This project deals with information gathering and statistics about the characteristics and behavior of vehicle movement through a traffic-light-controlled intersection
Abstract
This project deals with information gathering and statistics about the characteristics and behavior of vehicle movement through a traffic-light-controlled intersection, for adjusting the traffic light timing to the traffic passing through the junction it is stationed in. For this purpose, a camera placed on the traffic light post and pointed at the junction is used. Thereby, an efficient, simple method of analyzing the traffic in the intersection is obtained. In the first stage of the algorithm’s operation, a motion estimation process is applied to identify areas of the input video in which there is motion, and the directions of motion in these areas. After that, the algorithm performs identification of the lanes in the video. In the second stage, the algorithm analyzes the traffic load in every lane, by identifying the vehicles in the video received from the camera, and produces load percentage for every lane as output.
Motion Estimation – New Approach
- Less lane detection
- Original idea – separate lanes using vectors
- Not refined enough in practice
- More direction detection
- Helps capturing regions of interest
- Road mask can be easily extracted
Vehicle Detection
- Previous attempts at frame subtraction proved partially successful
- Subtract current frame from background
- Subtraction is done in grayscale
- To solve this, current frame is also subtracted from previous frame
- Problem still exists during red light
What about lane detection?
- Introducing the Monorail Algorithm
- Vehicles tend to pass on spatially local regions of the lane
- Foreground blob in lane center à Car in lane J
- Simple to obtain and use, high accuracy
- Does NOT count cars
- Evaluating load instead
Block Diagram
Monorail – Load Evaluation
- A block in the rail is “marked” if it overlaps the foreground mask
- Overlapping: >50% of block
- Marked block weights are summed, divided by total lane weight
- Load percentage is obtained!
Summary
- Completely automated system
- Easy to install and maintain
- Based on existing infrastructure
- Good accuracy
- More informative than metal detectors