Search

Target tracking via Correlation Filter (CF) is a hot research area of computer vision domain, and offers various credible benefits. Existing CF algorithms face challenges when there are target appearance variations due to background noise, scale and illumination changes, occlusion, and fast motion, which severely degrades the overall tracker performance. To get maximum benefits, an object tracker should perform well with the less computational burden in the presence of real time challenging situations. To address this issue, a novel visual object tracker is proposed based on multi feature fusion and adaptive learning technique with aberrance suppression. At first, multiple features i.e., Histogram of gradient (HOG), Color Naming (CN), saliency, and gray level intensities are combined using feature fusion technique. Further, based on the evaluation of final fused response map using Peak-to-Sidelobe Ratio (PSR), an adaptive learning strategy is integrated to improve the learning phase of tracker. Tracking results show that the proposed strategy beats the other modern CF trackers with Distance Precision (DP) scores of 88.2%, 85.9%, and 74.1% and 64.7% over OTB2013, OTB2015, and TempleColor128 and UAV123 datasets respectively. [ABSTRACT FROM AUTHOR]

Object tracking is a challenging task which is required for different problems such as surveillance, traffic analysis and human-computer interaction. The problem of tracking an object can be considered in different categories such as single object tracking, multiple object tracking, short-term tracking, long-term tracking, tracking by detection and detection-free tracking. This study focuses on detection-free tracking for ground targets on aerial images. The studies in the literature show that correlation filter and deep learning based object trackers perform well recently. This paper proposes a new correlation filter-based tracker containing a strategy for re-detection issue. We improve the performance of correlation filter-based tracker by adding a lightweight re-detection ability to the correlation filter tracker in case of a long occlusion or complete loss of target. We use deep features to train Discriminative Correlation Filter(DCF) by integrating sub-networks from pre-trained ResNet and SAND models. The experimental results on the popular UAV123L dataset show that the proposed method(MADCF) improves the performance of DCF tracker and have a reasonable performance for long-term tracking problem. Moreover, we prepare a new tracking dataset (PESMOD tracking) consisting of UAV images, and we evaluate the proposed method and state-of-the-art method in this dataset. We observed that the proposed method performs much better in ground target tracking from VIVID and PESMOD aerial datasets. The proposed MADCF tracker performs better for small targets tracked by UAVs compared to the deep learning-based trackers. The source code and prepared dataset are available at http://github.com/mribrahim/MADCF [ABSTRACT FROM AUTHOR]

Objectives: Object tracking is a research focus in the field of computer vision. The method based on correlation filters performs well in object tracking, but artificial feature description of images has certain limitations in the process of feature extraction. Convolutional neural network (CNN) has been widely used in computer vision, natural language processing and other fields, and they can tune the weights of network parameters by learning training samples to extract depth features of images. In order to obtain more robust feature expression of images, CNN is used to extract the features of images in object tracking. Methods: Combining CNN with correlation filters, we propose an object tracking method based on multi-stage features and asymmetric-dilated convolution. The ResNet50 network embedded with asymmetric-dilated convolution block is used as the network of feature extraction and it can respectively output the feature maps from multiple stages of the network for correlation filters to achieve object detection and localization. Results: The proposed method is tested on OTB100 video dataset. The distance precision can reach 85.38% if the distance threshold is set as 20 pixels, and the overlap precision can reach 80.42% if the overlap threshold is set as 50%. Conclusions: The experimental results verify the accuracy of the proposed method which is relatively robust under certain conditions such as complexity background, occlusion and rotational deformation. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The correlation filter object tracking algorithm has gained extensive attention from scholars in the field of tracking because of its excellent tracking performance and efficiency. However, the mathematical modeling relationships of correlation filter tracking frameworks are unclear. Therefore, many forms of correlation filters are susceptible to confusion and misuse. To solve these problems, we attempted to review various forms of the correlation filter and discussed their intrinsic connections. First, we reviewed the basic definitions of the circulant matrix, convolution, and correlation operations. Then, the relationship among the three operations was discussed. Considering this, four mathematical modeling forms of correlation filter object tracking from the literature were listed, and the equivalence of the four modeling forms was theoretically proven. Then, the fast solution of the correlation filter was discussed from the perspective of the diagonalization property of the circulant matrix and the convolution theorem. In addition, we delved into the difference between the one-dimensional and two-dimensional correlation filter responses as well as the reasons for their generation. Numerical experiments were conducted to verify the proposed perspectives. The results showed that the filters calculated based on the diagonalization property and the convolution property of the cyclic matrix were completely equivalent. The experimental code of this paper is available at https://github.com/110500617/Correlation-filter/tree/main.

Visual object tracking is a fundamental problem in computer vision. It has been widely used in civilian and military fields, such as battlefield reconnaissance, video surveillance, automatic driving, video analysis, and many other areas. In recent years, although the object tracking algorithm has made great progress, stable object tracking is still a challenging task due to random target changes and complex scenarios. Firstly, the difficulties and challenges in actual tracking scenarios are introduced in this paper. Then, aiming at the background clutter, rotation changes, occlusion, and scale changes, the representative discriminative object tracking algorithms are summarized and analyzed from the perspective of feature extraction, observation model, and model update mechanism. Subsequently, 25 typical tracking algorithms are evaluated and analyzed on OTB2015 database. Finally, the further research directions are prospected.

Due to their great balance between excellent performance and high efficiency, discriminative correlation filter (DCF) tracking methods for unmanned aerial vehicles (UAVs) have gained much attention. Due to these correlations being capable of being efficiently computed in a Fourier domain by discrete Fourier transform (DFT), the DFT of an image has symmetry in the Fourier domain. However, DCF tracking methods easily generate unwanted boundary effects where the tracking object suffers from challenging situations, such as deformation, fast motion and occlusion. To tackle the above issue, this work proposes a novel saliency-aware and spatial–temporal regularized correlation filter (SSTCF) model for visual object tracking. First, the introduced spatial–temporal regularization helps build a more robust correlation filter (CF) and improve the temporal continuity and consistency of the model to effectively lower boundary effects and enhance tracking performance. In addition, the relevant objective function can be optimized into three closed-form subproblems which can be addressed by using the alternating direction method of multipliers (ADMM) competently. Furthermore, utilizing a saliency detection method to acquire a saliency-aware weight enables the tracker to adjust to variations in appearance and mitigate disturbances from the surroundings environment. Finally, we conducted numerous experiments based on three different benchmarks, and the results showed that our proposed model had better performance and higher efficiency compared to the most advanced trackers. For example, the distance precision (DP) score was 0.883, and the area under the curve (AUC) score was 0.676 on the OTB2015 dataset. [ABSTRACT FROM AUTHOR]

Correlation filter tracking algorithms have garnered significant attention due to their efficiency and outstanding tracking performance. However, these methods face several limitations. Firstly, they rely on periodic boundary conditions, leading to boundary effects. Secondly, most traditional methods only extract hand-crafted features from the image. Nevertheless, these features are insufficient to discriminate in complex scenes. Thirdly, they assume that the maximum position of the correlation response represents the object without further evaluating its reliability. These limitations make it very easy to lose the object in occluded scenes. A background-aware correlation filter algorithm based on an anti-occlusion mechanism and deep features is proposed to solve the above limitations. Primarily, the video frames to be processed are cyclically shifted to crop the cyclically shifted samples in a small window. This operation significantly reduces boundary effects while obtaining background samples from the real world. Then, deep features are extracted through deep neural networks. Subsequently, we propose a background perception tracking framework that synchronously estimates position and scale based on these features. This framework aims to determine the optimal candidate sample position and scale. Finally, an anti-occlusion mechanism is constructed to evaluate the optimal candidate samples obtained in each frame further. This mechanism fully exploits the diversity of objects and effectively solves the tracking drift and failure issues caused by occlusion, fast motion, and so on. Extensive experiments are conducted on the object tracking benchmark (OTB) dataset and compared with industry-leading tracking algorithms to validate the effectiveness of the proposed method. The results show that the method has robust tracking performance. [ABSTRACT FROM AUTHOR]

The correlation filter object tracking algorithm has gained extensive attention from scholars in the field of tracking because of its excellent tracking performance and efficiency. However, the mathematical modeling relationships of correlation filter tracking frameworks are unclear. Therefore, many forms of correlation filters are susceptible to confusion and misuse. To solve these problems, we attempted to review various forms of the correlation filter and discussed their intrinsic connections. First, we reviewed the basic definitions of the circulant matrix, convolution, and correlation operations. Then, the relationship among the three operations was discussed. Considering this, four mathematical modeling forms of correlation filter object tracking from the literature were listed, and the equivalence of the four modeling forms was theoretically proven. Then, the fast solution of the correlation filter was discussed from the perspective of the diagonalization property of the circulant matrix and the convolution theorem. In addition, we delved into the difference between the one-dimensional and two-dimensional correlation filter responses as well as the reasons for their generation. Numerical experiments were conducted to verify the proposed perspectives. The results showed that the filters calculated based on the diagonalization property and the convolution property of the cyclic matrix were completely equivalent. The experimental code of this paper is available at https://github.com/110500617/Correlation-filter/tree/main. [ABSTRACT FROM AUTHOR]

Understanding the factors that impact students' achievements and failures in higher education is crucial as it enables the development of targeted interventions and support mechanisms that can enhance academic performance and foster student success. Artificial intelligence (AI) can help understand the factors that influence students' academic achievements and failures in higher education by analyzing large volumes of data, identifying patterns and correlations, and providing valuable insights. This article presents the application of eight classification models on a "Dataset of Academic Performance Evaluation of Higher Education Students" consisting of 145 higher education students. The aim is to identify the best classification algorithm for predicting academic performance. The correlation filter (CF) was used for the discovery and selection of relevant attributes, resulting in the choice of four attributes for analysis. The best classification models were random forest, support vector machine, and decision tree, with an average accuracy of 94.37% and a CF of 0.1. These results demonstrate that the application of AI and machine learning techniques is important for decisionmaking in higher education, allowing for a better understanding of the factors that influence academic success or failure. The study emphasizes the importance of careful attribute selection and the use of appropriate classification algorithms to ensure accuracy and reliability of the results. Additionally, the study was replicated and evaluated with nine Brazilian higher education students, achieving an accuracy of 88.89%. These results demonstrate the consistency and relevance of the proposed attribute filtering model. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicles (UAVs)-based visual object tracking has drawn significant attention recently and is extensively used in military applications, aviation, security, and agriculture, to name a few. Discriminative Correlation Filter (DCF)-based trackers have gained significant recognition in UAV-based visual tracking due to their efficiency and tracking speed. However, the training samples generated by cyclic shifts in the correlation filter are not real samples. In many cases, these approximate samples differ significantly from actual samples. Due to this, the traditional correlation filter-based trackers have inherent boundary effects and filter degradation issues. The traditional assumption of a single-centred Gaussian target response may not be reliable in challenging situations such as fast motion or occlusion. Such unreliable training samples lead to tracker drift. This paper proposes a novel Adaptive Target Spatio-Temporal Regularized Correlation Filter (ATCF) tracker to rectify these issues. A simple yet effective energy function is developed by combining the adaptive spatio-temporal regularized correlation filter and the adaptive target response. The closed-form solution is obtained using the Alternating Direction Multiplier Method (ADMM). The target response and spatio-temporal regularization parameters are learned online. Besides, a novel detection-based re-tracking strategy is introduced to improve long-term tracking performance. The proposed tracker's performance on four benchmark datasets, i.e. DTB70, UAV123@10fps, UAV20L, and UAVDT benchmarks, has proved its superiority over various state-of-the-art trackers in terms of accuracy and robustness while running in real time in a CPU environment. [ABSTRACT FROM AUTHOR]

Copyright of Aero Weaponry is the property of Aero Weaponry Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Xi'an Jiaotong University is the property of Editorial Office of Journal of Xi'an Jiaotong University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Short-Term Single-Object (STSO) tracking using Hyperspectral Videos (HSVs), which has become a hotspot recently, is a challenging task. Hyperspectral Object Tracking (HOT) makes full use of spatial and spectral information during the tracking process. In HOT, multiple features, including deep network features, have been combined with correlation filter methods, which increases time-consuming efficiency and tracking accuracy. However, redundant spectral information needs to be obtained in an effective way. In addition, there is currently no detailed investigation of HOT algorithms. Therefore, this survey studies the development of HOT algorithms in recent years. Specifically, several HSVs are listed, an investigation of HOT algorithms is conducted, and components of HOT are described in detail. Furthermore, several popular HOT algorithms, including our previous work BS-SiamPRN and AD-SiamRPN, are compared quantitatively and qualitatively. Finally, the research status of HOT is summarized, and future work has been described, which lays the foundation for future HOT or STSO referring to HSVs. [ABSTRACT FROM AUTHOR]

CNN (convolutional neural network) based real time trackers usually do not carry out online network update in order to maintain rapid tracking speed. This inevitably influences the adaptability to changes in object appearance. Correlation filter based trackers can update the model parameters online in real time. In this paper, we present an end-to-end lightweight network architecture, namely Discriminant Correlation Filter Network (DCFNet). A differentiable DCF (discriminant correlation filter) layer is incorporated into a Siamese network architecture in order to learn the convolutional features and the correlation filter simultaneously. The correlation filter can be efficiently updated online. In previous work, we introduced a joint scale-position space to the DCFNet, forming a scale DCFNet which carries out the predictions of object scale and position simultaneously. We combine the scale DCFNet with the convolutional-deconvolutional network, learning both the high-level embedding space representations and the low-level fine-grained representations for images. The adaptability of the fine-grained correlation analysis and the generalization capability of the semantic embedding are complementary for visual tracking. The back-propagation is derived in the Fourier frequency domain throughout the entire work, preserving the efficiency of the DCF. Extensive evaluations on the OTB (Object Tracking Benchmark) and VOT (Visual Object Tracking Challenge) datasets demonstrate that the proposed trackers have fast speeds, while maintaining tracking accuracy. [ABSTRACT FROM AUTHOR]

Object tracking in satellite videos has garnered significant attention due to its increasing importance. However, several challenging attributes, such as the presence of tiny objects, occlusions, similar objects, and background clutter interference, make it a difficult task. Many recent tracking algorithms have been developed to tackle these challenges in tracking a single interested object, but they still have some limitations in addressing them effectively. This paper introduces a novel correlation filter-based tracker, which uniquely integrates attention-enhanced bounding box regression and motion constraints for improved single-object tracking performance. Initially, we address the regression-related interference issue by implementing a spatial and channel dual-attention mechanism within the search area's region of interest. This enhancement not only boosts the network's perception of the target but also improves corner localization. Furthermore, recognizing the limitations in small size and low resolution of target appearance features in satellite videos, we integrate motion features into our model. A long short-term memory (LSTM) network is utilized to create a motion model that can adaptively learn and predict the target's future trajectory based on its historical movement patterns. To further refine tracking accuracy, especially in complex environments, an anti-drift module incorporating motion constraints is introduced. This module significantly boosts the tracker's robustness. Experimental evaluations on the SatSOT and SatVideoDT datasets demonstrate that our proposed tracker exhibits significant advantages in satellite video scenes compared to other recent trackers for common scenes or satellite scenes. [ABSTRACT FROM AUTHOR]

Single object tracking (SOT) in satellite video (SV) enables the continuous acquisition of position and range information of an arbitrary object, showing promising value in remote sensing applications. However, existing trackers and datasets rarely focus on the SOT of oriented objects in SV. To bridge this gap, this article presents a comprehensive review of various tracking paradigms and frameworks covering both the general video and satellite video domains and subsequently proposes the oriented object tracking benchmark (OOTB) to advance the field of visual tracking. OOTB contains 29,890 frames from 110 video sequences, covering common satellite video object categories including car, ship, plane, and train. All frames are manually annotated with oriented bounding boxes, and each sequence is labeled with 12 fine-grained attributes. Additionally, a high-precision evaluation protocol is proposed for comprehensive and fair comparisons of trackers. To validate the existing trackers and explore frameworks suitable for SV tracking, we benchmark 33 state-of-the-art trackers totaling 58 models with different features, backbones, and tracker tags. Finally, extensive experiments and insightful thoughts are also provided to help understand their performance and offer baseline results for future research. OOTB is available at https://github.com/YZCU/OOTB. [ABSTRACT FROM AUTHOR]

Due to its quick tracking, simple deployment, and straightforward principle, correlation filter-based tracking methods continue to have significant research implications. In order to make full use of different features while balancing the tracking speed and performance, the adaptive cascaded and parallel feature fusion-based tracker (ACPF), which could estimate the position, rotation and scale, respectively, is proposed. Comparing with other correlation filter-based trackers, the ACPF could fuse deep and handcrafted features in both Log-Polar and Cartesian branch and update templates according to the weights of response maps adaptively. Adaptive linear weights (ALW) are proposed to fuse feature response maps adaptively in the Log-Polar coordinates branch to improve the estimation of scale and rotation of object by solving constrained optimization problems. Response maps of shallow and deep features are merged adaptively by cascading numerous ALW modules in the Cartesian branch to make better utilize shallow and deep feature, and increase tracking accuracy. The final results are computed simultaneously by Cartesian and Log-Polar branch in parallel. Additionally, the learning rates are automatically changed in accordance with the weights of the ALW module to execute the adaptive template update. Extensive experiments on benchmarks show that the proposed tracker achieves the comparable results, especially in dealing with the challenges of deformation, rotation and scale variation. [ABSTRACT FROM AUTHOR]

As a tool for near-earth remote sensing, unmanned aerial vehicle (UAV) can be used to acquire images and data of the earth's surface. This provides a powerful support for Earth observation and resource management. Object tracking in UAV videos has been a topic of much interest in recent years. A large number of algorithms have been proposed. Among these algorithms, deep learning has achieved a high accuracy rate. However, it is difficult to carry hardware devices for UAV, which makes it difficult to be practically applied. The correlation filter does not require a graphic processing unit to accelerate the computation, but it uses only manual features, which makes it difficult to achieve satisfactory performance. In order to solve the above problems, we proposed adaptive spatial regularization correlation filters, called DTSRT. Specifically, we first introduce deep features in the correlation filter instead of the original manual features, which can greatly improve the discriminative ability of the model. At the same time, in order to prevent affecting the real-time performance of the algorithm, we use histogram of oriented gradients features to determine the target scale and deep features to determine the target location. In addition, considering the large inter-frame distance between targets in UAV videos, we use a saliency detection method to dynamically generate spatially constrained templates. The proposed DTSRT outperforms other state-of-the-art algorithms with area under curve of 0.481, 0.431, and 0.474 on UAV123@10FPS, UAVDT, and DTB70 datasets, respectively.

Tracking small objects in infrared videos is challenging due to a complex background, weak information and target mobility. To deal with these difficulties, an infrared small target tracking algorithm is proposed, which utilizes the Spatial-Temporal Regularized Correlation Filter (STRCF) as the backbone. First, the local image patch that refers to the target and its neighborhood background is given in the STRCF. Then, the guided local contrast mechanism is designed to eliminate noise and distinguish the target from the background. Furthermore, the robustness of the tracking is improved by using the detection model with an adaptive factor of search range, helping to alleviate the problem of tracking migration. Experimental results on entire public near-infrared videos show the superior performance of the proposed algorithm (named STRCFD), compared to several related algorithms in visual effects and objective evaluation. It should be mentioned that the proposed STRCFD achieves an overall precision of 81.1%.

Optical remote sensing videos, as a new source of remote sensing data that has emerged in recent years, have significant potential in remote sensing applications, especially national defense. In this paper, a tracking pipeline named TDNet (tracking while detecting based on a neural network) is proposed for optical remote sensing videos based on a correlation filter and deep neural networks. The pipeline is used to simultaneously track ships and planes in videos. There are many target tracking methods for general video data, but they suffer some difficulties in remote sensing videos with low resolution and those influenced by weather conditions. The tracked targets are usually misty. Therefore, in TDNet, we propose a new multi-target tracking method called MT-KCF and a detecting-assisted tracking (i.e., DAT) module to improve tracking accuracy and precision. Meanwhile, we also design a new target recognition (i.e., NTR) module to recognise newly emerged targets. In order to verify the performance of TDNet, we compare our method with several state-of-the-art tracking methods on optical video remote sensing data sets acquired from the Jilin No. 1 satellite. The experimental results demonstrate the effectiveness and the state-of-the-art performance of the proposed method. The proposed method can achieve more than 90% performance in terms of precision for single-target tracking tasks and more than 85% performance in terms of MOTA for multi-object tracking tasks. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Test & Measurement Technology is the property of Publishing Center of North University of China and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The field of real-time mobile object tracking is a crucial aspect of computer vision. Despite numerous algorithms proposed for efficient tracking, the high computational complexity presents challenges in achieving real-time performance. This paper presents a novel approach by introducing an adaptive search region proposal block that works in tandem with Mean-Shift and Unscented Kalman Filter. The block efficiently searches the region of the estimated object location. The dynamic changes in the appearance and size of a moving target make tracking difficult, but the proposed Multi-scale Template Matching technique addresses this challenge by utilizing the Normalized Cross-Correlation method in the adaptive search region. This optimization results in a reduced computational complexity and an increased frame rate of 53.4 FPS. Comparisons with various state-of-the-art trackers show that the proposed algorithm achieves the best results in terms of precision, success rate, and object tracking error. [ABSTRACT FROM AUTHOR]

In recent years, the multi-expert collaborative tracking strategy has been introduced into visual tracking tasks and achieves impressive performance. Different from most existing multi-expert trackers that linearly fuse multiple tracking models, we propose a novel cascaded-parallel tracking algorithm (CPT) via adaptively selecting the suitable expert among multiple tracking models. And the CPT consists of cascaded and parallel tracking components. In the cascaded tracking component, we hierarchically implement two effective correlation filter models to coarse-to-fine locate the target. And in the parallel tracking component, a color tracking model is applied to locate the target to compensate for the demerit of the correlation filter models. With the proposed adaptive expert selection mechanism, the most reliable expert (i.e. tracking model) is selected for tracking in each frame. Extensive experimental results on OTB2013, OTB2015 and TempleColor128 datasets demonstrate that our proposed algorithm performs favorably against some state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Unmanned Aerial Vehicle (UAV) tracking has been possible because of the growth of intelligent information technology in smart cities, making it simple to gather data at any time by dynamicallymonitoring events, people, the environment, and other aspects in the city. The traditional filter creates amodel to address the boundary effect and time filter degradation issues in UAV tracking operations. But these methods ignore the loss of data integrity terms since they are overly dependent on numerous explicit previous regularization terms. In light of the aforementioned issues, this work suggests a dual-domain Jensen-Shannon divergence correlation filter (DJSCF) model address the probability-based distance measuring issue in the event of filter degradation. The two-domain weighting matrix and JS divergence constraint are combined to lessen the impact of sample imbalance and distortion. Two new tracking models that are based on the perspectives of the actual probability filter distribution and observation probability filter distribution are proposed to translate the statistical distance in the online tracking model into response fitting. The model is roughly transformed into a linear equality constraint issue in the iterative solution, which is then solved by the alternate direction multiplier method (ADMM). The usefulness and superiority of the suggested strategy have been shown by a vast number of experimental findings. [ABSTRACT FROM AUTHOR]

A distortion-aware correlation filter object tracking algorithm is proposed to address the problem that the existing correlation filters have insufficient ability to deal with target distortion and the filter model updating error accumulation easily leads to tracking failure. Firstly, particle sampling is used to construct a spatial reference weight for enhancing the target information and adapt to changes in the target appearance between adjacent frames so that the filter is focused on the reliable part of the learning target and the interference of background information is suppressed. Meanwhile, to optimize the algorithm and reduce computational complexity, the alternating direction multiplier method is used to solve the objective optimal function value with fewer iterations. Finally, to further enhance the discrimination ability of the filter, a target distortion-aware strategy is designed, which combines the average peak correlation energy and the response map peak temporal constrain to measure the distortion of the target affected by interference factors and to determine whether the current tracking result is reliable. When the reliability of target tracking and positioning is low, the particle filter is used to selectively re-detect the target. Depending on the extent of distortion of the tracking target at any given time, the filter model is adaptively updated. Compared with various representative correlation filters on the OTB50, OTB100, and DTB70 datasets, the experimental results show that the tracking success rate and precision of the distortion-aware correlation filter object tracking algorithm are the best, and it has strong robustness in the face of targets distorted by multiple interference factors in the actual scene.

Due to their great balance between excellent performance and high efficiency, discriminative correlation filter (DCF) tracking methods for unmanned aerial vehicles (UAVs) have gained much attention. Due to these correlations being capable of being efficiently computed in a Fourier domain by discrete Fourier transform (DFT), the DFT of an image has symmetry in the Fourier domain. However, DCF tracking methods easily generate unwanted boundary effects where the tracking object suffers from challenging situations, such as deformation, fast motion and occlusion. To tackle the above issue, this work proposes a novel saliency-aware and spatial–temporal regularized correlation filter (SSTCF) model for visual object tracking. First, the introduced spatial–temporal regularization helps build a more robust correlation filter (CF) and improve the temporal continuity and consistency of the model to effectively lower boundary effects and enhance tracking performance. In addition, the relevant objective function can be optimized into three closed-form subproblems which can be addressed by using the alternating direction method of multipliers (ADMM) competently. Furthermore, utilizing a saliency detection method to acquire a saliency-aware weight enables the tracker to adjust to variations in appearance and mitigate disturbances from the surroundings environment. Finally, we conducted numerous experiments based on three different benchmarks, and the results showed that our proposed model had better performance and higher efficiency compared to the most advanced trackers. For example, the distance precision (DP) score was 0.883, and the area under the curve (AUC) score was 0.676 on the OTB2015 dataset.

In order to solve the problem that target is easy to lose in complex scenes such as similar background, occlusion, fast motion and motion blur, a new manifold background-aware correlation filter tracking algorithm is proposed. Firstly, the object tracking region is selected to extract the appearance features of target to establish object model. Then, taking target location as the origin, the manifold search area is constructed by using double expo-nential distribution. According to the target motion speed and direction, the manifold search range and search angle are dynamically adjusted. The background in the manifold search area is extracted, and the filter template is obtained by training the background information and the target feature model. Finally, the filter template is used to determine the target position and track the target. According to the speed and direction of the target motion, the manifold background-aware algorithm proposed adopts dynamic search mechanism to search, which covers the prob-ability space range of the target random motion. It can effectively search targets in complex scenarios, control calculation quantity, and improve the accuracy and speed of the target tracking algorithm. A great quantity of experiments are carried out on the standard dataset OTB100. Experimental results indicate that the proposed algorithm has good performance in accuracy, real time and robustness for target tracking under complex conditions such as similar background, occlusion, fast motion and motion blur in comparison with other mainstream algorithms.

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The extended maximum average correlation height (EMACH) filter is a potent pattern-detection tool used in image processing and computer vision applications. This filter enhances the effectiveness of the maximum average correlation height (MACH) filter by adding more features and flexibility. Incorporating the benefits of wavelet decomposition, we updated the EMACH filter to enhance its performance. The updated filter offered improved accuracy, robustness, and flexibility in recognizing complex patterns and objects in images with varying lighting conditions, noise levels, and occlusions. To verify the results' consistency and compare their performance with that of the MACH filter and EMACH filter, performance metrics like peak-to-correlation energy, peak-to-sidelobe ratio, signal-to-noise ratio, and discrimination ratio were computed. Through numerical and experimental studies, we found that the proposed filter enhances the identification rate and decreases the number of false alarms. [ABSTRACT FROM AUTHOR]

Aspects like deformation and occlusion are still the challenge cases which will result in failures of visual tracking. Many existing correlation filters (CFs) try to fuse the color information to improve the performance but ignore the sensitivity of color information to the background interference. For this case, we propose a color-saliency-aware correlation filter which exploits the color statistics as the model of image boundary connectivity cues. The proposed method limits the drift of correlation filter because of the saliency proposal. In addition, the bounding boxes of CFs absorb too much background information which can easily lead to the tracking failure. To solve this problem, we also present a decoupled-Fourier-Mellin (DFM) transform which is related to the independence of scale variations in log-polar coordinates. In addition to the rotation angle, the proposed DFM can also gain the scale factors of both horizontal and vertical directions, and the larger search space (5-DoF) is closer to the upper bound of object masks. Ultimately, multiple popular benchmarks demonstrate the superiority of our tracker. Compared with the current advanced CFs, our method achieves better performance, which is of great significance for continuous tasks requiring high DoF information, such as manipulator visual servo. [ABSTRACT FROM AUTHOR]

Abstract Correlation filter-based trackers have made significant progress in visual object tracking for various types of unmanned aerial vehicle (UAV) applications due to their promising performance and efficiency. However, the boundary effect remains a challenging problem. Several methods enlarge search areas to handle this shortcoming but introduce more background noise, and the filter is prone to learn from distractors. To address this issue, we present spatial regularized correlation filters with response consistency and distractor repression. Specifically, a temporal constraint is introduced to reinforce the consistency across frames by minimizing the difference between consecutive correlation response maps. A dynamic spatial constraint is also integrated by exploiting the local maximum points of the correlation response produced during the detection phase to mitigate the interference from background distractions. The proposed appearance model can optimize the temporal and spatial constraints together with a spatial regularization weight simultaneously. Meanwhile, the proposed appearance model can be solved effectively based on the alternating direction method of multipliers algorithm. The spatial and temporal information concealed in the response maps is fully taken into consideration to boost overall tracking performance. Extensive experiments are conducted on a public UAV benchmark dataset with 123 challenging sequences. The experimental results and analysis demonstrate that the proposed method outperforms 12 state-of-the-art trackers in terms of both accuracy and robustness while efficiently operating in real time.

Object tracking in satellite videos has garnered significant attention due to its increasing importance. However, several challenging attributes, such as the presence of tiny objects, occlusions, similar objects, and background clutter interference, make it a difficult task. Many recent tracking algorithms have been developed to tackle these challenges in tracking a single interested object, but they still have some limitations in addressing them effectively. This paper introduces a novel correlation filter-based tracker, which uniquely integrates attention-enhanced bounding box regression and motion constraints for improved single-object tracking performance. Initially, we address the regression-related interference issue by implementing a spatial and channel dual-attention mechanism within the search area’s region of interest. This enhancement not only boosts the network’s perception of the target but also improves corner localization. Furthermore, recognizing the limitations in small size and low resolution of target appearance features in satellite videos, we integrate motion features into our model. A long short-term memory (LSTM) network is utilized to create a motion model that can adaptively learn and predict the target’s future trajectory based on its historical movement patterns. To further refine tracking accuracy, especially in complex environments, an anti-drift module incorporating motion constraints is introduced. This module significantly boosts the tracker’s robustness. Experimental evaluations on the SatSOT and SatVideoDT datasets demonstrate that our proposed tracker exhibits significant advantages in satellite video scenes compared to other recent trackers for common scenes or satellite scenes.

Aiming at the problem that a single correlation filter model is sensitive to complex scenes such as background interference and occlusion, a tracking algorithm based on multi-time-space perception and instance-specific proposals is proposed to optimize the mathematical model of the correlation filter (CF). Firstly, according to the consistency of the changes between the object frames and the filter frames, the mask matrix is introduced into the objective function of the filter, so as to extract the spatio-temporal information of the object with background awareness. Secondly, the object function of multi-feature fusion is constructed for the object location, which is optimized by the Lagrange method and solved by closed iteration. In the process of filter optimization, the constraints term of time-space perception is designed to enhance the learning ability of the CF to optimize the final tracking results. Finally, when the tracking results fluctuate, the boundary suppression factor is introduced into the instance-specific proposals to reduce the risk of model drift effectively. The accuracy and success rate of the proposed algorithm are verified by simulation analysis on two popular benchmarks, the object tracking benchmark 2015 (OTB2015) and the temple color 128 (TC-128). Extensive experimental results illustrate that the optimized appearance model of the proposed algorithm is effective. The distance precision rate and overlap success rate of the proposed algorithm are 0.756 and 0.656 on the OTB2015 benchmark, which are better than the results of other competing algorithms. The results of this study can solve the problem of real-time object tracking in the real traffic environment and provide a specific reference for the detection of traffic abnormalities. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the object tracking methods based on correlation filter is easily affected by the distractive features in complex scenes such as object deformation and background interference, which leads to the tracking failure, a correlation filter for object tracking method based on sparse representation is proposed. The method combines correlation filter with sparse representation by using L1 norm to sparse constrain the correlation filter in the objective function, so that the trained correlation filter only contains the key features of the object. At the same time, different penalty parameters are assigned to the correlation filter coefficients according to spatial position of the correlation filter coefficients, and the alternating direction method of multipliers (ADMM) is used to solve the correlation filter. The experimental results show that: the method has the best precision and success rate in comparison with five object tracking methods based on correlation filter on three commonly used datasets. At the same time, the method has good robustness to the distractive features in complex scenes, and can meet the real-time requirements. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The purpose of object tracking is to locate a given target in image sequence, such as people and vehicles. In recent years, with the development of unmanned aerial vehicle (UAV) technology, object tracking in UAV videos has engaged many scholars. It has been widely used in traffic control, water quality inspection, wildlife census, and other fields. However, low resolution, scale change, occlusion, and other challenges have been restricting the development of the tracker. To solve the aforementioned problems, we put forward multifeature correlation filters with saliency proposals. First, we use histogram of oriented gradient features, gray (I) features, and color names features to heighten the representation information of the target, so that our algorithm can accurately locate small targets. Then, we introduce saliency proposals to reposition the occluded target. Finally, we use dynamic update weights instead of the fixed update weights to mitigate the adverse effects caused by template degradation. Experiments demonstrate that our tracker has achieved satisfactory tracking accuracy and AUC scores have reached 0.462, 0.417, and 0.425 on UAV123@10FPS, UAV20 L, and UAVDT datasets, respectively.

Increased traffic density, combined with global population development, has resulted in increasingly congested roads, increased air pollution, and increased accidents. Globally, the overall number of automobiles has expanded dramatically during the last decade. Traffic monitoring in this environment is undoubtedly a significant difficulty in various developing countries. This work introduced a novel vehicle detection and classification system for smart traffic monitoring that uses a convolutional neural network (CNN) to segment aerial imagery. These segmented images are examined to further detect the vehicles by incorporating novel customized pyramid pooling. Then, these detected vehicles are classified into various subcategories. Finally, these vehicles are tracked via Kalman filter (KF) and kernelized filter-based techniques to cope with and manage massive traffic flows with minimal human intervention. During the experimental evaluation, our proposed system illustrated a remarkable vehicle detection rate of 95.78% over the Vehicle Aerial Imagery from a Drone (VAID), 95.18% over the Vehicle Detection in Aerial Imagery (VEDAI), and 93.13% over the German Aerospace Center (DLR) DLR3K datasets, respectively. The proposed system has a variety of applications, including identifying vehicles in traffic, sensing traffic congestion on a road, traffic density at intersections, detecting various types of vehicles, and providing a path for pedestrians.