In recent years, nature-induced urban disasters in high-density modern cities in China have raised great concerns. The delayed and imprecise understanding of the real-time post-disaster situation made it difficult for the decision-makers to find a suitable emergency rescue plan. To this end, this study aims to facilitate the real-time performance and accuracy of on-site victim risk identification. In this article, we propose a victim identification model based on the You Only Look Once v7-W6 (YOLOv7-W6) algorithm. This model defines the “fall-down” pose as a key feature in identifying urgent victims from the perspective of disaster medicine rescue. The results demonstrate that this model performs superior accuracy (mAP@0.5, 0.960) and inference speed (5.1 ms) on the established disaster victim database compared to other state-of-the-art object detection algorithms. Finally, a case study is illustrated to show the practical utilization of this model in a real disaster rescue scenario. This study proposes an intelligent on-site victim risk identification approach, contributing significantly to government emergency decision-making and response.