Page 250 - 《水产学报》2026年第3期

3 期 李坤达，等：基于改进 YOLOv11 的海洋牧场中鲍的检测方法 50 卷

[12] Cui J, Zhang X L, Zhang J H, et al. Weed identification in soy- ation. Proceedings of 16th European Conference on Computer
bean seedling stage based on UAV images and Faster R- Vision. Glasgow: Springer, 2020: 213-229.
CNN[J]. Computers and Electronics in Agriculture, 2024, 227: [23] Tian S Z, Chen D B, Wang H, et al. Deep convolution stack for
109533. waveform in underwater acoustic target recognition[J]. Sci-
[13] Crespo A, Moncada C, Crespo F, et al. An efficient strawberry entific Reports, 2021, 11(1): 9614.
segmentation model based on Mask R-CNN and TensorRT[J]. [24] 张铮, 鲁祥, 胡庆松. 基于图像增强与 GC-YOLO v5s 的水下
Artificial Intelligence in Agriculture, 2025, 15(2): 327-337. 环境河蟹识别轻量化模型研究 [J]. 农业机械学报, 2024,
[14] Peng H X, Li Z H, Zhou Z Y, et al. Weed detection in paddy 55(11): 124-131,374.
field using an improved RetinaNet network[J]. Computers and Zhang Z, Lu X, Hu Q S. Lightweight model for river crab
Electronics in Agriculture, 2022, 199: 107179. detection based on image enhancement and improved YOLO
[15] Tan L, Wu H, Xu Z F, et al. Multi-object garbage image detec- v5s[J]. Transactions of the Chinese Society for Agricultural
tion algorithm based on SP-SSD[J]. Expert Systems with Machinery, 2024, 55(11): 124-131,374 (in Chinese).
Applications, 2025, 263: 125773. [25] Al Muksit A, Hasan F, Emon M F H B, et al. YOLO-Fish: a
[16] Terven J, Córdova-Esparza D M, Romero-González J A. A robust fish detection model to detect fish in realistic underwater
comprehensive review of YOLO architectures in computer vis- environment[J]. Ecological Informatics, 2022, 72: 101847.
ion: from yolov1 to yolov8 and YOLO-NAS[J]. Machine [26] 刘侦龙, 王骥, 麦仁贵. 基于改进 YOLOv10s 的海洋牧场水下
Learning and Knowledge Extraction, 2023, 5(4): 1680-1716. 海参检测方法 [J]. 农业工程学报, 2025, 41(10): 186-194.
[17] Tian Y N, Yang G D, Wang Z, et al. Apple detection during Liu Z L, Wang J, Mai R G. Detecting underwater sea cucumber
different growth stages in orchards using the improved YOLO- in marine ranching using improved YOLOv10s[J]. Transac-
V3 model[J]. Computers and Electronics in Agriculture, 2019, tions of the Chinese Society of Agricultural Engineering, 2025,
157: 417-426. 41(10): 186-194 (in Chinese).
[18] 董一兵, 曾辉, 侯少杰. LMUAV-YOLOv8: 低空无人机视觉 [27] Mai R G, Wang J. UM-YOLOv10: underwater object detection
目标检测轻量化网络 [J]. 计算机工程与应用, 2025, 61(3): 94- algorithm for marine environment based on YOLOv10
110. model[J]. Fishes, 2025, 10(4): 173.
Dong Y B, Zeng H, Hou S J. LMUAV-YOLOv8: lightweight [28] Lin Y, Zhou J C, Ren W Q, et al. Autonomous underwater
network for object detection in low-altitude UAV vision[J]. robot for underwater image enhancement via multi-scale
Computer Engineering and Applications, 2025, 61(3): 94-110 deformable convolution network with attention mechanism[J].
(in Chinese). Computers and Electronics in Agriculture, 2021, 191: 106497.
[19] Khan Z, Liu H, Shen Y, et al. Optimizing precision agriculture: [29] Huang Y Y, Huang J W, Huang M H. A Lightweight YOLO
a real-time detection approach for grape vineyard unhealthy Network for Robotic Underwater Biological Detection[J]. Fron-
leaves using deep learning improved YOLOv7 with feature tiers in Marine Science, 12: 1673437.
extraction capabilities[J]. Computers and Electronics in Agri- [30] Khanam R, Hussain M. YOLOv11: An overview of the key
culture, 2025, 231: 109969. architectural enhancements[J]. arXiv: 2410.17725, 2024.
[20] Wang A, Chen H, Liu L H, et al. YOLOv10: real-time end-to- [31] Wang C Y, Yeh I H, Mark Liao H Y. YOLOv9: learning what
end object detection[C]//NeurIPS Conference Committee. Pro- you want to learn using programmable gradient
ceedings of the 38th International Conference on Neural information[C]// ECCV. Proceedings of 18th European Confer-
Information Processing Systems. Vancouver: Curran Asso- ence on Computer Vision. Milan: Springer, 2024: 1-21.
ciates Inc. , 2024: 3429. [32] Ma X, Dai X Y, Bai Y, et al. Rewrite the stars[C]//IEEE. Pro-
[21] Zhuang X, Li D G, Wang Y, et al. Military target detection ceedings of the IEEE/CVF Conference on Computer Vision and
method based on EfficientDet and Generative Adversarial Net- Pattern Recognition. Seattle: IEEE, 2024: 5694-5703.
work[J]. Engineering Applications of Artificial Intelligence, [33] Pan X R, Ge C J, Lu R, et al. On the integration of self-atten-
2024, 132: 107896. tion and convolution[C]// IEEE. Proceedings of the IEEE/CVF
[22] Carion N, Massa F, Synnaeve G, et al. End-to-end object detec- Conference on Computer Vision and Pattern Recognition. New
tion with transformers[C]//European Computer Vision Associ- Orleans: IEEE, 2022: 805-815.

中国水产学会主办 sponsored by China Society of Fisheries https://www.china-fishery.cn
11