Visual object tracking plays a significant role in our daily life such as intelligent transportation and surveillance. However, an accurate and robust object tracker is hard to be obtained as target objects often go through huge appearance changes caused by deformation, abrupt motion, background clutter and occlusion. In this paper, we combine features extracted from deep convolutional neural networks pretrained on object recognition datasets with color name features and histogram of oriented gradient features skillfully to improve tracking accuracy and robustness. The outputs of the convolutional layers encode the senior semantic information of targets and such representations are robust to great appearance variations while their spatial resolution is too coarse to precisely locate targets. In contrast, color name features connected at the back of HOG features could provide more precise localization but are less invariant to appearance changes. We first infer the response of the convolutional features and HOG-CN features respectively, then make a linear combination of them. The maximum value of the result could represent the accurate localization of the target. We not only compare the tracking results of adopting a single feature alone, showing that the performance of them is inferior to ours, but also analyze the effect of exploiting features extracted from different convolutional layers on the tracking performance. What’s more, we introduce the adaptive target response map in our tracking algorithm to keep the target from drifting as much as possible. Extensive experimental results on a large scale benchmark dataset illustrates outstanding performance of the proposed algorithm.
KEYWORDS: Video, Detection and tracking algorithms, Heart, Video compression, Data modeling, Computed tomography, Beam propagation method, Facial recognition systems, Databases, RGB color model
Remote monitoring of vital physiological signs allows for unobtrusive, nonrestrictive, and noncontact assessment of an individual’s health. We demonstrate a simple but robust image photoplethysmography-based heart rate (HR) estimation method for multiple subjects. In contrast to previous studies, a self-learning procedure of tech was developed in our study. We improved compress tracking algorithm to track the regions of interest from video sequences and used support vector machine to filter out potentially false beats caused by variations in the reflected light from the face. The experiment results on 40 subjects show that the absolute value of mean error reduces from 3.6 to 1.3 beats / min. We further explore experiments for 10 subjects simultaneously, regardless of the videos at a resolution of 600 by 800, the HR is predicted real-time and the results reveal modest but significant effects on HR prediction.
KEYWORDS: Video, Heart, Video compression, Detection and tracking algorithms, Video processing, Medicine, Automatic tracking, Signal detection, Denoising, Oximetry
The rise of aging population has created a demand for inexpensive, unobtrusive, automated health care solutions. Image PhotoPlethysmoGraphy(IPPG) aids in the development of these solutions by allowing for the extraction of physiological signals from video data. However, the main deficiencies of the recent IPPG methods are non-automated, non-real-time and susceptible to motion artifacts(MA). In this paper, a real-time heart rate(HR) detection method for multiple subjects simultaneously was proposed and realized using the open computer vision(openCV) library, which consists of getting multiple subjects’ facial video automatically through a Webcam, detecting the region of interest (ROI) in the video, reducing the false detection rate by our improved Adaboost algorithm, reducing the MA by our improved compress tracking(CT) algorithm, wavelet noise-suppression algorithm for denoising and multi-threads for higher detection speed. For comparison, HR was measured simultaneously using a medical pulse oximetry device for every subject during all sessions. Experimental results on a data set of 30 subjects show that the max average absolute error of heart rate estimation is less than 8 beats per minute (BPM), and the processing speed of every frame has almost reached real-time: the experiments with video recordings of ten subjects under the condition of the pixel resolution of 600× 800 pixels show that the average HR detection time of 10 subjects was about 17 frames per second (fps).
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.