Comparative Study of CAMSHIFT and RANSAC Methods for Face and Eye Tracking in Real-Time Video

2017 ◽  
Vol 13 (2) ◽  
pp. 63-75 ◽  
Author(s):  
T. Raghuveera ◽  
S. Vidhushini ◽  
M. Swathi
Keyword(s):  
Eye Tracking ◽  
Real Time ◽  
Performance Measures ◽  
Pervasive Computing ◽  
Heterogeneous Environments ◽  
Camshift Algorithm ◽  
The Face ◽  
Real Time Tracking ◽  
Face Detector

Real-Time Facial and eye tracking is critical in applications like military surveillance, pervasive computing, Human Computer Interaction etc. In this work, face and eye tracking are implemented by using two well-known methods, CAMSHIFT and RANSAC. In our first approach, a frontal face detector is run on each frame of the video and the Viola-Jones face detector is used to detect the faces. CAMSHIFT Algorithm is used in the real- time tracking along with Haar-Like features that are used to localize and track eyes. In our second approach, the face is detected using Viola-Jones, whereas RANSAC is used to match the content of the subsequent frames. Adaptive Bilinear Filter is used to enhance quality of the input video. Then, we run the Viola-Jones face detector on each frame and apply both the algorithms. Finally, we use Kalman filter upon CAMSHIFT and RANSAC and compare with the preceding experiments. The comparisons are made for different real-time videos under heterogeneous environments through proposed performance measures, to identify the best-suited method for a given scenario.

scholarly journals Detection of Hidden Facial Surface Masking in Stored and Real Time Captured Images: A Deep Learning Perspective in Covid Time

2021 ◽  
Vol 38 (6) ◽  
pp. 1875-1885
Author(s):  
Ruchi Jayaswal ◽  
Manish Dixit
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Preventive Measure ◽  
Face Mask ◽  
Histogram Equalization ◽  
Test Accuracy ◽  
The Face ◽  
Novel Coronavirus ◽  
Face Detector

A novel coronavirus has spread over the world and has become an outbreak. This, according to a WHO report, is an infectious disease that aims to spread. As a consequence, taking precautions is the only method to avoid catching this virus. The most important preventive measure against COVID-19 is to wear a mask. In this paper, a framework is designed for face mask detection using a deep learning approach. This paper aims to predict a person having a mask or unmask and also presents a proposed dataset named RTFMD (Real-Time Face Mask Dataset) to accomplish this objective. We have also taken the RFMD dataset from the internet to analyze the performance of system. Contrast Limited Adaptive Histogram Equalization (CLAHE) technique is applied at the time of pre-processing to enhance the visual quality of images. Subsequently, Inceptionv3 model used to train the face mask images and SSD face detector model has been used for face detection. Therefore, this paper proposed a model CLAHE-SSD_IV3 to classify the mask or without mask images. The system is also tested at VGG16, VGG19, Xception, MobilenetV2 models at different hyperparameters values and analyze them. Furthermore, compared the result of the proposed dataset RTFMD with the RFMD dataset. Additionally, proposed approach is compared with the existing approach on Face Mask dataset and RTFMD dataset. The outcomes have obtained 98% test accuracy on this proposed dataset RTFMD while 97% accuracy on the RFMD dataset in real-time.

Controlling a motorized electric wheelchair based on face tilting

2019 ◽  
Vol 15 (4) ◽  
Author(s):  
Hassan M. Qassim ◽  
Abdulrahman K. Eesee ◽  
Omar T. Osman ◽  
Mohammed S. Jarjees
Keyword(s):  
Quality Of Life ◽  
Real Time ◽  
Tracking System ◽  
Lower Limbs ◽  
Direct Impact ◽  
Excellent Performance ◽  
Electric Wheelchair ◽  
Real Time Tracking

AbstractDisability, specifically impaired upper and/or lower limbs, has a direct impact on the patients’ quality of life. Nowadays, motorized wheelchairs supported by a mobility-aided technique have been devised to improve the quality of life of these patients by increasing their independence. This study aims to present a platform to control a motorized wheelchair based on face tilting. A real-time tracking system of face tilting using a webcam and a microcontroller circuit has been designed and implemented. The designed system is dedicated to control the movement directions of the motorized wheelchair. Four commands were adequate to perform the required movements for the motorized wheelchair (forward, right, and left, as well as stopping status). The platform showed an excellent performance regarding controlling the motorized wheelchair using face tilting, and the position of the eyes was shown as the most useful face feature to track face tilting.

Reducing facial dynamics’ speed during speech enhances attention to mouth in children with autism spectrum disorder: An eye-tracking study

2020 ◽  
pp. 1-10
Author(s):  
Bruno Gepner ◽  
Anaïs Godde ◽  
Aurore Charrier ◽  
Nicolas Carvalho ◽  
Carole Tardif
Keyword(s):  
Autism Spectrum Disorder ◽  
Eye Tracking ◽  
Real Time ◽  
Therapeutic Potential ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Visual Exploration ◽  
Children With Asd ◽  
The Face ◽  
Visual Fixations

Abstract Facial movements of others during verbal and social interaction are often too rapid to be faced and/or processed in time by numerous children and adults with autism spectrum disorder (ASD), which could contribute to their face-to-face interaction peculiarities. We wish here to measure the effect of reducing the speed of one's facial dynamics on the visual exploration of the face by children with ASD. Twenty-three children with ASD and 29 typically-developing control children matched for chronological age passively viewed a video of a speaker telling a story at various velocities, i.e., a real-time speed and two slowed-down speeds. The visual scene was divided into four areas of interest (AOI): face, mouth, eyes, and outside the face. With an eye-tracking system, we measured the percentage of total fixation duration per AOI and the number and mean duration of the visual fixations made on each AOI. In children with ASD, the mean duration of visual fixations on the mouth region, which correlated with their verbal level, increased at slowed-down velocity compared with the real-time one, a finding which parallels a result also found in the control children. These findings strengthen the therapeutic potential of slowness for enhancing verbal and language abilities in children with ASD.

scholarly journals Real-Time Multi-Scale Face Detector on Embedded Devices

Sensors ◽  
2019 ◽  
Vol 19 (9) ◽  
pp. 2158 ◽  
Author(s):  
Xu Zhao ◽  
Xiaoqing Liang ◽  
Chaoyang Zhao ◽  
Ming Tang ◽  
Jinqiao Wang
Keyword(s):  
Real Time ◽  
Face Detection ◽  
Class Imbalance ◽  
Network Capacity ◽  
Raspberry Pi ◽  
Class Imbalance Problem ◽  
Embedded Devices ◽  
Basic Step ◽  
The Face ◽  
Face Detector

Face detection is the basic step in video face analysis and has been studied for many years. However, achieving real-time performance on computation-resource-limited embedded devices still remains an open challenge. To address this problem, in this paper we propose a face detector, EagleEye, which shows a good trade-off between high accuracy and fast speed on the popular embedded device with low computation power (e.g., the Raspberry Pi 3b+). The EagleEye is designed to have low floating-point operations per second (FLOPS) as well as enough capacity, and its accuracy is further improved without adding too much FLOPS. Specifically, we design five strategies for building efficient face detectors with a good balance of accuracy and running speed. The first two strategies help to build a detector with low computation complexity and enough capacity. We use convolution factorization to change traditional convolutions into more sparse depth-wise convolutions to save computation costs and we use successive downsampling convolutions at the beginning of the face detection network. The latter three strategies significantly improve the accuracy of the light-weight detector without adding too much computation costs. We design an efficient context module to utilize context information to benefit the face detection. We also adopt information preserving activation function to increase the network capacity. Finally, we use focal loss to further improve the accuracy by handling the class imbalance problem better. Experiments show that the EagleEye outperforms the other face detectors with the same order of computation costs, on both runtime efficiency and accuracy.

scholarly journals Sistem Deteksi Biometrik Keunikan Wajah Secara Real Time

2020 ◽  
Vol 4 (1) ◽  
pp. 30
Author(s):  
Anita Sindar RM Sinaga
Keyword(s):  
Real Time ◽  
Face Detection ◽  
Filter Design ◽  
Detection System ◽  
Training Data ◽  
Gabor Wavelet ◽  
Design Problems ◽  
Camshift Algorithm ◽  
The Face ◽  
The Difference

<table width="605" border="0" cellspacing="0" cellpadding="0"><tbody><tr><td valign="top" width="382"><p>Facial recognition is important for identifying a person's biodata profile. The physical development of students from the time they entered college to graduation has experienced inconspicuous changes but it is sometimes difficult to identify faces one by one. Digital form is becoming a trend to remember more real time. An important part of human physical identification has begun to shift from signature - finger - face selection. The face includes five important senses that are interconnected into an identification device. In this study the focus is on face detection based on color, the application of the Camshift Algorithm and finding the distance between the face sensing points is the result of the Gabor Wavelet method. Training data uses 4-8 second real time video. The hue histogram is basically the same as the RGB histogram, the difference is that the hue histogram uses the Hue value instead of RGB because the hue value represents natural color without regard to lighting. Gabor Wavelet transform is provided to solve filter design problems. The face detection system looks for face points to form a frame-shaped face selection if previously the face has been stored in a database so the system can easily describe biodata. Face selection can be done on live testing data. The selection box detection follows every facial movement.</p></td></tr></tbody></table>

Research of CamShift Algorithm Used in Object Tracking of Selfvision Underwater Robot

2013 ◽  
Vol 662 ◽  
pp. 971-974
Author(s):  
Wei Xiang
Keyword(s):  
Object Tracking ◽  
Real Time ◽  
Mean Shift ◽  
Underwater Robot ◽  
Background Color ◽  
Mean Shift Algorithm ◽  
Experimental Platform ◽  
Camshift Algorithm ◽  
Tracking Process ◽  
Real Time Tracking

It is difficult for self-vision underwater robot to track object, and the tracking process is frequently inaccurate, unstable or even loss goals. To solve the above questions, Continuously Adaptive Mean Shift Algorithm (CamShift) is used in object tracking of self-vision underwater robot in this paper. We build a software experimental platform by VC++6.0 and Opencv1.0, with the external camera to capture video, and then apply Camshift algorithm in the environment, in which background color is not similar to the object to realize the real time tracking. The experimental results show the effectiveness of the algorithm for self-vision underwater robot.

Design Algorithm of Moving Target Adaptive Tracking System

2015 ◽  
Vol 738-739 ◽  
pp. 373-376
Author(s):  
Ju Bao Qu
Keyword(s):  
Real Time ◽  
Adaptive Algorithm ◽  
Tracking System ◽  
Moving Target ◽  
Design Algorithm ◽  
State Information ◽  
Camshift Algorithm ◽  
Real Time Tracking ◽  
High Degree ◽  
Multi Mode

According to the characteristics of the moving target state information, we propose a multi-mode adaptive CamShift algorithm (MACA), and using the adaptive algorithm designed a real-time tracking system. The large number of experiments show that the algorithm robustness, real-time, high degree of system automation.

Face Tracking Based on Particle Filtering and α-β-γ Filtering

2014 ◽  
Vol 651-653 ◽  
pp. 2306-2309
Author(s):  
Dong He Yang
Keyword(s):  
Particle Filter ◽  
Real Time ◽  
Particle Filtering ◽  
Face Tracking ◽  
Candidate Model ◽  
Target Rotation ◽  
Computing Center ◽  
The Face ◽  
Real Time Tracking ◽  
Particle Filter Algorithm

In view of the traditional particle filter algorithm cannot guarantee effective tracking in the case of target rotation or obscured. The study proposes a tracking method based on α-β-γ filter and particle filter. The algorithm uses α-β-γ filtering prediction position as the next frame image target candidate model of computing center of particle filter algorithm. The algorithm uses α-β-γ filtering prediction position as the next frame image target candidate model of computing center of particle filter. To reduce the number of iterations of particle filter algorithm, strengthen the real-time tracking of moving face. When detect the face is obscured, with α-β-γ filter prediction point as facial movement position, so as to realize the continuity of the movement. The experimental results show that the proposed algorithm improves the traditional particle filter for real-time face tracking, enhancing the ability of anti-occlusion.

Sign in / Sign up

Export Citation Format

Share Document