Shihong Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shihong Yao has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Chao Yang
National Engineering Research Center of Geographic Information System, China University of Geosciences, Wuhan 430074, China
1 shared publication Daole Ding
1 shared publication- Hao Huang
Wuhan University
1 shared publication - Kai Yin
School of Computer Science, Wuhan University, Wuhan, China
1 shared publication Shaojun Liu
1 shared publicationShengnan Kong
1 shared publication
Latest Publications
- Open Access
- 24 August 2026
- Published by Elsevier in SSRN Electronic Journal
Understanding Pedestrian Walking Patterns in Heat-Exposed Environments: A Computer Vision-Based Approach
Understanding pedestrian behavior in heat-exposed environments is essential for designing climate-adaptive urban spaces. Compared to traditional methods for investigating pedestrian walking behavior, we propose a computer vision–based framework for human behavior analysis that integrates pedestrian video, 3D imagery, climatic data, and microclimate simulation tools. Pedestrian trajectories are extracted using YOLOv8-SPD and DeepSORT and georeferenced into real-world coordinates via MASt3R-based scene matching. The resulting trajectories are then coupled with simulated shade and Physiological Equivalent Temperature (PET*) to enable fine-scale analysis of pedestrian behavior under thermal exposure. We examine pedestrian walking behavior under hot, sun-exposed conditions through two complementary experiments focused on walking-area selection and route-level path choice. The results reveal that pedestrians exhibit a strong preference for shaded walking areas within the same road segment; however, this preference becomes less pronounced at the route level, where walking distance remains the dominant factor. Overall, the proposed workflow offers a robust, computer vision–based approach for analyzing pedestrian behavior under outdoor heat exposure at high spatial resolution.
- 24 August 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessUnderstanding Pedestrian Walking Patterns in Heat-Exposed Environments: A Computer Vision-Based Approach
Understanding pedestrian behavior in heat-exposed environments is essential for designing climate-adaptive urban spaces. Compared to traditional methods for investigating pedestrian walking behavior, we propose a computer vision–based framework for human behavior analysis that integrates pedestrian video, 3D imagery, climatic data, and microclimate simulation tools. Pedestrian trajectories are extracted using YOLOv8-SPD and DeepSORT and georeferenced into real-world coordinates via MASt3R-based scene matching. The resulting trajectories are then coupled with simulated shade and Physiological Equivalent Temperature (PET*) to enable fine-scale analysis of pedestrian behavior under thermal exposure. We examine pedestrian walking behavior under hot, sun-exposed conditions through two complementary experiments focused on walking-area selection and route-level path choice. The results reveal that pedestrians exhibit a strong preference for shaded walking areas within the same road segment; however, this preference becomes less pronounced at the route level, where walking distance remains the dominant factor. Overall, the proposed workflow offers a robust, computer vision–based approach for analyzing pedestrian behavior under outdoor heat exposure at high spatial resolution.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3102-3110
DeepUL: Deep Unlearning via Model Sparsity
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 3102-3110
Open AccessDeepUL: Deep Unlearning via Model Sparsity