The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Visual tracking is a very challenging problem in computer vision as the performance of a tracking algorithm may be degraded due to many challenging issues in the scenes, such as illumination change, deformation, and background clutter. So far no algorithms can handle all these challenging issues. Recently, it has been shown that correlation filters can be implemented efficiently and, with suitable...
This work applies the Gaussian Mixture Probability Hypothesis Density (GMPHD) Filter to multi-object tracking in video data. In order to take advantage of additional visual information, Kernelized Correlation Filters (KCF) are evaluated as a possible extension of the GMPHD tracking-by-detection scheme to enhance its performance. The baseline GMPHD filter and its extension are evaluated on the UA-DETRAC...
Recently, kernelized correlation Filter-based trackers have aroused the interest of many researchers and achieved good results in the field of tracking. However, the current tracking model based on kernelized correlation filters can not deal with the changes of the target appearance and scale effectively. Therefore, in this paper, we intend to solve these two problems and improve the robustness of...
We propose a new tracking framework with an attentional mechanism that chooses a subset of the associated correlation filters for increased robustness and computational efficiency. The subset of filters is adaptively selected by a deep attentional network according to the dynamic properties of the tracking target. Our contributions are manifold, and are summarised as follows: (i) Introducing the Attentional...
The Kernelized Correlation Filters (KCF) tracker has caused the extensive concern in recent years because of the high efficiency. Numberous improvements have been made later. However, due to the large displacement motion between the consecutive image frames, these methods cannot track object well. To better cope the problem, we proposed a new simulated annealed KCF (SAKCF) tracker. Take advantage...
Visual tracking is intrinsically a temporal problem. Discriminative Correlation Filters (DCF) have demonstrated excellent performance for high-speed generic visual object tracking. Built upon their seminal work, there has been a plethora of recent improvements relying on convolutional neural network (CNN) pretrained on ImageNet as a feature extractor for visual tracking. However, most of their works...
This paper gives a research work in solving visual SLAM via a target-oriented tracking approach. The target-oriented tracking in this context refers to those object tracking approaches such as the well-known MeanShift but the approaches based on state-space or prediction are not included. The target-oriented tracking generally locks a dynamic or specific object which is not always available in a natural...
Correlation filter-based tracking methods have accomplished competitive performance on accuracy and robustness, but there is still a huge potential in choosing suitable features. Recently, Convolutional Kernel Networks (CKN), which provide a fast and simple procedure to approximate kernel descriptors, have been proposed and achieved state-of-the-art performance in many vision tasks. In this paper,...
Visual object tracking is a fundamental task in many high-level computer vision applications. Most existing algorithms have to build complex models with expensive computation to achieve accurate object tracking, which brings significant difficulty in real-time tracking. In order to address this problem, motivated by recent success of high-speed correlation filter (CF) models, a novel real-time object...
In order to cope with the complex variation of target appearance during visual tracking, a robust tracking algorithm based on multi-scale kernelized least squares (KLS) is proposed. First, by showing that the dense sampling set of translated patches is circulant, using the well-established theory of circulant matrices, kernelized least squares is efficient computed with fast Fourier transform (FFT)...
Occlusion is a challenging problem in visual object tracking. Most state-of-the-art trackers may learn the appearance of the occluding target when it becomes occluded by other objects in the scene. This paper proposes a novel approach of detecting occlusion by dividing the target into several patches and computing the peak-to-sidelobe ratio of every response map. Furthermore, our method can calculate...
In this paper, a novel Semi-Supervised Multiple Instance Learning (Semi-MIL) approach is presented. Compared with conventional approaches, we utilize a kind of “bag of instances” representation in the semi-supervised learning process, which provides an effective way to use the unlabeled data in multiple instance learning problem. We formulate the problem with a graph model based on the Minimax kernel...
Robust scale and rotation estimation is an important and challenging problem in visual object tracking. There have been proposed many sophisticated trackers to track the location of a target accurately, but most of them do not take much attention to the scale and rotation estimation. Inspired by the success of the correlation filters in visual tracking, we proposed a novel scale-and-rotation correlation...
Achieving precise and robust human detection and tracking over camera networks is a very challenging task in the research of intelligent video surveillance. Its difficulties mainly result from abrupt human object motion, object occlusion and object scale change, and changing object appearance due to changes in illumination and viewpoint, non-rigid deformations, intra-class variability in shape and...
In this paper, we propose a robust visual tracking method based on a temporal ensemble framework. Different from conventional ensemble-based trackers, which combine weak classifiers into a strong one using AdBoost in spatial fusion manners, our method adopts a powerful and efficient tracker integrated with its snapshots in different temporal windows of online tracking process to construct a temporal...
Recently, convolutional neural network (CNN) models have achieved great success in many vision tasks. However, few attempts have been made to explore CNN for online model-free object tracking without time-consuming offline training. In this paper, we propose an online convolutional network (OC-N) for visual object tracking. To make the network less dependent on labeled data, K-means is employed to...
This paper identifies the major drawbacks of a very computationally efficient and state-of-the-art-tracker known as the Kernelized Correlation Filter (KCF) tracker. These drawbacks include an assumed fixed scale of the target in every frame, as well as, a heuristic update strategy of the filter taps to incorporate historical tracking information (i.e. simple linear combination of taps from the previous...
This paper presents a novel object tracking algorithm. Object appearance and spatial information is learned from a single template using a non-linear subspace projection. A probabilistic search strategy, based on particle filter, is employed to find object region in each frame of the video sequence that best models the target object in the subspace representation. Particle filter estimates the posterior...
Robust scale calculation is a challenging problem in visual object tracking. Most state-of-the-art trackers fail to handle large scale variations in complex image sequences. This paper propose a novel approach for robust scale calculation in a tracking-by-detection framework. The proposed approach divides the target into four patches and computes the scale factor by finding the maximum response position...
In this paper, we propose a fast and long-term object tracking algorithm using the ℓ2,1 minimization to obtain a better tracking quality. Our method is based on Regularized Least-Squares Classification (RLSC), in which the target model is updated using an online learning process during object tracking. We construct an appearance model using saliency map, image intensity and position of the target...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.