Abstract
Forward-looking sonar is a commonly used underwater detection device at present, but the detection accuracy is poor due to the complex underwater environment, small target highlight area and fuzzy feature details. Therefore, this paper proposes a forward sonar image target detection model based on You Only Look Once Version 5 (YOLOv5) network using transfer learning method. First, the YOLOv5 network is pretrained with COCO data set. Then the pre-training model is fine-tuned according to the training set of forward-looking sonar images. Before fine-tuning, the traditional k-means clustering is improved. The intersection over union ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$IoU$ </tex-math></inline-formula> ) value is used as the distance function to cluster the labeling information of the training set of the forward-looking sonar image. The results of clustering serve as the initial anchor frame of the training network. This operation greatly improves the detection speed. Second, due to the characteristics of weak echo intensity and small target area of forward-looking sonar image, an improved feature extraction method of CoordConv was proposed to give corresponding coordinate information to high-level features which improves the accuracy of network detection regression. Finally, the fine-tuned network is used to detect the target in the forward-looking sonar image. The experimental results show that the improved model based on YOLOv5 network is superior to the original YOLOv5 network and other popular deep neural networks for target detection in the forward-looking sonar image, which has a reference significance for underwater target detection. The CoordConv-YOLOv5 network based on transfer learning proposed in this paper shows the best performance in both detection accuracy and detection speed. Detection accuracy mAP@0.5:0.95 can reach 56.95%, and detection speed can reach 9ms.
Highlights
Sonar image target detection is a hot topic in the field of target detection
PROPOSED METHOD In this part, an improved YOLOv5 detection model based on transfer learning is proposed for the image target detection task of forward-looking sonar, which includes transfer learning training structure, IoU k-means clustering improved algorithm, CoordConv-YOlOv5 network and forwardlooking sonar target detection model
In this paper, a forward sonar image target detection model based on transfer learning CoordConv-YOlOv5 is proposed for the task of forward sonar image target detection
Summary
Sonar image target detection is a hot topic in the field of target detection. In civil and military fields, it is of great significance to submarine landform mapping, underwater search and rescue, salvage, oil exploration and submarine suspicious target detection. The positioning accuracy of sonar image target detection task is a great consideration, this paper proposes to use IoU as the clustering function of k-means algorithm. By evaluating the average IoU accuracy of the two algorithms, the introduction of IoU as a distance function does better than the traditional k-means used in YOLOv5 on the target clustering of the forward-looking sonar data set, and the average IoU accuracy is improved by 5.5%. In view of the above problems, this section proposes to use CoordConv to improve the feature extraction module of YOLOv5 network It extracted the multi-scale high level features, and introduced the corresponding coordinate information for different scale features.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
