Lightweight Underwater Object Detection Based on YOLO v4 and Multi-Scale Attentional Feature Fusion

Minghua Zhang,Shubo Xu,Qi He,Wei Song,Quanmiao Wei

doi:10.3390/rs13224706

Abstract

A challenging and attractive task in computer vision is underwater object detection. Although object detection techniques have achieved good performance in general datasets, problems of low visibility and color bias in the complex underwater environment have led to generally poor image quality; besides this, problems with small targets and target aggregation have led to less extractable information, which makes it difficult to achieve satisfactory results. In past research of underwater object detection based on deep learning, most studies have mainly focused on improving detection accuracy by using large networks; the problem of marine underwater lightweight object detection has rarely gotten attention, which has resulted in a large model size and slow detection speed; as such the application of object detection technologies under marine environments needs better real-time and lightweight performance. In view of this, a lightweight underwater object detection method based on the MobileNet v2, You Only Look Once (YOLO) v4 algorithm and attentional feature fusion has been proposed to address this problem, to produce a harmonious balance between accuracy and speediness for target detection in marine environments. In our work, a combination of MobileNet v2 and depth-wise separable convolution is proposed to reduce the number of model parameters and the size of the model. The Modified Attentional Feature Fusion (AFFM) module aims to better fuse semantic and scale-inconsistent features and to improve accuracy. Experiments indicate that the proposed method obtained a mean average precision (mAP) of 81.67% and 92.65% on the PASCAL VOC dataset and the brackish dataset, respectively, and reached a processing speed of 44.22 frame per second (FPS) on the brackish dataset. Moreover, the number of model parameters and the model size were compressed to 16.76% and 19.53% of YOLO v4, respectively, which achieved a good tradeoff between time and accuracy for underwater object detection.

Highlights

The marine environment is a complicated system
The main framework of the reimplemented You Only Look Once (YOLO) v4 algorithm was used and the backbone network of YOLOv4 was replaced by MobileNet v2 at the same time
The results indicated that the proposed Model2 respectively reduced the amount of model parameters and the model size by 72.97% and 69.72% compared with Model1, while the mean average precision (mAP) and frame per second (FPS) were only decreased by 0.35% and 3.85, respectively

Summary

Introduction

As the underwater environment is very different from the land environment, some techniques of remote sensing including acoustic, magnetism [1], and 3D shallow seismic [2] sensing have achieved good performance in the marine realm. As a basic task of computer vision, object detection based on optical imaging has become an absorbing work in the marine realm. Many researchers have begun to study underwater object detection based on optical imaging and have achieved great results. Underwater object detection has many applications in the marine environment, including the study of marine ecosystems, marine biological population estimation, marine species conservation, pelagic fishery, underwater unexploded ordnance detection [3], underwater archaeology and many other potential applications, providing an effective way to exploit marine resources

Results

Discussion

Conclusion