Lightweight Salmon Detection Model Based on Improved YOLO v7
Abstract
In order to achieve rapid and accurate identification of salmon in complex underwater environments, a lightweight salmon detection model, YOLO v7-CSMRep, was proposed based on YOLO v7. Firstly, by adopting the Stem module, the first four convolutional operations in the backbone layer were merged into an efficient convolutional operation, reducing the computational load of the model. Secondly, the ELAN and ELAN-H modules of the YOLO v7 network were replaced with the multi-directional reparameterization (MRep) module, which enhanced the one-way feature extraction capability while greatly reducing parameters and calculations. Finally, at the end of the backbone layer, the convolutional block attention module (CBAM) was integrated to enhance the network’s spatial and channel feature extraction capabilities. The experimental results showed that the improved model’s volume, parameter count, and computational load were reduced by 4.28%, 5.29% and 31.30%, respectively. The F1 score and mAP0.5 were increased by 0.5 and 0.7 percentage points, and reached 93.1% and 97.1%, respectively. Additionally, the frame rate was increased by 15.41%, and reached 140.8f/s. Compared with that of YOLO v5s, YOLO v6s, YOLO v7, YOLO v7-tiny, and YOLO v8s models, the mAP0.5 was improved by 1.0, 2.0, 0.7, 0.8, and 1.2 percentage points, respectively. Therefore, the method proposed can rapidly and accurately identify salmon and provide technical support for biomass monitoring in deep-sea aquaculture.
Keyword: deep-sea aquaculture ; salmon detection ; YOLO v7 ; Stem module ; multi-directional reparameterization ; convolutional block attention module
Download Full Text:
PDFReferences
XU Lejun, ZHAO Lei, LI Xue, et al. The basic thoughts of building a powerful fishery country from the perspective of No. 1 Central Document; Interpretation of the No. 1 Central Document for 2023 and the fishery development strategy [J]. Chinese Fisheries Economics, 2023, 41 (2 ): 1 -13.
LUO Yihao, LIU Qipei, ZHANG Yin, et al. Review of underwater image object detection based on deep learning[J]. Journal of Electronics & Information Technology ,2023 ,45 ( 10) :3468 -3482.
GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation [С]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition ,2014 :580 -587.
GIRSHICK R. Fast R - CNN [С] // Proceedings of the IEEE International Conference on Computer Vision ,2015 :1440 - 1448.
REN S, HE K, GIRSHICK R, et al. Faster R — CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,39(6) : 1137 - 1149.
HE K, GKIOXARI G, DOLLAR P, et al. Mask R - CNN С //Proceedings of the IEEE International Conference on Computer Vision,2017:2961 -2969.
LIU W, ANGUELOV D, ERIIAN D, et al. SSD: single shot multibox detector[С]// European Computer Vision —ECCV 2016: 14th European Conference. Amsterdam; Springer International Publishing,2016:21 -37.
REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once; unified, real-time object detection [ С ] // IEEE Conference on Computer Vision and Pattern Recognition. IEEE ,2016 ;779 -788.
REDMON J, FARHADI A. YOL09000; better, faster, stronger [С] //IEEE Conference on Computer Vision and Pattern Recognition. IEEE ,2017 :7263 -7271.
REDMON J, FARHADI A. YOLO v3: an incremental improvement [С]//Computer Vision and Pattern Recognition,2018;1 -6.
BOCHKOVSKIY A, WANG С Y, LIAO H Y M. YOLO v4: optimal speed and accuracy of object detection [C] //IEEE Conference on Computer Vision and Pattern Recognition. IEEE,2020;1 - 17.
SUN Z, CHEN B. Research on pedestrian detection and recognition based on improved YOLO v6 algorithm [С] // International Conference on Artificial Intelligence in China,2022:281 -289.
SOEB M J A, JUBAYER M F, TARIN T A, et al. Tea leaf disease detection and identification based on YOLO v7 ( YOLO — T)[J]. Scientific Reports,2023 ,13(1) :6078.
WU Xing, QI Zeyu, W ANG Longjun, et al. Apple detection method based on light-YOLO v3 convolutional neural network [J] . Transactions of the Chinese Society for Agricultural Machinery ,2020,51 ( 8 ) ; 17 -25. (in Chinese)
MENG F, CHENG II, LI K, et al. Pruning filter in filterf J - Advances in Neural Information Processing Systems,2020,33 : 17629 - 17640.
FANG Peng, HAO Hongvun, WANG Hongying. Behavior recognition model of stacked-cage layers based on knowledge distillation. Transactions of the Chinese Society for Agricultural Machinery ,2021 ,52( 10) :300 -306. (in Chinese)
TAN K, WANG D. Compressing deep neural networks for efficient speech enhancement [С] // IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ,2021 -.8358 -8362.
HOWARD A G, ZHU M, CHEN B, et al. Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv Preprint, arXiv; 1704. 04861, 2017.
SANDLER M, HOWARD A, ZHU M, et al. Mobilenetv2: inverted residuals and linear bottlenecks [С]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2018 :45 10 -4520.
HOWARD A, SANDLER M, CHU G, et al. Searching for Mobilenetv3 [С] //Proceedings of the IEEE/CVF International Conference on Computer Vision,2019:1314 - 1324.
FRAN C. Deep learning with depth wise separable convolutions [С] // IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
ZHANG X, ZHOU X, LIN M, et al. Shufflenet: an extremely efficient convolutional neural network for mobile devices [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition ,2018 ;6848 -6856.
HAN K, WANG Y, TIAN Q, et al. Ghostnet; more features from cheap operations [С] //Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition ,2020; 1580 - 1589.
TAN M, LE Q. Efficientnet; rethinking model scaling for convolutional neural networks [С] // International Conference on Machine Learning. PMLR, 2019; 6105 -6114.
LUO Zhicong, LI Pengbo, SONG Feiyu, et al. Lightweight passion fruit detection model based on embedded device [J].
Transactions of the Chinese Society for Agricultural Machinery,2022,53( 1 1 ) ;262 -269,322.
MIAO Ronghui, LI Zhiwei, WU Jinlong. Lightweight maturity detection of cherry tomato based on improved YOLO v7 [J]. Transactions of the Chinese Society for Agricultural Machinery ,2023 ,54 ( 10) *.225 -233. (in Chinese)
LI Li, LU Shibo, REN Hao, et al. Mulberry branch identification and location method based on improved YOLO v5 in complex environment [J ]. Transactions of the Chinese Society for Agricultural Machinery ,2024,55 ( 2 ) ;249 -257.
LI Jianyuan, LIU Chunna, LU Xiaochun, et al. Fish passage monitoring based on improved YOLO v5s and TensorRT deployment [J]. Transactions of the Chinese Society for Agricultural Machinery ,2022 ,53 ( 12) : 3 14 -322.
QIN Xuebiao, HUANG Dongmei, SONG Wei, et al. Fish image segmentation method based on object detection and edge support[J] . Transactions of the Chinese Society for Agricultural Machinery ,2023 ,54( 1 ) :280 -286.
Refbacks
- There are currently no refbacks.
