Real-time GAN-based image enhancement for robust underwater monocular SLAM

Abstract

Underwater monocular visual simultaneous localization and mapping (SLAM) plays a vital role in underwater computer vision and robotic perception fields. Unlike the autonomous driving or aerial environment, performing robust and accurate underwater monocular SLAM is tough and challenging due to the complex aquatic environment and the collected critically degraded image quality. The underwater images’ poor visibility, low contrast, and color distortion result in ineffective and insufficient feature matching, leading to the poor or even failure of the existing SLAM algorithms. To address this issue, we propose introducing the generative adversarial network (GAN) to perform effective underwater image enhancement before conducting SLAM. Considering the inherent real-time requirement of SLAM, we conduct knowledge distillation to achieve GAN compression to reduce the inference cost, while achieving high-fidelity underwater image enhancement and real-time inference. The real-time underwater image enhancement acts as the image pre-processing to build a robust and accurate underwater monocular SLAM system. With the introduction of real-time underwater image enhancement, we can significantly promote underwater SLAM performance. The proposed method is a generic framework, which could be extended to various SLAM systems and achieve various scales of performance gain.

Advancements in Underwater Navigation: Integrating Deep Learning and Sensor Technologies for Unmanned Underwater Vehicles

“…Furthermore, specific algorithms, such as ORB-SLAM3, demonstrate adaptability for use with both pinhole and fisheye cameras, broadening their applicability in visual SLAM scenario Monocular or single-lens camera: Singular lenses and monocular cameras provide economical and straightforward imaging solutions. Mono SLAM pioneered in establishing real-time monocular vision SLAM [21,22]. In underwater research, Hidalgo et al investigated ORB-SLAM through controlled experiments featuring diverse conditions.…”

RU-SLAM: A Robust Deep-Learning Visual Simultaneous Localization and Mapping (SLAM) System for Weakly Textured Underwater Environments

“…These factors pose challenges for SLAM methods based on hand-crafted features such as SIFT [ 5 ], ORB [ 6 ], and Shi-Tomasi [ 7 ] in terms of ensuring consistent feature extraction and tracking. To address these issues, methods of image enhancement on image frames before feature extraction were proposed by scholars [ 8 , 9 ]. For example, an adversarial contrast learning method in [ 8 ] was designed for addressing underwater image degradation in visual SLAM.…”

“…To address these issues, methods of image enhancement on image frames before feature extraction were proposed by scholars [ 8 , 9 ]. For example, an adversarial contrast learning method in [ 8 ] was designed for addressing underwater image degradation in visual SLAM. Considering the issue of water turbidity, ref.…”

CCGAN as a Tool for Satellite-Derived Chlorophyll a Concentration Gap Reconstruction

“…GANs have been successfully utilised within the domain of satellite oceanography for reconstruction purposes [13][14][15][16], but their application has been limited to sea surface temperature (SST) only [11]. Outside of strictly reconstruction-oriented purposes, GANs have seen a vast range of utilisation in oceanography [17][18][19][20].…”