Adaptive Entropy-Driven Sensor Selection in a Camera-LiDAR Particle Filter for Single-Vessel Tracking
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910046451924992 |
|---|---|
| author | Starodubov, Andrei Prabowo, Yaqub Aris Hadjipieris, Andreas Kyriakides, Ioannis Galeazzi, Roberto |
| author_facet | Starodubov, Andrei Prabowo, Yaqub Aris Hadjipieris, Andreas Kyriakides, Ioannis Galeazzi, Roberto |
| contents | 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 heterogeneous multi-sensor fusion particle-filter tracker that incorporates an information-gain (entropy-reduction) adaptive sensing policy to select the most informative configuration at each fusion time bin. The approach is validated in a real maritime deployment at the CMMI 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. By avoiding continuous multi-stream processing, the adaptive configuration provides a practical baseline for resilient and resource-aware maritime surveillance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08457 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Adaptive Entropy-Driven Sensor Selection in a Camera-LiDAR Particle Filter for Single-Vessel Tracking Starodubov, Andrei Prabowo, Yaqub Aris Hadjipieris, Andreas Kyriakides, Ioannis Galeazzi, Roberto Robotics Machine Learning Systems and Control Signal Processing Data Analysis, Statistics and Probability 93E11 (Primary) 93E10, 62M20, 60G35, 68T45 (Secondary) G.3; H.1.1; I.4.8; I.6.8; J.2; J.7 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 heterogeneous multi-sensor fusion particle-filter tracker that incorporates an information-gain (entropy-reduction) adaptive sensing policy to select the most informative configuration at each fusion time bin. The approach is validated in a real maritime deployment at the CMMI 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. By avoiding continuous multi-stream processing, the adaptive configuration provides a practical baseline for resilient and resource-aware maritime surveillance. |
| title | Adaptive Entropy-Driven Sensor Selection in a Camera-LiDAR Particle Filter for Single-Vessel Tracking |
| topic | Robotics Machine Learning Systems and Control Signal Processing Data Analysis, Statistics and Probability 93E11 (Primary) 93E10, 62M20, 60G35, 68T45 (Secondary) G.3; H.1.1; I.4.8; I.6.8; J.2; J.7 |
| url | https://arxiv.org/abs/2603.08457 |