Abstract
This work proposes a fast face tracking-by-detection (FFTD) algorithm that can perform tracking, face detection and discrimination tasks. On the basis of using the kernelized correlation filter (KCF) as the basic tracker, multitask cascade convolutional neural networks (CNNs) are used to detect the face, and a new tracking update strategy is designed. The update strategy uses the tracking result modified by detector to update the filter model. When the tracker drifts or fails, the discriminator module starts the detector to correct the tracking results, which ensures the out-of-view object can be tracked. Through extensive experiments, the proposed FFTD algorithm is shown to have good robustness and real-time performance for video monitoring scenes.
Highlights
In recent years, the Internet of Things (IoT) and big data have grown substantially, and secure monitoring is one of the most challenging tasks [1,2,3]
The kernelized correlation filter (KCF) and fast face tracking-by-detection (FFTD) algorithms adopted the histogram of oriented gradients (HOG) feature; the cell size was 4 × 4 using a Gaussian kernel in the experiment
To improve the robustness and real-time performance of the tracking algorithm in intelligent video monitoring, this work proposes the FFTD algorithm, which is based on the tracking-by-detection framework
Summary
The Internet of Things (IoT) and big data have grown substantially, and secure monitoring is one of the most challenging tasks [1,2,3]. Correlation filters and deep learning have been used for tracking and have achieved good results [8,9]. Some convolutional neural network (CNN)-based correlation filters tracking methods [11,12] and deep learning detection methods [13,14] have high accuracy in tracking. A multitask cascade CNN, as a detector, is introduced to detect faces and modify the tracker’s result. The experimental results show that the fast face tracking-by-detection (FFTD) algorithm has high robustness and real-time operation; high performance and long-term tracking secure monitoring can be achieved.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have