A Systematic Review of UAV Structure and Monitoring Models for Forest Fire Detection

Abstract

Forest fires pose a significant threat to ecosystems and economic development. In recent years, unmanned aerial vehicles (UAVs) have emerged as a critical technology for forest fire monitoring due to their high mobility, low cost, and real-time surveillance capabilities. This paper provides a systematic review of research progress on UAV-based forest fire monitoring, focusing on three key aspects: hardware design, fire detection algorithm improvement, and multi-sensor data fusion technologies. First, it summarizes optimization strategies for UAV hardware, including sensor configurations, wing design, and power supply improvements, aimed at enhancing flight stability and environmental adaptability. Second, it analyzes advancements in fire detection algorithms, particularly the performance enhancement and lightweight modifications of deep learning models, and explores their applicability in high-noise environments. Finally, it evaluates the potential of multi-sensor data fusion techniques to improve fire detection accuracy by integrating temperature, smoke, and image data. Despite the significant advantages of UAVs in fire monitoring, challenges remain, such as hardware performance limitations, the trade-off between algorithm accuracy and real-time processing, and the complexity of multi-sensor coordination. Future research should focus on flight stability optimization, the development of novel detection algorithms, and the refinement of sensor integration techniques to further advance UAV applications in forest fire monitoring.