Real-Time Eye Detection in Video Streams

Author(s):  
Kunhui Lin ◽  
Jiyong Huang ◽  
Jiawei Chen ◽  
Changle Zhou
2021 ◽  
Vol 11 (11) ◽  
pp. 4758
Author(s):  
Ana Malta ◽  
Mateus Mendes ◽  
Torres Farinha

Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.


2012 ◽  
Author(s):  
Husniza Razalli ◽  
Rahmita Wirza O. K. Rahmat ◽  
Ramlan Mahmud

Masalah sistem pengesanan mata yang tegar tanpa sebarang gangguan adalah satu isu yang penting dan mencabar di dalam bidang visi komputer. Masalah ini bukan hanya mengurangkan masalah dalam carian ciri–ciri paras rupa untuk proses pengecaman tetapi juga boleh digunakan untuk memudahkan tugas pengenalpastian dan interaksi antara manusia dan sistem komputer. Walaupun kebanyakan hasil kerja terdahulu telah pun mempunyai keupayaan menentukan lokasi mata manusia tetapi objektif utama rencana ini bukan tertumpu kepada pengesanan mata sahaja. Objektif kajian adalah untuk merekabentuk sebuah sistem masa nyata dan terperinci, iaitu sistem pengesanan muka berskala dengan ciri–ciri petunjuk pergerakan mata berdasarkan pergerakan anak mata (iris) dengan mengunakan teknik penempatan yang terhasil daripada teknik pemprosesan imej dan teknik muatan bulatan. Hasil daripada kajian ini telah pun berjaya diimplimentasikan menggunakan kamera web dengan ralat yang minimum. Kata kunci: Pengesanan mata masa nyata; penempatan anak mata; pemprosesan imej; pengesanan bucu; muatan bulatan Robust, non–intrusive human eye detection problem has been a fundamental and challenging problem for computer vision area. Not only it is a problem of its own, it can be used to ease the problem of finding the locations of other facial features for recognition tasks and human–computer interaction purposes as well. Many previous works have the capability of determining the locations of the human eyes but the main task in this paper is not only a vision system with eye detection capability. Our aim is to design a real–time face tracker system and iris localization using edge point detection method indicates from image processing and circle fitting technique. As a result, our eye tracker system was successfully implemented using non–intrusive webcam with less error. Key words: Real–time face tracking; iris localization; image processing; edge detection; circle fitting


Sign in / Sign up

Export Citation Format

Share Document