DRespNeT: A UAV Dataset and YOLOv8-DRN Model for Aerial Instance Segmentation of Building Access Points for Post-Earthquake Search-and-Rescue Missions
This work addresses the need for rapid situational awareness in post-earthquake environments for SAR teams and robotic systems, though it is incremental as it builds on existing YOLO-based methods with a new dataset.
The paper tackles the problem of identifying accessible entry points and obstacles in earthquake-affected areas for search-and-rescue missions by introducing DRespNeT, a high-resolution aerial dataset with detailed instance segmentation annotations, and an optimized YOLOv8-DRN model that achieves 92.7% mAP50 at 27 FPS.
Recent advancements in computer vision and deep learning have enhanced disaster-response capabilities, particularly in the rapid assessment of earthquake-affected urban environments. Timely identification of accessible entry points and structural obstacles is essential for effective search-and-rescue (SAR) operations. To address this need, we introduce DRespNeT, a high-resolution dataset specifically developed for aerial instance segmentation of post-earthquake structural environments. Unlike existing datasets, which rely heavily on satellite imagery or coarse semantic labeling, DRespNeT provides detailed polygon-level instance segmentation annotations derived from high-definition (1080p) aerial footage captured in disaster zones, including the 2023 Turkiye earthquake and other impacted regions. The dataset comprises 28 operationally critical classes, including structurally compromised buildings, access points such as doors, windows, and gaps, multiple debris levels, rescue personnel, vehicles, and civilian visibility. A distinctive feature of DRespNeT is its fine-grained annotation detail, enabling differentiation between accessible and obstructed areas, thereby improving operational planning and response efficiency. Performance evaluations using YOLO-based instance segmentation models, specifically YOLOv8-seg, demonstrate significant gains in real-time situational awareness and decision-making. Our optimized YOLOv8-DRN model achieves 92.7% mAP50 with an inference speed of 27 FPS on an RTX-4090 GPU for multi-target detection, meeting real-time operational requirements. The dataset and models support SAR teams and robotic systems, providing a foundation for enhancing human-robot collaboration, streamlining emergency response, and improving survivor outcomes.