Enhancing Underwater Object Detection through Spatio-Temporal Analysis and Spatial Attention Networks

TL;DR

The paper tackles the challenge of underwater object detection by integrating spatio-temporal modeling with spatial attention within the YOLOv5 framework. It introduces T-YOLOv5 (ConvLSTM-based temporal modeling) and a CBAM-enhanced variant, evaluated on the UOT32 underwater dataset with 3-frame sequences and temporal augmentations. Results show substantial improvements over baseline YOLOv5, with T-YOLOv5 achieving the highest overall performance and T-YOLOv5+CBAM delivering gains in complex scenes at the expense of some temporal simplicity, suggesting a trade-off between accuracy and efficiency. The work demonstrates the value of combining temporal context and attention for robust underwater detection, with potential impact on real-time underwater robotics and marine monitoring.

Abstract

This study examines the effectiveness of spatio-temporal modeling and the integration of spatial attention mechanisms in deep learning models for underwater object detection. Specifically, in the first phase, the performance of temporal-enhanced YOLOv5 variant T-YOLOv5 is evaluated, in comparison with the standard YOLOv5. For the second phase, an augmented version of T-YOLOv5 is developed, through the addition of a Convolutional Block Attention Module (CBAM). By examining the effectiveness of the already pre-existing YOLOv5 and T-YOLOv5 models and of the newly developed T-YOLOv5 with CBAM. With CBAM, the research highlights how temporal modeling improves detection accuracy in dynamic marine environments, particularly under conditions of sudden movements, partial occlusions, and gradual motion. The testing results showed that YOLOv5 achieved a mAP@50-95 of 0.563, while T-YOLOv5 and T-YOLOv5 with CBAM outperformed with mAP@50-95 scores of 0.813 and 0.811, respectively, highlighting their superior accuracy and generalization in detecting complex objects. The findings demonstrate that T-YOLOv5 significantly enhances detection reliability compared to the standard model, while T-YOLOv5 with CBAM further improves performance in challenging scenarios, although there is a loss of accuracy when it comes to simpler scenarios.

Figures (10)

• Figure 1: One sample image per class from the UOT32 Dataset
• Figure 2: Sample Images Utilized In Training Batches, After Augmentations.
• Figure 3: YOLOv5 Architecture Diagram
• Figure 4: T-YOLOv5 Architecture Diagram
• Figure 5: ConvLSTM Architecture Diagram