Towards a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection
This work addresses the challenge of real-time visual tracking for underwater robots in diverse environments, representing an incremental improvement in domain-specific applications.
The paper tackles the problem of developing a robust diver-following algorithm for autonomous underwater robots by designing a CNN-based detection model that balances robustness and efficiency, achieving comparable performance to state-of-the-art deep models while being much faster, as validated through field experiments.
This paper explores the design and development of a class of robust diver-following algorithms for autonomous underwater robots. By considering the operational challenges for underwater visual tracking in diverse real-world settings, we formulate a set of desired features of a generic diver following algorithm. We attempt to accommodate these features and maximize general tracking performance by exploiting the state-of-the-art deep object detection models. We fine-tune the building blocks of these models with a goal of balancing the trade-off between robustness and efficiency in an onboard setting under real-time constraints. Subsequently, we design an architecturally simple Convolutional Neural Network (CNN)-based diver-detection model that is much faster than the state-of-the-art deep models yet provides comparable detection performances. In addition, we validate the performance and effectiveness of the proposed diver-following modules through a number of field experiments in closed-water and open-water environments.