Technical Name 基於深度學習的可見光穿戴式眼動追踪設備瞳孔中心偵測與追踪技術
Project Operator National Chung Hsing University
Project Host 范志鵬
Deep-Learning-Based Pupil Center DetectionTracking Technology for Visible-Light Wearable Gaze Tracking Devices
Scientific Breakthrough
By applying deep-learning object detection technology based on YOLO model, the proposed pupil tracking method can effectively estimatepredict the center of the pupil in  visible-light mode. For pupil tracking test, the detection accuracy reaches 80,the recall rate is close to 83. The average visible-light pupil tracking errors  are smaller than 2 pixels for the training mode5 pixels for the cross-person test, which are much smaller than those of the previous ellipse fitting design without using deep-learning technology under the same visible-light conditions. After the combination of calibration process, the average gaze tracking errors by the proposed YOLOv3-tiny-based pupil tracking models are smaller than 2.93.5 degrees at the trainingtesting modes, respective
Industrial Applicability
Wearable eye tracker can trackmeasure eyeball positioneye movement information. It has been widely used in visual system, psychology,cognitive linguistics. In educationlearning research, it can analyze the eye movement of each tester to support a unique teaching method. In  market researchconsumer surveys, eye trackers can be used to learn which productspackaging designs are more attractive to consumers. The developed scheme can also be applied to various domains such as driving safety monitoringhuman-computer interaction/ interface designs.
Matching Needs
Keyword Deep-Learning YOLOv3-tiny Model Visible-Light Pupil Tracking Eye Tracking Gaze Tracking Wearable Eye Tracker Convolutional Neural Network (CNN) Object Detection Pattern Recognition
  • Contact
other people also saw