Wildfires pose increasing environmental and economic threats, making early and accurate detection essential to minimize their impact. This paper presents an AI driven UAV surveillance system designed to balance wildfire detection accuracy with energy efficiency. The system operates in two stages: UAVs conduct continuous low resolution monitoring and switch to high resolution imaging only when potential fire signals are detected. A custom Convolutional Neural Network (CNN) was trained on a curated dataset of fire and non fire images with diverse environmental conditions. Performance was evaluated using accuracy, precision, recall, and F1 score, demonstrating that the dual resolution approach improves fire precision to 0.96 while reducing false positives, achieving an overall accuracy of 83 percent. An energy analysis shows that the selective two stage model achieves 64.4 percent lower energy consumption compared to continuous high resolution imaging, extending UAV endurance. This work introduces a scalable and cost effective approach to UAV based wildfire surveillance, highlighting tradeoffs between accuracy, latency, and energy, and setting the stage for real world deployments in wildfire prone regions.

Drones are integral to various applications, out of which traffic surveillance is an important application. However, their operational efficiency is limited by battery life, which restricts their capacity for extended critical missions. Additionally, in remote or high-interference areas, the bandwidth for drone communication is often limited, leading to a decrease in the quality of images transmitted to the base station. This paper aims to address such challenges by having drones transmit video data in real-time at lower resolutions for traffic monitoring. This approach conserves energy and optimizes transmission. However, it adversely affects object detection accuracy at the base station due to compromised data quality. To address this issue, we incorporate Generative Adversarial Networks (GANs) to improve LR images, restoring their quality for precise object detection. Results indicate that the accuracy of traffic analytics achieved with GAN-enhanced images is comparable to that obtained with high-resolution data transmission. Consequently, our approach allows a fundamental trade-off among drone energy consumption, transmission time, flight time, and object detection accuracy, enabling robust detection performance while conserving energy and enhancing operational capabilities.