Object Detection in Thermal Images Using Deep Learning for Unmanned Aerial Vehicles
This work addresses the problem of detecting small objects in thermal imagery for UAV applications, representing an incremental improvement over existing methods.
The paper tackles object detection in thermal images from UAVs by proposing a neural network model that combines YOLOv5 with transformers and sliding windows, achieving higher accuracy than state-of-the-art methods and real-time performance with over 90% stability on embedded systems.
This work presents a neural network model capable of recognizing small and tiny objects in thermal images collected by unmanned aerial vehicles. Our model consists of three parts, the backbone, the neck, and the prediction head. The backbone is developed based on the structure of YOLOv5 combined with the use of a transformer encoder at the end. The neck includes a BI-FPN block combined with the use of a sliding window and a transformer to increase the information fed into the prediction head. The prediction head carries out the detection by evaluating feature maps with the Sigmoid function. The use of transformers with attention and sliding windows increases recognition accuracy while keeping the model at a reasonable number of parameters and computation requirements for embedded systems. Experiments conducted on public dataset VEDAI and our collected datasets show that our model has a higher accuracy than state-of-the-art methods such as ResNet, Faster RCNN, ComNet, ViT, YOLOv5, SMPNet, and DPNetV3. Experiments on the embedded computer Jetson AGX show that our model achieves a real-time computation speed with a stability rate of over 90%.