Thermal RGB Fusion for Micro-UAV Wildfire Perimeter Tracking with Minimal Comms

Reading time: 4 minute
...

📝 Original Info

  • Title: Thermal RGB Fusion for Micro-UAV Wildfire Perimeter Tracking with Minimal Comms
  • ArXiv ID: 2512.12199
  • Date: 2025-12-13
  • Authors: Ercan Erkalkan, Vedat Topuz, Ayça Ak

📝 Abstract

This study introduces a lightweight perimeter tracking method designed for micro UAV teams operating over wildfire environments under limited bandwidth conditions. Thermal image frames generate coarse hot region masks through adaptive thresholding and morphological refinement, while RGB frames contribute edge cues and suppress texture related false detections using gradient based filtering. A rule level merging strategy selects boundary candidates and simplifies them via the Ramer Douglas Peucker algorithm. The system incorporates periodic beacons and an inertial feedback loop that maintains trajectory stability in the presence of GPS degradation. The guidance loop targets sub 50 ms latency on embedded System on Chip (SoC) platforms by constraining per frame pixel operations and precomputing gradient tables. Small scale simulations demonstrate reductions in average path length and boundary jitter compared to a pure edge tracking baseline, while maintaining environmental coverage measured through intersection merge analysis. Battery consumption and computational utilization confirm the feasibility of achieving 10, 15 m/s forward motion on standard micro platforms. This approach enables rapid deployment in the field, requiring robust sensing and minimal communications for emergency reconnaissance applications.

💡 Deep Analysis

Figure 1

📄 Full Content

17. Uluslararası Bilimsel Çalışmalar Kongresi 278 Mikro-İHA ile Yangın Sınırı Takibi için Termal–RGB Füzyonu ve Minimum İletişim Gereksinimi Thermal–RGB Fusion for Micro-UAV Wildfire Perimeter Tracking with Minimal Comms

Ercan ERKALKAN1, Vedat TOPUZ 2, Ayça AK 3 1 E-mail: ercan.erkalkan@marmara.edu.tr; Marmara Üniversitesi, Teknik Bilimler MYO, Elektronik ve Otomasyon Bölümü, İstanbul / Türkiye. 2E-mail: vtopuz@marmara.edu.tr; Marmara Üniversitesi, Teknik Bilimler MYO, Bilgisayar Teknolojileri Bölümü, İstanbul / Türkiye. 3 E-mail: aycaak@marmara.edu.tr; Marmara Üniversitesi, Teknik Bilimler MYO, Elektronik ve Otomasyon Bölümü, İstanbul / Türkiye.

Özet Bu çalışmada sınırlı bant genişliğine sahip, orman yangınları üzerinde görev yapan mikro İHA ekipleri için hafif bir çevre izleme yöntemi tanıtılmıştır. Termal görüntü çerçeveleri, uyarlamalı eşikleme ve morfolojik düzeltme adımları aracılığıyla kaba sıcak bölge maskeleri üretirken; RGB çerçeveler, gradyan tabanlı filtreleme yoluyla kenar ipuçları sağlar ve dokuya bağlı yanlış algılamaları bastırır. Kural düzeyinde birleştirme yöntemi, sınır adaylarını seçerek Ramer–Douglas–Peucker algoritmasıyla sadeleştirir. Bu yapı, periyodik işaretler ve GPS bozulması durumunda ilerlemeyi sürdüren ataletsel geri besleme döngüsünü içerir. Yönlendirme döngüsü, gömülü SoC’lerde (System- on-Chip) kare başına piksel işlemlerini sınırlayarak ve gradyan tablolarını önceden hesaplayarak 50ms’ nin altında gecikme hedeflemektedir. Küçük ölçekli simülasyonlar, saf kenar-izleme taban çizgisine kıyasla ortalama yol uzunluğu ve sınır titreşiminin azaldığını, ancak kesişim-birleştirme yöntemiyle ölçülen çevresel kapsamanın korunduğunu göstermektedir. Pil tüketimi ve hesaplamalı kullanım, standart mikro platformlarda 10-15 m/s ileri hareketin elde edilebileceğini doğrulamaktadır. Bu yaklaşım, acil keşif uygulamaları için dayanıklı algılama ve asgari iletişim gerektiren durumlarda hızlı konuşlandırmayı mümkün kılmaktadır.
Anahtar Kelimeler: Çevre takibi, görüntü birleştirme, lider-takipçi, Mikro-İHA, orman yangını izleme. Abstract This study introduces a lightweight perimeter-tracking method designed for micro-UAV teams operating over wildfire environments under limited bandwidth conditions. Thermal image frames generate coarse hot-region masks through adaptive thresholding and morphological refinement, while RGB frames contribute edge cues and suppress texture-related false detections using gradient-based filtering. A rule-level merging strategy selects boundary candidates and simplifies them via the Ramer–Douglas–Peucker algorithm. The system incorporates periodic beacons and an inertial feedback loop that maintains trajectory stability in the presence of GPS degradation. The guidance

  1. Uluslararası Bilimsel Çalışmalar Kongresi 279 loop targets sub-50 ms latency on embedded System-on-Chip (SoC) platforms by constraining per- frame pixel operations and precomputing gradient tables. Small-scale simulations demonstrate reductions in average path length and boundary jitter compared to a pure edge-tracking baseline, while maintaining environmental coverage measured through intersection–merge analysis. Battery consumption and computational utilization confirm the feasibility of achieving 10–15 m/s forward motion on standard micro platforms. This approach enables rapid deployment in the field, requiring robust sensing and minimal communications for emergency reconnaissance applications. Keywords: Image fusion, leader–follower, Micro-UAV, perimeter tracking, wildfire monitoring,

INTRODUCTION
Rapid wildfire reconnaissance demands fast deployment, high interpretability, and robustness under degraded communication conditions. In such missions, micro-UAV teams must operate within strict payload, energy, and onboard-compute constraints while exchanging sparse and lossy messages over short-range links. The primary operational objective is to achieve reliable perimeter tracking and sampling under limited bandwidth and computational budgets. Thermal imagery provides strong hotspot localization but often exhibits boundary noise, whereas RGB imagery contributes structural and textural cues that degrade under smoke, glare, and illumination variability. To address these challenges, a low- configuration perception pipeline is prioritized—one that emphasizes graceful degradation, field- oriented diagnosability, and real-time execution on commodity embedded SoCs. Previous studies have established the feasibility of UAV-based wildfire observation and coordination. Cooperative forest-fire surveillance using teams of small UAVs has been demonstrated (Casbeer et al., 2006), and automatic wildfire monitoring and measurement with unmanned aircraft systems have been reported (Merino et al., 2012). Ground-station and UAV integration approaches have further validated forest-fire quantification under operational conditio

📸 Image Gallery

cover.png

Reference

This content is AI-processed based on open access ArXiv data.

Start searching

Enter keywords to search articles

↑↓
ESC
⌘K Shortcut