# Towards a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection

arXiv: https://arxiv.org/abs/1809.06849 · HTML: https://mlsanity.com/paper/1809.06849/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Sep 2018.

## Built on by (most cited first, 5 of 5)

- [Domain Adaptation for Underwater Image Enhancement](https://mlsanity.com/paper/2108.09650/) (2021)
- [Underwater Object Classification and Detection: first results and open challenges](https://mlsanity.com/paper/2201.00977/) (2022)
- [Single Underwater Image Enhancement Using an Analysis-Synthesis Network](https://mlsanity.com/paper/2108.09023/) (2021)
- [A comparison of RL-based and PID controllers for 6-DOF swimming robots: hybrid underwater object tracking](https://mlsanity.com/paper/2401.16618/) (2024)
- [Stable Multi-Drone GNSS Tracking System for Marine Robots](https://mlsanity.com/paper/2511.18694/) (2025)

## Abstract (arXiv)

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.