90 likes | 219 Vues
Eye Tracking Using A Simple Webcamera. David Wild Supervisor: James Connan Rhodes University Computer Science Department. Contents:. Brief Recap of project Approaches found My choice Tools Still Needs to be done Questions. Brief Recap of project. Eye tracking:
E N D
Eye Tracking Using A Simple Webcamera David Wild Supervisor: James Connan Rhodes University Computer Science Department
Contents: • Brief Recap of project • Approaches found • My choice • Tools • Still Needs to be done • Questions
Brief Recap of project • Eye tracking: • Find the eyes in a frame • Use the eyes to calculate point of interest • Usually pre-program calibration to find the limits • Original Plan • Use an infrared camera to make the detection simpler, still a possibility • Find, or make an appropriate algorithm to calculate the gaze
Approaches found (1) • Real Time Tracking Algorithm with head movement Compensation (RTAC) • Eye detection using the corneal glint • Find the glint-pupil vector • Map to 3D • Calculate head movement • Compensate for head movement
Approaches found (2) • Neural Networks • Find the eye and face using intensities of pixels • Use OpenCv to detect the eye and face regions • Create a smaller picture for training the NN • Use the intensities of each pixel as a input for the NN • Starburst • Noise reduction (shot and line) • Corneal reflection detection using adaptive brightness-threshold • Feature Detection • Ellipse Detection • Calibration
My Choice • Starburst Eye detection • Robust system • Interesting to examine • Could possibly include head movement compensation as a extension to the original algorithm • Can still change this choice
Tools • C++ • OpenCV • Ordinary USB Webcam
Still needs to be done • Obviously Coding and Implementation • Finding the eye • Design the Calibration pre-program • Implement the algorithm • Test and improve