Transportation Informatics Group, ALPEN-ADRIA University of Klagenfurt. Transportation Informatics Group University of Klagenfurt 3/10/2009 1

Transcription

1 Machine Vision Transportation Informatics Group University of Klagenfurt Alireza Fasih, /10/ Address: L4.2.02, Lakeside Park, Haus B04, Ebene 2, Klagenfurt-Austria

2 Index Driver Fatigue Detection based on Head Tracking Driver Fatigue Detection based on Eye Blinking Detection Gesture Recognition Traffic Sign Recognition Pedestrian Recognition on the Night By Thermal Camera Augmented Reality Surveillance 3/10/2009 2

3 1- Driver Fatigue Detection Based on Head Tracking Based on Eyes Blinking Detection 3/10/2009 3

4 Driver Fatigue Detection By Head Tracking Based on Head Tracking It should be at least 24 fps Based on Head Tracking Camera is mounted beside the driver in orthogonal mode Digital Camera 1m 3/10/2009 4

5 Driver Fatigue Detection By Eye Blinking Detection - It should be at least 24 fps - Based on Circular Hough Transform - Camera is Mounted in front of the Driver 3/10/2009 5

6 Gesture Recognition Gesture Recognition is a topic in computer science and language technology with the goal of interpreting human gestures via mathematical algorithms. Gestures can originate from any bodily motion or state but commonly originate from the face or hand. Current focuses in the field include emotion recognition from the face and hand gesture recognition. In this project we are going to recognize some basic action. 3/10/2009 6

7 Lane Departure Warning System In road-transport terminology, a lane departure warning system (LDW) is a mechanism designed to warn a driver when the vehicle begins to move out of its lane (unless a turn signal is on in that direction) on freeways and arterial roads. 3/10/2009 7

8 Lane Departure Warning System Project Properties: The video is already captured, and you don t need to grab from a real camera. It should be very fast, at least 24 fps. Hough transform or other method for lean detection is required. 3/10/2009 8

9 Traffic Sign Recognition Traffic sign recognition is a technology by which a vehicle is able to recognize the traffic signs put on the road e.g. "slow" or "school ahead" or "turn ahead". This is part of the features collectively called ADAS. The idea is to improve road safety by assisting the driver. It may happen that the driver is tired or misses the road sign. This feature will recognize the road sign and accordingly inform the driver to go slow or take a turn. 3/10/2009 9

10 Traffic Sign Recognition Project Properties: Program should recognize at least 4 types of traffic sign. For simplification, a video is already prerecorded. Shape Matching Based 3/10/

11 Pedestrian Recognition on the Night By Thermal Camera 3/10/

12 Pedestrian Recognition on the Night By Thermal Camera 3/10/

13 Augmented Reality Based on ARToolkit ARToolKit is a computer vision tracking library that allows for the creation of augmented reality applications that overlay virtual imagery on the real world. To do this, it uses video tracking capabilities in order to calculate the real camera position and orientation relative to square physical markers in real time. 3/10/

14 Augmented Reality Based on ARToolkit 3/10/

15 Surveillance Systems surveillance is the process of monitoring the behavior of people, objects or processes within systems for conformity to expected or desired norms in trusted systems for security or social control. 3/10/

16 Car Plate License Recognition Automatic number plate recognition is a mass surveillance method that uses optical character recognition on images to read the licence plates on vehicles. 3/10/