# Adaptive Entropy-Driven Sensor Selection in a Camera-LiDAR Particle Filter for Single-Vessel Tracking

arXiv: https://arxiv.org/abs/2603.08457 · HTML: https://mlsanity.com/paper/2603.08457/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 23 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 2 of 2)

- [Marine vessel tracking using a monocular camera](https://mlsanity.com/paper/2108.10367/) (2021)
- [Near-Shore Mapping for Detection and Tracking of Vessels](https://mlsanity.com/paper/2502.18368/) (2025)

## Built on by (most cited first, 1 of 1)

- [Reinforcement Learning for Heterogeneous Sensor Selection in Maritime Surveillance](https://mlsanity.com/paper/2607.22667/) (2026)

## Abstract (arXiv)

Robust single-vessel tracking from fixed coastal platforms is hindered by modality-specific degradations: cameras suffer from illumination and visual clutter, while LiDAR performance drops with range and intermittent returns. We present a particle-filter tracker that supports sequential measurement-level camera-LiDAR fusion and an information-gain (entropy-reduction) adaptive sensing policy that selects the most informative sensing modality at each fusion time bin. The approach is validated in a real maritime deployment at the Cyprus Marine and Maritime Institute Smart Marina Testbed (Ayia Napa Marina, Cyprus), using a shore-mounted 3D LiDAR and an elevated fixed camera to track a rigid inflatable boat with onboard GNSS ground truth. We compare LiDAR-only, camera-only, All sensors, and adaptive configurations. Results show LiDAR dominates near-field accuracy, the camera sustains longer-range coverage when LiDAR becomes unavailable, and the adaptive policy achieves a favorable accuracy-continuity trade-off by switching modalities based on information gain. The adaptive configuration therefore provides a practical sensor-selection baseline for resilient and resource-aware maritime surveillance.