Distance Determination for an Automobile Environment
Shane Tuohy
Introduction
In 2008, rear end collisions accounted for almost 25% of all injuries sustained in road traffic accidents on Irish roads [RSA Road Collision Factbook 2008]
Effective distance determination can go a long way to reducing injuries
Current Systems
Mercedes Pre-Safe Audi Pre-Sense Plus Toyota Pre-Collision System
All are RADAR systems Expensive Cannot detect humans, animals Susceptible to interference
System Overview
Front facing standard optical camera
Cheap Many uses Simple to install
OpenCV Begun by Intel, currently maintained by
community, under stewardship of Willow Garage
Extensive library of Computer Vision functions
C, C++, Python, Java
No need to continually ‘reinvent the wheel’
System Overview
Capture Image Process (OpenCV) Feedback To User
System Overview
Capture Image Process (OpenCV) Feedback To User
Image Processing Steps
Threshold Image
Warp Perspective
Determine Distance
Thresholding
Remove road surface and highlight objects Sample road surface in front of vehicle Remove pixels ±35 of sampled value Apply binary threshold
Image Processing Steps
Threshold Image
Warp Perspective
Determine Distance
The Problem
Distance in image does not change linearly as vehicle changes position
The Solution
Inverse Perspective Mapping
Inverse Perspective Mapping Geometric transform which allows us
to remove perspective effect
Image Processing Steps
Threshold Image
Warp Perspective
Determine Distance
Distance Determination
All road pixels are zero
Analyze area in front of car
Find first non zero pixels
Translate to distance using scaling factor
Accurate Distance Calibration How can we know this ‘scaling factor’?
Need to calibrate for particular camera setup
Can be done once for given environment and parameters Lay 1m object on road surface Use chessboard pattern of known size
Roughly calculated for project testing
System Overview
Capture Image Process (OpenCV) Feedback To User
Information Overlay
Provide graphical feedback to user
Project Milestones
1. Threshold to remove road surface. Generate transformation matrix
2. Transform image to IPM view
3. Distance determination
4. Graphics overlay
5. Modify algorithm for use on a real time video stream
Conclusion Further work possible
Improve thresholding for different road conditions Improve performance of IPM algorithm Automatic calibration implementation
Paper submitted to ISSC 2010, awaiting review S. Tuohy, D. O Cualain, M. Glavin, E. Jones:“Distance
Determination for an Automobile Environment using Inverse Perspective Mapping in OpenCV”
Successful implementation of proposed algorithm
Demonstration