Underwater Optical Object Detection in the Era of Artificial Intelligence: Current, Challenge, and Future

Abstract

Underwater optical object detection (UOD), aiming to identify and localise objects in underwater optical images or videos, presents significant challenges due to the optical distortion, water turbidity, and changing illumination in underwater scenes. In recent years, artificial intelligence (AI) based methods, especially deep learning methods, have shown promising performance in UOD. To further facilitate future advancements, we comprehensively study AI-based UOD. In this survey, we first categorise existing algorithms into traditional machine learning-based methods and deep learning-based methods, and summarise them by considering learning strategies, experimental datasets, learning stages, employed features or techniques, and underlying frameworks. Next, we discuss the potential challenges and suggest possible solutions and new directions. We also perform both quantitative and qualitative evaluations of mainstream algorithms across multiple benchmark datasets, taking into account the diversity and biases in experimental setups. Finally, we introduce two off-the-shelf detection analysis tools, Diagnosis and TIDE, which will examine the effects of object characteristics and various types of errors on detector performance. These tools help identify the strengths and weaknesses of different detectors, providing insights for further improvement. The source code, trained models, utilized datasets, detection results, and detection analysis tools are publicly available at https://github.com/LongChenCV/UODReview and will be regularly updated.