Robust visual tracking based on kernelized correlation filters

Recently, kernelised correlation filter (KCF)‐based trackers aroused increasing interest and achieved extremely compelling results in different competitions and benchmarks in the field of visual object tracking. However, the training mechanism of the KCF that exploits simple linear combinations of filter from the previous frame easily cause error accumulation. To overcome this problem, the authors propose a novel training strategy that utilises all of the previous training samples, and a sparsity‐related loss function regularised by the L 1 norm to deal with the problem of the fixed template size in KCF trackers, a separate scale filter is learned for scale estimation during the tracking process. Moreover, powerful features that include histogram of oriented gradients (HOG) and colour features are integrated to further improve the robustness of the authors’ tracking. Extensive experiments in various challenging situations demonstrate that the proposed method performs favourably against several state‐of‐the‐art tracking algorithms.

MSST-ResNet: Deep multi-scale spatiotemporal features for robust visual object tracking

Visual object tracking is still considered a challenging task in computer vision research society. The object of interest undergoes significant appearance changes because of illumination variation, deformation, motion blur, background clutter, and occlusion. Kernelized correlation filter- (KCF) based tracking schemes have shown good performance in recent years. The accuracy and robustness of these trackers can be further enhanced by incorporating multiple cues from the response map. Response map computation is the complementary step in KCF-based tracking schemes, and it contains a bundle of information. The majority of the tracking methods based on KCF estimate the target location by fetching a single cue-like peak correlation value from the response map. This paper proposes to mine the response map in-depth to fetch multiple cues about the target model. Furthermore, a new criterion based on the hybridization of multiple cues i.e., average peak correlation energy (APCE) and confidence of squared response map (CSRM), is presented to enhance the tracking efficiency. We update the following tracking modules based on hybridized criterion: (i) occlusion detection, (ii) adaptive learning rate adjustment, (iii) drift handling using adaptive learning rate, (iv) handling, and (v) scale estimation. We integrate all these modules to propose a new tracking scheme. The proposed tracker is evaluated on challenging videos selected from three standard datasets, i.e., OTB-50, OTB-100, and TC-128. A comparison of the proposed tracking scheme with other state-of-the-art methods is also presented in this paper. Our method improved considerably by achieving a center location error of 16.06, distance precision of 0.889, and overlap success rate of 0.824.

Visual tracking is one of the most important components in numerous applications of computer vision. Although correlation filter based trackers gained popularity due to their efficiency, there is a need to improve the overall tracking capability. In this paper, a tracking algorithm based on the kernelized correlation filter (KCF) is proposed. First, fused features including HOG, color-naming, and HSV are employed to boost the tracking performance. Second, to tackle the fixed template size, a scale adaptive scheme is proposed which strengthens the tracking precision. Third, an adaptive learning rate and an occlusion detection mechanism are presented to update the target appearance model in presence of occlusion problem. Extensive evaluation on the OTB-2013 dataset demonstrates that the proposed tracker outperforms the state-of-the-art trackers significantly. The results show that our tracker gets a 14.79% improvement in success rate and a 7.43% improvement in precision rate compared to the original KCF tracker, and our tracker is robust to illumination variations, scale variations, occlusion, and other complex scenes.

Aiming at the problem of severe accuracy degradation in the traditional KCF (Kernel correlation filter) target tracking algorithm in a complex environment, we propose an improved kernel correlation filter target tracking algorithm. First, the target scale is estimated by fusing the scale filter in the DSST (Discriminative Scale Space Tracking) algorithm to solve the traditional KCF algorithm cannot estimate the scale. Secondly, So as to solve the KCF algorithm's limited ability to express the features of the target appearance model, by fusing HOG (Histogram of Oriented Gradient) features and CN (Color Name) features, the algorithm's ability to extract target features is enhanced. Finally, by introducing peak response fluctuation detection, the credibility of the tracking target is judged, so as to decide whether to update the filter model. The experiment tested the overall tracking performance of the improved KCF algorithm by using the video sequences in the OTB2013 and OTB2015 standard data sets. The experimental results show that the accuracy and performance of the improved algorithm in complex environments have been significantly improved.

In order to solve the problems of motion blur and fast motion, a new robust object tracking algorithm using the Kernelized Correlation Filters (KCF) and the Mean Shift (MS) algorithm, called KCFMS is presented in this paper. The object tracking process can be described as: First, we give the initial position and size of the object and use the Mean Shift algorithm to obtain the position of the object. Second, the Kernelized Correlation Filtering algorithm is used to obtain the position of the object in the same frame. Third, we use the cross update strategy to update the object models. In order to improve the tracking speed as much as possible, our object tracking algorithm works only over one layer. This hybrid algorithm has a good tracking effect on the target fast motion and motion blur. We present extensive experimental results on a number of challenging sequences in terms of efficiency, accuracy and robustness.

The target tracking technology in the UAV autonomous landing process is studied. Based on the analysis of the occlusion, background change, and variable scale problems in the target tracking process, a scale adaptive method for UAV target tracking based on KCF (Kernelized Correlation Filter) algorithm is proposed. The original KCF target tracking framework is adopted to achieve the target position prediction function. Secondly, to address the variable scale problem of moving targets and the target loss problem caused by scale changes, the scale filter of the DSST target tracking algorithm is used. The algorithm is for estimating the scale of moving targets and generating a small-scale filter estimate to improve the tracking efficiency of the UAV for moving targets and reduce the target loss rate. The final test on the OTB dataset showed a 4% improvement in variable scale accuracy and a 2.9% improvement in variable scale success rate. A Gazebo 3D environment scene was set up under the Linux system, and UAV autonomous landing simulation experiments were conducted to verify the improved algorithm’s real-time effectiveness in the UAV autonomous landing application. The simulation results show that the improved KCF target tracking algorithm has real-time performance in the UAV autonomous landing trajectory tracking process.

Aiming at the problem of UAV autonomous object tracking under the condition of limited computing resources, this paper combines the high-speed Kernel Correlation Filter (KCF) tracking algorithm with UAV motion control to construct a vision-based UAV autonomous object tracking system. Firstly, the RGB data is captured through the UAV on-board camera and transmitted to the control terminal; After calibrating the initial frame of the tracked object, the control terminal uses KCF algorithm to predict the position of the tracked object at the subsequent time; Then, the relative position of the UAV to the object is estimated based on the visual tracking results; Finally, the relative position of the UAV and the object is used to calculate the movement control amount of the UAV. The experimental results show that the vision-based UAV autonomous object tracking system constructed in this paper can achieve fast and robust UAV autonomous object tracking and relative position maintenance with CPU support and low memory usage.

Robust regularized extreme learning machine for regression using iteratively reweighted least squares

In recent years, online building an adaptive target appearance model has been investigated for robust visual tracking in a dynamic environment. However one inherent problem of adaptive appearance trackers is drift, a gradual adaptation of the tracker to non-targets. To alleviate this problem, we consider visual tracking in a novel online manifold regularization (Online-MR) setting where labeled and unlabeled data arrive sequentially in large volume for tracker update. A discriminative target appearance model based on Haar wavelet is learned at each frame and its output score is used as the input sample feature for Online-MR tracker learning. Such a combination of Online-MR semi-supervised learning and online appearance model adaptation results in a robust tracking scheme that can prevent the tracker from drifting while retain its adaptation to appearance changing. Experimental results demonstrate the effectiveness of the proposed method from comparisons with adaptive appearance model based trackers on several challenging video sequences.

Object tracking in video sequences has broad applications in both military and civilian domains. However, as the length of input video sequence increases, a number of problems arise, such as severe object occlusion, object appearance variation, and object out-of-view (some portion or the entire object leaves the image space). To deal with these problems and identify the object being tracked from cluttered background, we present a robust appearance model using Speeded Up Robust Features (SURF) and advanced integrated features consisting of the Felzenszwalb's Histogram of Oriented Gradients (FHOG) and color attributes. Since re-detection is essential in long-term tracking, we develop an effective object re-detection strategy based on moving area detection. We employ the popular kernel correlation filters in our algorithm design, which facilitates high-speed object tracking. Our evaluation using the CVPR2013 Object Tracking Benchmark (OTB2013) dataset illustrates that the proposed algorithm outperforms reference state-of-the-art trackers in various challenging scenarios.

Visual tracking is an important area in computer vision. How to deal with illumination and occlusion problems is a challenging issue. This paper presents a novel and efficient tracking algorithm to handle such problems. On one hand, a target’s initial appearance always has clear contour, which is light-invariant and robust to illumination change. On the other hand, features play an important role in tracking, among which convolutional features have shown favorable performance. Therefore, we adopt convolved contour features to represent the target appearance. Generally speaking, first-order derivative edge gradient operators are efficient in detecting contours by convolving them with images. Especially, the Prewitt operator is more sensitive to horizontal and vertical edges, while the Sobel operator is more sensitive to diagonal edges. Inherently, Prewitt and Sobel are complementary with each other. Technically speaking, this paper designs two groups of Prewitt and Sobel edge detectors to extract a set of complete convolutional features, which include horizontal, vertical and diagonal edges features. In the first frame, contour features are extracted from the target to construct the initial appearance model. After the analysis of experimental image with these contour features, it can be found that the bright parts often provide more useful information to describe target characteristics. Therefore, we propose a method to compare the similarity between candidate sample and our trained model only using bright pixels, which makes our tracker able to deal with partial occlusion problem. After getting the new target, in order to adapt appearance change, we propose a corresponding online strategy to incrementally update our model. Experiments show that convolutional features extracted by well-integrated Prewitt and Sobel edge detectors can be efficient enough to learn robust appearance model. Numerous experimental results on nine challenging sequences show that our proposed approach is very effective and robust in comparison with the state-of-the-art trackers.

Video target tracking is a critical problem in the field of computer vision. Particle filters have been proven to be very useful in target tracking for nonlinear and non-Gaussian estimation problems. Although most existing algorithms are able to track targets well in controlled environments, it is often difficult to achieve automated and robust tracking of pedestrians in video sequences if there are various changes in target appearance or surrounding illumination. To surmount these difficulties, this paper presents multitarget tracking of pedestrians in video sequences based on particle filters. In order to improve the efficiency and accuracy of the detection, the algorithm firstly obtains target regions in training frames by combining the methods of background subtraction and Histogram of Oriented Gradient (HOG) and then establishes discriminative appearance model by generating patches and constructing codebooks using superpixel and Local Binary Pattern (LBP) features in those target regions. During the process of tracking, the algorithm uses the similarity between candidates and codebooks as observation likelihood function and processes severe occlusion condition to prevent drift and loss phenomenon caused by target occlusion. Experimental results demonstrate that our algorithm improves the tracking performance in complicated real scenarios.

In previous research, most Multi-object tracking (MOT) algorithms focus on the optical image dataset, while the Synthetic Aperture Radar (SAR) image dataset faces the characteristics of few prior samples, high false alarm rate, and various defocusing interference. On the SAR image dataset, a robust MOT algorithm is proposed to fulfill multi-ship tracking in complex imaging conditions. First, the kernelized correlation filters (KCF) algorithm, a single-object tracking algorithm, is modified and applied to reduce the impact of false alarms on tracking performance. After that, different matching strategies are adaptively adapted to associate the targets based on the three intersection patterns between the predictions and the detections, which can reduce the impact of the deviated detections. Finally, the tracker’s time limit with Gaussian distribution is proposed to improve the re-association ability after the tracking interruption caused by the defocusing. The experiment results demonstrate the robust tracking ability of the proposed MOT algorithm.

Objective. Accurate target localization is essential for effective radiation therapy, yet respiratory motion introduces considerable uncertainty. Ultrasound-based motion tracking offers a non-invasive solution, but the presence of similar anatomical structures and significant changes in appearance severely hinders robust and accurate tracking. Robust tracking is essential to ensure accuracy and improve treatment outcomes.Approach. We propose SiamAT, a tracking framework comprising a Siamese-like feature extraction network with a Swin-Transformer backbone, an attention-based target-aware module, and multi-task prediction heads. The target-aware module adaptively integrate template and search features to generate target-aware representations for precise localization.Main results. The proposed SiamAT is evaluated on a public dataset, i.e. MICCAI 2015 challenge on liver US tracking, and our clinical dataset provided by the Chinese People's Liberation Army General Hospital. Experimental results demonstrate that the method achieves accurate and robust tracking(0.60±0.30 mm and 0.47±0.31 mm tacking errors in two datasets) and outperforms existing methods. The proposed method runs at approximatively 36 fps on GPU.Significance. The proposed SiamAT provides clinicians with an effective tool for analyzing 2D motion in US images in clinical settings, assisting in the planning of optimal treatment strategies while reducing diagnostic and therapeutic risks.