Multimodal Vision Research Laboratory

MVRL

Research Area: Transportation

How can overhead imagery and 3D sensing improve roadway safety assessment and traffic understanding? Transportation research applies computer vision and machine learning to crash risk, traffic dynamics, and infrastructure monitoring. Recent work includes beta distribution learning for reliable roadway crash risk assessment, multi-scale satellite imagery for fatal crash risk estimation, fully automated roadway safety assessment using LiDAR and overhead imagery (FARSA), and remote estimation of free-flow speeds. These projects sit within our broader geospatial AI portfolio, targeting public-safety outcomes from aerial and LiDAR data.

All Publications

  1. Thumbnail for MCPDepth: Omnidirectional Depth Estimation via Stereo Matching from Multi-Cylindrical Panoramas
    Qiao F, Xiong Z, Zhu X, Ma Y, He Q, Jacobs N. 2026. MCPDepth: Omnidirectional Depth Estimation via Stereo Matching from Multi-Cylindrical Panoramas. In: Omnidirectional Computer Vision Workshop (OmniCV) (IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshop).
  2. Xiong Z, Ye X, Yaman B, Cheng S, Lu Y, Luo J, Jacobs N, Ren L. 2026. UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving.
  3. Elallaf A, Jacobs N, Ye X, Chen M, Liang G. 2026. Beta Distribution Learning for Reliable Roadway Crash Risk Assessment. In: Association for the Advancement of Artificial Intelligence (AAAI).
  4. Liang G, Zulu J, Xing X, Jacobs N. 2023. Unveiling Roadway Hazards: Enhancing Fatal Crash Risk Estimation through Multi-Scale Satellite Imagery and Self-Supervised Cross-Matching. Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS). DOI: 10.1109/JSTARS.2023.3331438.
  5. Chen M, Hadzic A, Song W, Jacobs N. 2021. Applications of Deep Machine Learning to Highway Safety and Usage Assessment. In: Transportation Research Board Workshop (Sponsored by AED50).
  6. Hadzic A, Blanton H, Song W, Chen M, Workman S, Jacobs N. 2020. RasterNet: Modeling Free-Flow Speed using LiDAR and Overhead Imagery. In: IEEE/ISPRS Workshop: Large Scale Computer Vision for Remote Sensing (EARTHVISION). DOI: 10.1109/CVPRW50498.2020.00112.
  7. Thumbnail for Dynamic Traffic Modeling from Overhead Imagery
    Workman S, Jacobs N. 2020. Dynamic Traffic Modeling from Overhead Imagery. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). DOI: 10.1109/CVPR42600.2020.01233.
  8. Thumbnail for Remote Estimation of Free-Flow Speeds
    Song W, Salem T, Blanton H, Jacobs N. 2019. Remote Estimation of Free-Flow Speeds. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS). DOI: 10.1109/IGARSS.2019.8900286.
  9. Thumbnail for Learning to Look around Objects for Top-View Representations of Outdoor Scenes
    Schulter S, Zhai M, Jacobs N, Chandraker M. 2018. Learning to Look around Objects for Top-View Representations of Outdoor Scenes. In: European Conference on Computer Vision (ECCV). DOI: 10.1007/978-3-030-01267-0_48.
  10. Thumbnail for FARSA: Fully Automated Roadway Safety Assessment
    Song W, Workman S, Hadzic A, Souleyrette R, Green E, Chen M, Zhang X, Jacobs N. 2018. FARSA: Fully Automated Roadway Safety Assessment. In: IEEE Winter Conference on Applications of Computer Vision (WACV). DOI: 10.1109/WACV.2018.00063.