4.5 Article

An Improved YOLO Algorithm for Fast and Accurate Underwater Object Detection

期刊

SYMMETRY-BASEL
卷 14, 期 8, 页码 -

出版社

MDPI
DOI: 10.3390/sym14081669

关键词

underwater object detection; symmetric FPN-Attention module; symmetric dilated convolutional module; label smoothing; YOLOv4-tiny; YOLO-UOD

资金

  1. Xiamen Ocean and Fishery Development Special Fund Project [21CZB013HJ15]
  2. Xiamen Key Laboratory of Marine Intelligent Terminal R&D and Application [B18208]
  3. Fund Project of Jimei University [ZP2020042]

向作者/读者索取更多资源

This study proposes an underwater object detection algorithm based on YOLOv4-tiny, which achieves better performance with less computational cost. The algorithm improves the detection accuracy by introducing a symmetric bottleneck-type structure and a symmetric FPN-Attention module. The proposed YOLO-UOD outperforms the baseline model on the Brackish underwater dataset and shows effective detection in scenarios with limited computing power.
Due to the abundant natural resources of the underwater world, autonomous exploration using underwater robots has become an effective technological tool in recent years. Real-time object detection is critical when employing robots for independent underwater exploration. However, when a robot detects underwater, its computing power is usually limited, which makes it challenging to detect objects effectively. To solve this problem, this study presents a novel algorithm for underwater object detection based on YOLOv4-tiny to achieve better performance with less computational cost. First, a symmetrical bottleneck-type structure is introduced into the YOLOv4-tiny's backbone network based on dilated convolution and 1 x 1 convolution. It captures contextual information in feature maps with reasonable computational cost and improves the mAP score by 8.74% compared to YOLOv4-tiny. Second, inspired by the convolutional block attention module, a symmetric FPN-Attention module is constructed by integrating the channel-attention module and the spatial-attention module. Features extracted by the backbone network can be fused more efficiently by the symmetric FPN-Attention module, achieving a performance improvement of 8.75% as measured by mAP score compared to YOLOv4-tiny. Finally, this work proposed the YOLO-UOD for underwater object detection through the fusion of the YOLOv4-tiny structure, symmetric FPN-Attention module, symmetric bottleneck-type dilated convolutional layers, and label smoothing training strategy. It can efficiently detect underwater objects in an embedded system environment with limited computing power. Experiments show that the proposed YOLO-UOD outperforms the baseline model on the Brackish underwater dataset, with a detection mAP of 87.88%, 10.5% higher than that of YOLOv4-tiny's 77.38%, and the detection result exceeds YOLOv5s's 83.05% and YOLOv5m's 84.34%. YOLO-UOD is deployed on the embedded system Jetson Nano 2 GB with a detection speed of 9.24 FPS, which shows that it can detect effectively in scenarios with limited computing power.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据