
SAHINER B, PETRICK N, CHAN H P, et al. Compu-ter-aided characterization of mammographic masses: accuracy of mass segmentation and its effects on characte-rization\[J\]. IEEE Transactions on Medical Imaging, 2001, 20(12): 1275-1284.
2021, Vol. 42 
