Visual Tracking Method Research Articles

Efficient scale estimation methods using lightweight deep convolutional neural networks for visual tracking

In recent years, visual tracking methods that are based on discriminative correlation filters (DCFs) have been very promising. However, most of these methods suffer from a lack of robust scale estimation skills. Although a wide range of recent DCF-based methods exploit the features that are extracted from deep convolutional neural networks (CNNs) in their translation model, the scale of the visual target is still estimated by hand-crafted features. Whereas the exploitation of CNNs imposes a high computational burden, this paper exploits pre-trained lightweight CNNs models to propose two efficient scale estimation methods, which not only improve the visual tracking performance but also provide acceptable tracking speeds. The proposed methods are formulated based on either holistic or region representation of convolutional feature maps to efficiently integrate into DCF formulations to learn a robust scale model in the frequency domain. Moreover, against the conventional scale estimation methods with iterative feature extraction of different target regions, the proposed methods exploit proposed one-pass feature extraction processes that significantly improve the computational efficiency. Comprehensive experimental results on the OTB-50, OTB-100, TC-128 and VOT-2018 visual tracking datasets demonstrate that the proposed visual tracking methods outperform the state-of-the-art methods, effectively.

Robust Visual Tracking Based on Convolutional Sparse Coding

This paper proposes a new visual tracking method by constructing the robust appearance model of the target with convolutional sparse coding. First, our method uses convolutional sparse coding to divide the interest region of the target into a smooth image and four detail images with different fitting degrees. Second, we compute the initial target region by tracking the smooth image with the kernel correlation filtering. We define an appearance model to describe the details of the target based on the initial target region and the combination of four detail images. Third, we propose a matching method by the overlap rate and Euclidean distance to evaluate candidates and the appearance model to compute the tracking results based on detail images. Finally, the two tracking results are separately computed by the smooth image, and the detail images are combined to produce the final target rectangle. Many experiments on videos from Tracking Benchmark 2015 demonstrate that our method produces much better results than most of the present visual tracking methods.

A rough set fuzzy logic algorithm for visual tracking of blockchain logistics transportation labels

The development of blockchain technology has introduced new elements to the logistics service supply chain, which provides solutions to the related problems in the development at present. In this paper, mainly the relevant contents of blockchain technology are analyzed. At the same time, the composition and application of the logistics service supply chain algorithm based on the blockchain technology are clarified. A fuzzy logic algorithm logistics based on the rough set visual image label tracking method is put forward for container transportation to address the problems in the application process. The overall visual features of the container are taken as the label feature, and the image segmentation transformation method is used to extract the features from the images collected from container logistics transportation, which has provided a basis for the logistics transportation visual tracking. The background is separated based on the key feature frames of the container images collected. The separated features are recorded, and the similarity of the features is used to complete the visual tracking of logistics transportation. The experimental results suggest that the application of the proposed method to the visual tracking of container logistics transportation can improve the accuracy of container tracking.

Multi-Channel Feature Dimension Adaption for Correlation Tracking

Recent discriminative trackers especially based on Correlation Filters (CFs) have shown dominant performance for visual tracking. This kind of trackers benefit from multi-resolution deep features a lot, taking the expressive power of deep Convolutional Neural Networks (CNN). However, distractors in complex scenarios, such as similar targets, occlusion, and deformation, lead to model drift. Meanwhile, learning deep features results in feature redundancy that the increasing number of learning parameters introduces the risk of over-fitting. In this paper, we propose a discriminative CFs based visual tracking method, called dimension adaption correlation filters (DACF). First, the framework adopts the multi-channel deep CNN features to obtain a discriminative sample appearance model, resisting the background clutters. Moreover, a dimension adaption operation is introduced to reduce relatively irrelevant parameters as possible, which tackles the issue of over-fitting and promotes the model effectively adapting to different tracking scenes. Furthermore, the DACF formulation optimization can be efficiently performed on the basis of implementing the alternating direction method of multipliers (ADMM). Extensive evaluations are conducted on benchmarks, including OTB2013, OTB2015, VOT2016, and UAV123. The experiments results show that our tracker gains remarkable performance. Especially, DACF obtains an AUC score of 0.698 on OTB2015.

Deep Siamese Cross-Residual Learning for Robust Visual Tracking

The sixth-generation (6G) wireless technology contributes to the establishment of the Internet of Things (IoT). Recently, the IoT has become popular because of its smart architectures and various applications. Among these applications, intelligent urban surveillance systems for smart cities are becoming more and more important. Therefore, designing a robust visual tracking method has become an urgent task. Deep Siamese convolutional neural networks have been applied to visual tracking recently because of their advantageous abilities to learn a matching function between the template and the target candidate. Unlike traditional Siamese networks, which separately treat the two branches, we propose deep Siamese cross-residual learning to entangle the two branches from the beginning to the end of the Siamese network. This strategy can make the two branches exchange instance-specific information at different nodes of the network and learn a more compact representation of the target. In addition, we propose a combined loss function, which consists of two complementary tasks. One task is to learn a matching function directly and the other one is to learn a classification function. Moreover, our model does not need to load any pretrained weights and is trained with limited sequences from scratch. Plenty of experiments show that our tracker performs favorably against many state-of-the-art tracking methods.

Three-Dimensional Image Recognition of Athletes' Wrong Motions Based on Edge Detection

The traditional 3D visual motion amplitude tracking algorithms cannot acquire the complete contour features, not to mention the correction of wrong motions in sports training. To solve the problem, this paper designs a 3D visual image recognition method based on contourlet domain edge detection, and applies it to the recognition of athlete’s wrong motions in sports training. Firstly, the visual reconstruction and feature analysis of human motions were carried out, and the edge detection features were extracted by edge detection algorithm. Then, a 3D visual motion amplitude tracking method was proposed based on improved inverse kinematics. The simulation results show that the proposed algorithm can effectively realize the recognition of 3D visual images of athlete motions, and improve the correction and judgment ability of athlete motions.

Effective template update mechanism in visual tracking with background clutter

Today, artificial intelligence is everywhere in people’s daily lives. Visual tracking, which is used to identify and continuously track specific targets, is an important research domain in the study of artificial intelligence. However, current visual tracking methods are not accurate enough for object tracking with background clutter, which can easily lead to tracking failures. Therefore, in this paper, in order to solve the problem of tracking failure in clutter background, we propose a template update mechanism to improve the accuracy of visual tracking. First, an original template is saved when the background clutter is detected. During background clutter, we use both the original template and the current template at the location estimated by the optical flow and choose better one. Next, the original template is reused after the background clutter is ended. Finally, the proposed mechanism is used both in the KCF and BACF algorithm to verify the effectiveness of the mechanism. With experiments on the OTB2015 dataset, results show that the proposed mechanism has improved accuracy and success rate of the two baseline algorithms. Meanwhile, in state-of-the-art algorithms, the algorithm using the proposed mechanism also has excellent tracking performance. In addition, this method also has strong tracking robustness and adaptation capability to sequential learning for video data.

Visual Target Tracking via Online Reliability Evaluation and Feature Selection in the Framework of Correlation Filtering

Background: Although correlation filtering is one of the most successful visual tracking frameworks, it is prone to drift caused by several factors such as occlusion, deformation and rotation. Objective: In order to improve the performance of correlation filter-based trackers, this paper proposes a visual tracking method via online reliability evaluation and feature selection. Methods: The main contribution of this paper is to introduce three schemes in the framework of correlation filtering. Firstly, we present an online reliability evaluation to assess the current tracking result by using the method of adaptive threshold segmentation of response map. Secondly, the proposed tracker updates the regression model of correlation filter according to the assessment result. Thirdly, when the tracking result based on a handcrafted feature is not reliable enough, we propose a feature selection scheme that autonomously replaces a handcrafted feature used in the traditional correlation filter-based trackers with a deep convolutional feature that can re-capture the target by its powerful discriminant ability. Results: On OTB-2013datasets, the Precision rate and Success rate of the proposed tracking algorithm can reach 84.8% and 62.5%, respectively. Moreover, the tracking speed of proposed algorithm is 19 frame per second. Conclusion: The quantitative and qualitative experimental results both demonstrate that the proposed algorithm performed favorably against nine state-of-the-art algorithms.

Phase separation behavior of whey protein isolate particle dispersions in the presence of xanthan.

In this study, phase separation of colloidal whey protein isolate (WPI) particle dispersions was studied using a rod-like polysaccharide xanthan. Effects of different xanthan concentration, particle volume fraction, and temperature were analyzed by visual observations, turbidity measurements, and particle mobility tracking method. Particle mobility was determined using a diffusing wave spectroscopy (DWS) set up. Xanthan concentration was kept low in order not to increase the viscosity of dispersions, so that the phase separation could be observed easily. Visual observations showed that there was a minimum concentration of xanthan to induce phase separation at a constant particle volume fraction, and xanthan concentration was found to have an important effect on the degree of phase separation. The temperature was also found to have an effect on depletion mechanism. Phase separation was mainly a result of different sizes of WPI particles, and xanthan induced the depletion interaction between WPI particles, as supported by the data obtained from DWS. The results of this study explained both the mechanism and the stability range of particle dispersions in the presence of xanthan, which is important for the design of stable systems, including colloidal particles.

Siamese networks with distractor-reduction method for long-term visual object tracking

Many trackers which divide the tracking process into two stages have recently been proposed to solve the problem of long-term tracking. Their outstanding performance makes them become one of the mainstream algorithms of long-term tracking. To further improve the performance of two-stage tracking algorithms, some improvements are proposed in this paper. (a) A hard negative mining method is proposed. It can optimize the training process of the verification network and bridge the gap between the two sub-networks. (b) The architecture of the verification network is designed as a Siamese structure; therefore, the semantic ambiguity in classification can be alleviated. Extensive experiments performed on benchmarks demonstrate that the proposed approach significantly outperforms the state-of-the-art methods, yielding 7% relative gain in the VOT2018-LT dataset and 14.2% relative gain in the OxUvA dataset.

CNN-based single object detection and tracking in videos and its application to drone detection

This paper presents convolutional neural network (CNN)-based single object detection and tracking algorithms. CNN-based object detection methods are directly applicable to static images, but not to videos. On the other hand, model-free visual object tracking methods cannot detect an object until a ground truth bounding box of the target is provided. Moreover, many annotated video datasets of the target object are required to train both the object detectors and visual trackers. In this work, three simple yet effective object detection and tracking algorithms for videos are proposed to efficiently combine a state-of-the-art object detector and visual tracker for circumstances in which only a few static images of the target are available for training. The proposed algorithms are tested using a drone detection task and the experimental results demonstrated their effectiveness.

Unsupervised Deep Representation Learning for Real-Time Tracking

The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotation and learn to track arbitrary objects, we propose an unsupervised learning method for visual tracking. The motivation of our unsupervised learning is that a robust tracker should be effective in bidirectional tracking. Specifically, the tracker is able to forward localize a target object in successive frames and backtrace to its initial position in the first frame. Based on such a motivation, in the training process, we measure the consistency between forward and backward trajectories to learn a robust tracker from scratch merely using unlabeled videos. We build our framework on a Siamese correlation filter network, and propose a multi-frame validation scheme and a cost-sensitive loss to facilitate unsupervised learning. Without bells and whistles, the proposed unsupervised tracker achieves the baseline accuracy of classic fully supervised trackers while achieving a real-time speed. Furthermore, our unsupervised framework exhibits a potential in leveraging more unlabeled or weakly labeled data to further improve the tracking accuracy.

Tracking and grasping of moving target based on accelerated geometric particle filter on colored image

Visual tracking and grasping of moving object is a challenging task in the field of robotic manipulation, which also has great potential in applications such as human-robot collaboration. Based on the particle filtering framework and position-based visual servoing, this paper proposes a new method for visual tracking and grasping of randomly moving objects. A geometric particle filter tracker is established for visual tracking. In order to deal with the tracking efficiency issue for particle filter, edge detection and morphological dilation are employed to reduce the computation burden of geometric particle filtering. Meanwhile, the HSV image feature is employed instead of the grayscale feature to improve the tracking algorithm’s robustness to illumination change. A grasping strategy combining tracking and interception is adopted along with the position-based visual servoing (PBVS) method to achieve stable grasp of the target. Comprehensive comparisons on open source dataset and a large number of experiments on real robot system are conducted, which demonstrate the proposed method has competitive performance in random moving object tracking and grasping.

Zero‐variance minibatch Monte Carlo for pixel‐wise visual tracking

In this study, the authors present a novel visual tracking method using the pixel-wise posterior estimation and minibatch Monte Carlo sampling. To avoid background pixels in the noisy bounding box representation, they estimate the posteriors in a pixel-wise manner. To boost the pixel-wise posterior estimation, they adopt minibatch Monte Carlo sampling, where only a small portion of pixels are used for inference. Experimental results demonstrate that the proposed visual tracker produces accurate tracking results using a small portion of pixels for the posterior estimation and is comparable to state-of-the-art methods.

SiamMN: Siamese modulation network for visual object tracking

Visual object tracking methods based on Siamese network are often difficult to distinguish objects with the same semantic or similar appearance as tracking target in tracking process due to the lack of discriminating strategies for the confusing objects. We propose a visual object tracking method based on Siamese modulation network. It takes the given bounding box in the target frame and the current frame as input, and fuses these multi-layer convolutional features to obtain more target appearance information of bounding box and the current frame. The feature modulator generates feature modulation vector based on the given bounding box to enhance visual appearance information of target instance in multi-layer feature of the current frame, so as to make target instance obtain higher score in response map of region proposal network, and thus realize target instance-specific tracking task. Experiments on two public benchmark datasets, OTB2015 and VOT2018, show that the proposed tracker has a competitive performance among other state-of-the art trackers.

A Visual Tracking Method Based on an Adaptive Overlapping Correlation Filter for Robotic Real-Time Cognitive Imaging

Computer vision is a very important research direction in the cognitive computing field. Robots encounter various target-tracking problems with computer vision systems. Robust scale estimation is an important issue in tracking algorithms. Most of the available methods have difficulty addressing even reasonable changes of scale in complex videos. In this paper, we propose a visual tracking method based on robust scale estimation, which uses a discriminant correlation filter based on a time-dependent scale-space filter and an adaptive cross-correlation filter. The tracker uses separate essential filters for sample migration and scale estimation. Furthermore, the built-in scale estimation method can be introduced into other tracking algorithms. We validate the proposed method on the UAV123 dataset. The results of comparison experiments with the traditional correlation filter tracking method demonstrate that the proposed method improves the success rate and tracking accuracy while controlling the computational complexity; its success rate measured by the area under the curve is 0.638, while at a location error precision of 20%, it is 0.649.

A novel visual tracking method using stochastic fractal search algorithm

Recently metaheuristic algorithms have attracted the attention of many researchers in various disciplines for their simplicity of application and their efficiency. Visual tracking is one of the most promising fields of application of these methods, and although many approaches have been proposed, their main disadvantage is the convergence at local minima which make them unable to find the exact position. To overcome this drawback, we propose to use an algorithm that provides an efficient exploration of the search space, which is stochastic fractal search (SFS) algorithm. SFS is used as a localization method, to find the most similar candidate to a previous defined template. Standard kernel-based spatial color histogram of the object bounding box, is evaluated in order to model the object appearance. Subsequently, Bhattacharyya distance is measured between the two histograms of the model and the candidate to define the fitness function, in which optimization is sought. To assess fairly the robustness of our approach, we have evaluated its performance on 20 video sequences from the OTB-100 sequences dataset and compared it to 11 other state-of-the-art trackers. Quantitative and qualitative evaluations on challenging situations provided satisfying results of SFS-based tracker compared to other state-of-the-art algorithms.

Kernel correlation filters based on feature fusion for visual tracking

This paper presents a CF-based method for robust visual tracking by multiple features fusion. HOG features and high-level CNN features are used to enhance tracking performance. First, different features are extracted from the target. Secondly, the extracted features are employed to learn the corresponding discriminant models, which are used to generate response maps respectively. Finally, an accurate response map can be obtained by fusing multiple response maps. In addition, we propose a model update strategy to reduce model drift under occlusion. The OTB benchmark is used to test the proposed method. Experimental results show that the proposed method can significantly improve tracking performance in complex situations especially in occlusion and fast motion. In addition, compared with several state-of-the-art methods, the proposed method shows competitive accuracy rate and success rate.

STGL: Spatial-Temporal Graph Representation and Learning for Visual Tracking

Tracking-by-detection framework has been normally adopted in visual tracking methods. It aims to localize the visual target object with a bounding box. However, the bounding box is usually difficult to describe the target object accurately and thus easily introduces noisy background information, which usually degrades the final tracking results. Recently, weighted patch representation of the object has been shown very effectively for suppressing the undesirable background information and thus can obviously improve the tracking results. In this paper, we propose a novel Spatial-Temporal Graph representation and Learning (STGL) model to generate a kind of robust target representation for visual tracking problem. The main aspect of STGL is that it aims to exploit both spatial (within each frame) and temporal (between consecutive frames) structure of patches simultaneously in a unified graph representation and semi-supervised learning model. Comparing with existing works, STGL naturally exploits the learned representation of object in previous frame and thus can obtain the representation of object in current frame more accurately and robustly. A new ADMM algorithm is derived to solve the proposed STGL model. Based on the proposed object representation, we then adapt the structured SVM by introducing scale estimation to achieve object tracking. Extensive experiments show that our method outperforms the state-of-the-art patch based tracking methods on two standard benchmark datasets.

Robust visual tracking via part-based model

In this paper, we propose a novel visual object tracking method using a part based appearance model. First, a local kernel feature is developed to encode edge information of patches. Next, bounding box of the target is divided into multiple parts. Then, each part uses correlation filter based tracking to predict position in the next frame. The matrix cosine similarity is utilized to measure reliabilities of the patches. Finally, optimal target location is predicted via maximizing the likelihood, which is obtained by adaptively fusing the reliable patches locations. Experimental results illustrate that our algorithm outperforms state-of-the-art tracking methods significantly in terms of accuracy and robustness.