【摘要】 为实现在复杂水体下对鱼道过鱼进行监测，提出了一种基于YOLOv5s的改进模型，并用TensorRT部署应用于某水电站鱼道现场。首先，针对水下图像模糊、目标检测困难的问题，提出了将Swin Transformer(STR)作为检测层，提升了模型对目标的检测能力；其次，针对鱼群密集、图像信息少的问题，将Efficient channel attention(ECA)注意力机制作为主干特征提取网络C3结构的Bottleneck,减少了计算参数并提升了检测精度；然后，针对检测目标定位差、回归不收敛的问题，将Focal and efficient IOU loss(FIOU)作为模型损失函数，优化了模型整体性能；最后将模型部署在TensorRT框架进行优化，处理速度得到了大幅度提升。基于实际采集的复杂水体数据集进行实验，结果表明，本文算法mAP为91.9%,单幅图像处理时间为10.4 ms,在相同条件下，精度比YOLOv5s提升4.8个百分点，处理时间减少0.4 ms。模型使用TensorRT部署后单幅图像推理时间达到2.3 ms,在不影响检测精度的前提下，推理速度提高4.5倍。综上，本文算法模型在保证快速检测的基础上，具有较高的准确性，更适用于复杂水体下鱼道过鱼监测。更多还原

【Abstract】 In order to realize the detection of fish passage in fishway under complex water, an improved model based on YOLOv5 s was proposed, and it was deployed and applied to the fishway site of one hydropower station with TensorRT. Firstly, in view of the problems of underwater image blur and target detection difficulty, the Swin Transformer(STR) was proposed as the detection layer, which improved the detection ability of the model for targets. Secondly, in view of the problem of dense fish and little image information, the efficient channel attention(ECA) attention mechanism was used as the Bottleneck of the backbone feature extraction network C3 structure, which reduced the calculation parameters and improved the detection accuracy. Then aiming at the problem of detection target positioning error and non convergence of regression, taking focal and efficient IOU loss(FIOU) as the loss function of the model to optimize the overall performance of the model. Finally, the model was deployed in TensorRT framework for optimization, and the processing speed was greatly improved. Based on the actual collection of complex water body data set, the experiment results showed that the algorithm mAP was 91.9%, and the processing time of a single image was 10.4 ms. Under the same conditions, the precision was 4.8 percentage points higher than that of YOLOv5 s, and the processing time was 0.4 ms. After the model was deployed with TensorRT, the reasoning speed reached 2.3 ms/img, a 4.5 times improvement in reasoning speed without affecting detection accuracy. In conclusion, the algorithm model had good effectiveness and superiority, and it was more suitable for fish passage detection in complex water bodies.更多还原