Critical Overview of Visual Tracking with Kernel Correlation Filter

Abstract

With the development of new methodologies for faster training on datasets, there is a need to provide an in-depth explanation of the workings of such methods. This paper attempts to provide an understanding for one such correlation filter-based tracking technology, Kernelized Correlation Filter (KCF), which uses implicit properties of tracked images (circulant matrices) for training and tracking in real-time. It is unlike deep learning, which is data intensive. KCF uses implicit dynamic properties of the scene and movements of image patches to form an efficient representation based on the circulant structure for further processing, using properties such as diagonalizing in the Fourier domain. The computational efficiency of KCF, which makes it ideal for low-power heterogeneous computational processing technologies, lies in its ability to compute data in high-dimensional feature space without explicitly invoking the computation on this space. Despite its strong practical potential in visual tracking, there is a need for an in-depth critical understanding of the method and its performance, which this paper aims to provide. Here we present a survey of KCF and its method along with an experimental study that highlights its novel approach and some of the future challenges associated with this method through observations on standard performance metrics in an effort to make the algorithm easy to investigate. It further compares the method against the current public benchmarks such as SOTA on OTB-50, VOT-2015, and VOT-2019. We observe that KCF is a simple-to-understand tracking algorithm that does well on popular benchmarks and has potential for further improvement. The paper aims to provide researchers a base for understanding and comparing KCF with other tracking technologies to explore the possibility of an improved KCF tracker.

Dancer Tracking Algorithm in Ethnic Areas Based on Multifeature Fusion Neural Network

“…Computer vision collects image information through sensor equipment and obtains the information contained in the image through image processing, detection, recognition, understanding, etc., so as to achieve the purpose of perceiving the external world. At present, the visual target tracking technology has been developed rapidly, especially in the case of simple background; few interfering objects or setting constraints, the tracking effect has been able to meet the needs of human beings [4]. However, there are still many challenges in target tracking in practical applications, especially the illumination changes, deformation, occlusion, background clutter, and other factors during the tracking process have a great impact on the performance of the target tracking algorithm.…”

DATaR: Depth Augmented Target Redetection using Kernelized Correlation Filter

“…One of the popular CF-based trackers was proposed by Henrique et al where the authors proposed a kernelized version of the CF tracker [ 7 ] which benefitted from the circulant structure of the samples. This tracker was studied in [ 8 – 10 ] and further improvements were investigated by [ 11 , 12 ] who applied a correlation filter to scale space, addressing the issue of scale adaptation. Other improvements include spatial regularization in SRDCF [ 13 ], continuous convolution in C-COT [ 14 ], max-margin classifiers in [ 15 ], Spatio-temporal learning [ 16 ], and adding robustness using part-based features [ 17 , 18 ].…”

Application of Human Posture Recognition Based on the Convolutional Neural Network in Physical Training Guidance

“…It can provide athletes and coaches with corresponding data as a reference through video analysis and make a relatively systematic evaluation of individual athletes' and groups' performance in sports competitions [ 1 ]. In recent years, the number of sports videos has increased geometrically, and at the same time, there is a large amount of interference information in the huge amount of sports videos [ 2 ]. The information that athletes and coaches need and pay attention to occupies relatively little in the game video, so how to quickly find the needed information in the massive video information has become a research hotspot in sports video technology.…”