Abstract
Due to a growing number of people who carry out various adrenaline activities or adventure tourism and stay in the mountains and other inaccessible places, there is an increasing need to organize a search and rescue operation (SAR) to provide assistance and health care to the injured. The goal of SAR operation is to search the largest area of the territory in the shortest time possible and find a lost or injured person. Today, drones (UAVs or drones) are increasingly involved in search operations, as they can capture a large, controlled area in a short amount of time. However, a detailed examination of a large amount of recorded material remains a problem. Even for an expert, it is not easy to find searched people who are relatively small considering the area where they are, often sheltered by vegetation or merged with the ground and in unusual positions due to falls, injuries, or exhaustion. Therefore, the automatic detection of persons and objects in images/videos taken by drones in these operations is very significant. In this paper, the reliability of existing state-of-the-art detectors such as Faster R-CNN, YOLOv4, RetinaNet, and Cascade R-CNN on a VisDrone benchmark and custom-made dataset SARD build to simulate rescue scenes was investigated. After training the models on selected datasets, detection results were compared. Because of the high speed and accuracy and the small number of false detections, the YOLOv4 detector was chosen for further examination. YOLOv4 model results related to different network sizes, different detection accuracies, and transfer learning settings were analyzed. The model robustness to weather conditions and motion blur were also investigated. The paper proposes a model that can be used in SAR operations because of the excellent results in detecting people in search and rescue scenarios.
Highlights
Many people are included in sport tourism to actively spend leisure time such as skiing, hiking, or nautical, which motivate them to stay in nature
The ability to detect people on drone images using computer vision methods automatically is a significant help in search and rescue operation (SAR) operations
We explored the state-of-the-art person detectors in drone images and proposed a model for detecting persons in SAR actions
Summary
Many people are included in sport tourism to actively spend leisure time such as skiing, hiking, or nautical, which motivate them to stay in nature. B) comparison of the performance of selected CNN detectors (Cascade R-CNN, Faster R-CNN, RetinaNet, YOLOv4) for use in SAR operations, c) analyses of the influence of different network resolutions, detection accuracies, and confidence values on YOLOv4 person detection performance, and analysis of different transfer learning strategies considering the impact on detection results, e) proposal of ROpti metrics for evaluating detector performances for SAR operations taking into account that there are as many positive detections as possible and as few false detections as possible, f) proposal of YOLOv4 model to be used for person detection in SAR actions taking care to achieve the highest possible accuracy, with a few false detections as possible, with a network configuration that allows a person's online location and a configuration for off-line analysis, robust to various weather conditions. The paper ends with the conclusion and direction for future research
Sign-in/Register to view highlights & summary 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 callDisclaimer: 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.
