1. SEMINAR ON TRAFFIC MANAGEMENT USING IMAGE PROCESSING by Smruti Ranjan Mishra (1AY07IS072) Under the guidance of Prof Mahesh G. Acharya Institute Of Technology Bangalore

2. Introduction Importance Types Working of queue detection Results Conclusion OUTLINE

3. introduction What are traffic detectors?

4. TRAFFIC DETECTION SYSTEMS STRUCTURE Detector Processor/controller Storage

5. IMPORTANCE Freeway Monitoring Actuated Signal Control Ramp Meter Control Road Discipline Enforcement Dynamic Traffic Assignment

6. Traffic DETECTOR TYPES Inductive loops Video Microwave Infrared Acoustic Radar Magnetic Radio frequency Global positioning system (GPS)

7. Shares Of Detector Types at new ATMS Sites

8. working  Presently the most new detector types are compatible with loop detectors.  Using the loop detector speed of a vehicle can be estimated using the speed calculation algorithm.  Now lets see the Traffic queue detection using Image Processing.

9. Working (contd…) After getting the images of the vehicle, they get analyzed. The Parameters get measured are traffic volumes, speed, headways, inter vehicle gap, junction turning, origin and destination of traffic.

10. Working (contd…)  Stages Of Image Analysis a. The Image Sensors Used b. ADC Conversion c. Pre-processing  Then the proposed picture is submitted to processor as 2-D array of numbers.  Two jobs to be done a. Green light on b. Red light on

11. Working (contd…)  Methods Of Vehicle detection a. Background frame differencing b. Inter frame differencing c. Segmentation and classification  Queue Detection Algorithm For this two different algorithms have been used a. Motion Detection Algorithm b. Vehicle Detection Algorithm

12. Working (contd…)

13. Threshold Selection Program:-  The no. of edge points greater than the left limit get enough parameters below and above a proper threshold value.  These nos. are used to create a histogram.  This histogram is smoothed using a median filter and we expect to get two peaks, one peak related to the frames passing a vehicle and the other related to the frames without vehicles for that window.

14. Working (contd…) Traffic Movements at Junctions (TMJ) Measuring traffic movements of vehicles at junctions is Important. Previous research work for the TMJ parameter is based on a full-frame approach. The first step to measure the TMJ parameters using the key region.

15. Working (contd…) The second step of the algorithm is to define a minimum numbers of key regions inside the boundary of the polygon, covering the junction. These key regions are used for detecting vehicles entering and exiting the junction. A status vector is created for each window in each frame. If a vehicle is detected in a window, a “one” is inserted on its corresponding status vector, otherwise, a “Zero” is inserted. Now by analyzing the status vector of each window, the TMJ parameters are calculated for each path of the junction.

16. result To implement the algorithm in real-time, it was decided that the vehicle detection operation should only be used in a sub-profile where we expect the queue will be extended.

17. Result (contd…)

18. conclusion Algorithm measuring basic queue parameters s have been discussed. The algorithm uses a recent technique by applying simple but effective operations. In order to reduce computation time motion detection operation is applied on all sub profiles. The vehicle detection operation is a less sensitive edge-based technique. The threshold selection is done dynamically to reduce the effects of variations of lighting. The measurement algorithm has been applied to traffic scenes with different lighting conditions. Queue length measurement showed 95% accuracy at maximum. Error is due to objects located far from camera and can be reduced to some extent by reducing the size of the sub profiles.

19. references Digital Image Processing by Rafael C.Gonzalez and Richard E.Woods. Hoose. N: ‘Computer Image Processing in Traffic Engineering’. Rourke, A., and Bell, M.G.H.: ‘Queue detection and congestion monitoring using mage processing’, Traffic Engg. And Control. Traffic Queue Length Measurement Using an Image Processing Sensor by Masakatsu Higashikobo, Toshio Hinenoya and Kouhei Takeouchi. A Real-time Computer Vision System for Vehicle Tracking and Traffic Surveillance by Benjamin Coifman (corresponding author). A Real-time Computer Vision System for Measuring Traffic Parameters by David Beymer, Philip McLauchlan, Benn Coifman and Jitendra Malik.

20. QUERIES ? QUERIES ?

21. THANK YOU