High Speed and Precision Underwater Biological Detection Based on the Improved YOLOV4-Tiny Algorithm

Abstract

Realizing high-precision real-time underwater detection has been a pressing issue for intelligent underwater robots in recent years. Poor quality of underwater datasets leads to low accuracy of detection models. To handle this problem, an improved YOLOV4-Tiny algorithm is proposed. The CSPrestblock_body in YOLOV4-Tiny is replaced with Ghostblock_body, which is stacked by Ghost modules in the CSPDarknet53-Tiny backbone network to reduce the computation complexity. The convolutional block attention module (CBAM) is integrated to the algorithm in order to find the attention region in scenarios with dense objects. Then, underwater data is effectively improved by combining the Instance-Balanced Augmentation, underwater image restoration, and Mosaic algorithm. Finally, experiments demonstrate that the YOLOV4-Tinier has a mean Average Precision (mAP) of 80.77% on the improved underwater dataset and a detection speed of 86.96 fps. Additionally, compared to the baseline model YOLOV4-Tiny, YOLOV4-Tinier reduces about model size by about 29%, which is encouraging and competitive.

An Effective Method for Underwater Biological Multi-Target Detection Using Mask Region-Based Convolutional Neural Network

“…In conclusion, deep learning has strong generalization capabilities [26,27] and is effective in fish target recognition, benefitting from clear and rich underwater datasets [28][29][30][31]. For instance, Shi et al [28] introduced an improved Faster-RCNN algorithm for underwater biological detection, and the proposed model performed better than the YOLOv4 and Faster-RCNN models.…”

“…To estimate the performance of the convolutional neural network model, the evaluation criteria included the precision, recall, average precision (AP), and mean AP (mAP) [31].…”

G-Net: An Efficient Convolutional Network for Underwater Object Detection

“…Yeh [38] et al used a color conversion module and detection module jointly trained to enhance underwater target detection through the joint training of color conversion and detection modules. The underwater target single aggregation network was proposed in [39] by using multiscale features and complementary context information [40] proposed a fast underwater target detection network [41] fine-tuned YOLOv2 and tested it on the underwater dataset.…”

Gaussian Weighted Eye State Determination for Driving Fatigue Detection

“…YOLOv4tiny is one of them based on the YOLOv4 model [41], which simplified the network structure, cut down the parameters, and enhanced the target detection speed at the expense of accuracy. The YOLOv4-tiny model uses the CSPDarknet53-tiny network [42] to extract features, then a feature fusion structure is added to withdraw the multi-scale feature maps. All these strategies promote the detection accuracy of the model, making the YOLOv4tiny model have both good detection accuracy and faster detection speed, improving the feasibility of the model in the application of embedded systems or mobile devices.…”