Abstract
When a natural disaster occurs, the most critical task is to search and rescue trapped people as soon as possible. In recent years, unmanned aerial vehicles (UAVs) have been widely employed because of their high durability, low cost, ease of implementation, and flexibility. In this article, we collected a new thermal image dataset captured by drones. After that, we used several different deep convolutional neural networks to train survivor detection models on our dataset, including YOLOV3, YOLOV3-MobileNetV1, and YOLOV3- MobileNetV3. Due to the limited computing power and memory of the onboard microcomputer, to balance the inference time and accuracy, we found the optimal points to prune and fine-tune the survivor detection network based on the sensitivity of the convolutional layer. We verified it on NVIDIA’s Jetson TX2 and achieved a real-time performance of 26.60 frames/s (FPS). Moreover, we designed a real-time survivor detection system based on DJI Matrice 210 and Manifold 2-G to provide search and rescue services after the disaster.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal on Miniaturization for Air and Space Systems
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
