• Built by Dong Chen, Zhaojian Li from Michigan State University
• Started on Oct.19, 2019, Lastly updated on Sept.14, 2021

This project aims at building a on-device APP used to asist human drivers. This APP combines three basic functions: object detection(vehicle, traffic light, stop sign, pedestrain), lane deviation warning and distance estimation.

To be added...

We use the deep learning methods to do object detection. To be specific, we use the YOLO-v3 model to do object detection, here we are only curious about traffic-related objects, such as vehicles, pedestrain, traffic lights and stop signs.

Architecture of Yolo-v3 model

Considered limited computing resources on mobile devices (smart phones), we adapt the convential computer vision methods.

Modification logs:

• Delete the display code for "intermediate pipeline images".
• Simiplify codes.
• Problems with road curvature and offset values are always positive.

47o FOV len.

Distance Estimation

    d = F_c * H_c / (y_b - y_h)

For privacy issues, there are few open resources for dash camera videos. We will show our application by three different video demos.

• Stop sign detection

  video link

• Traffic light detection

  video link

• Lane deviation detection

  video link

1. YOLOv3: An Incremental Improvement
2. What’s new in YOLO v3?
3. Integration of Vehicle Detection and Distance Estimation using Stereo Vision for Real-Time AEB System
4. Robust Range Estimation with a Monocular Camera for Vision-Based Forward Collision Warning System
5. Advanced Lane Finding
6. Lane Departure Warning System for Autonomous Driving

To be added...

1. Yolo on iOS
2. Mobileye Camera Development Kit