Video Object Tracking Algorithm Research Articles

Deep-feature-based asymmetrical background-aware correlation filter for object tracking

Correlation filter-based video object-tracking algorithms have gained widespread attention due to their efficiency and excellent tracking performance. However, traditional correlation filtering tracking algorithms possess several limitations. (1) They extract image features only by using rule sampling, which ignores the shape information of the target, resulting in insufficient discriminative power of the features. (2) They focus only on the difference between the background and the object, ignoring the effects of more challenging intra-class interference. (3) They do not further evaluate the reliability of the optimal candidate samples, resulting in easy failure in occlusion scenarios. This paper proposes an asymmetric background-aware correlation filter method for object tracking with deep features to solve the above limitations. First, an asymmetrical background-aware sampling method based on the shape information of the object is proposed. This sampling method significantly differs from the symmetrical sampling method in the traditional correlation filter framework. By exploring the shape information of the object, improving the otherness between the background and object samples is easy, thus suppressing the intra-class interferences. Second, deep neural networks are introduced in the correlation filter framework to extract the deep object features and a spatio-temporal regularization factor is adaptively assigned to suppress the boundary effects, intra-class distractors and aberrance between frames. Finally, a multi-modal object pool is constructed to evaluate the optimal candidate sample in each frame. This template pool fully exploits object diversity and solves the tracking drift and failure caused by invalid appearance changes in scenes such as occlusion and vigorous motion scenarios. To validate the effectiveness of the proposed method, it was compared with the state-of-the-art methods on public datasets. The experimental results show that the tracking performance of the proposed method is competitive.

Sports Video Object Tracking Algorithm Based on Optimized Particle Filter

INTRODUCTION: Particle filter based human motion video target tracking technology has become a trend. This project intends to apply particle filters to image processing of human activities. Firstly, an improved particle filter model is used to track moving video objects. The purpose is to further improve the tracking effect and increase the tracking accuracy. HSV distribution model was used to establish target observation model. The algorithm is combined with the weight reduction algorithm to realize the human motion trajectory detection in the target observation mode. The model was then confirmed by an examination of sports player videos. Experiments show that this method can be used to track people in moving images of sports. Compared with other methods, this method has higher computational accuracy and speed.

Quality Aware Features for Performance Prediction and Time Reduction in Video Object Tracking

The existing body of work on video object tracking (VOT) algorithms has studied various image conditions such as occlusion, clutter, and object shape, which influence video quality and affect tracking performance. Nonetheless, there is no clear distinction between the performance reduction caused by scene-dependent challenges such as occlusion and clutter, and the effect of authentic in-capture and post-capture distortions. Despite the plethora of VOT methods in the literature, there is a lack of detailed studies analyzing the performance of videos with authentic in-capture and post-capture distortions. We introduced a new dataset of authentically distorted videos (AD-SVD) to address this issue. This dataset contains 4476 videos with different authentic distortions and surveillance activities. Furthermore, it provides benchmarking results for evaluating ten state-of-the-art visual object trackers (from VOT 2017–2018 challenges) based on the proposed dataset. In addition, this study develops an approach for performance prediction and quality-aware feature selection for single-object tracking in authentically distorted surveillance videos. The method predicts the performance of a VOT algorithm with high accuracy. Then, the probability of obtaining the reference output is maximized without executing the tracking algorithms. We also propose a framework to reduce video tracker computation resources (time and video storage space). We achieve this by balancing processing time and tracking accuracy by predicting the performance in a range of spatial resolutions. This approach can reduce the execution time by up to 34% with a slight decrease in performance of 3%.

Two motion models for improving video object tracking performance

Two motion models are proposed to enhance the performance of video object tracking (VOT) algorithms. The first one is a random walk model that captures the randomness of motion patterns. The second one is a data-adaptive vector auto-regressive (VAR) model that exploits more regular motion patterns. The performance of these models is evaluated empirically using real-world datasets. Three real-time publicly available visual object trackers: the normalized cross-correlation (NCC) tracker, the New Scale Adaptive with Multiple Features (NSAMF) tracker, and the correlation filter neural network (CFNet) are modified using each of these two models. The tracking performances are then compared against the original formulation. It is observed that both models of the prior information lead to performance enhancement of all three trackers. This validates the hypothesis that when training videos are available, prior information embodied in the motion models can improve the tracking performance.

Temporal Frame Sub-Sampling for Video Object Tracking

Temporal frame sub-sampling (TFS) for reducing video object tracking (VOT) computing time is investigated. With a sampling ratio N, the TFS VOT algorithm will process a shorter video by sampling 1 out of N frames of the given video. The object trajectory of the remaining frames will be interpolated linearly based on those of sampled frames. Thus, TFS can result in a significant reduction of processing time at a cost of losing tracking accuracy. More importantly, it can be applied to accelerate any VOT algorithms. However, it is observed that when the object trajectory is smooth, the tracking accuracy of a TFS VOT algorithm may be improved compared to non-TFS results. In this work, we provide an empirical analysis of this unexpected outcome of the TFS scheme. We also suggest rules of thumb to leverage this property to use TFS to enhance efficiency and accuracy of VOT.

Video analysis of Hammersmith lateral tilting examination using Kalman filter guided multi-path tracking.

Video object tracking plays an important role in many computer vision-aided applications. This paper presents a novel multi-path analysis-based video object tracking algorithm. Trajectory of the moving object is refined using a Kalman filter-based prediction method. The proposed algorithm has been used successfully to analyze one of the complex infant neurological examinations often referred to as Hammersmith lateral tilting test. This is an important test of the infant neurological assessment process, and this test is difficult to grade by visual observation. It has been shown in this paper that the proposed video object tracking algorithm can be used to analyze the videos of fast moving objects by incorporating application-specific information. For example, the proposed tracking algorithm can be used to assess lateral tilting test of the Hammersmith infant neurological examinations. The algorithm has been tested with several video recordings of this test which were captured at the neurodevelopment clinic of the SSKM Hospital, Kolkata, India during the period of the study. It is found that the proposed algorithm is capable of estimating the score for the test with high values of sensitivity and specificity.

Video object tracking based on improved gradient vector flow snake and intra-frame centroids tracking method

Accurately tracking the video object in video sequence is a crucial stage for video object processing which has wide applications in different fields. In this paper, a novel video object tracking algorithm based on the improved gradient vector flow (GVF) snake model and intra-frame centroids tracking algorithm is proposed. Unlike traditional gradient vector flow snake, the improved gradient vector flow snake adopts anisotropic diffusion and a four directions edge operator to solve the blurry boundary and edge shifting problem. Then the improved gradient vector flow snake is employed to extract the object contour in each frame of the video sequence. To set the initial contour of the gradient vector flow snake automatically, we design an intra-frame centroids tracking algorithm. Splitting the original video sequence into segments, for each segment, the initial contours of first two frames are set by change detection based on t-distribution significance test. Then, utilizing the redundancy between the consecutive frames, the subsequent frames’ initial contours are obtained by intra-frame motion vectors. Experimental results with several test video sequences indicate the validity and accuracy of the video object tracking.

Rebound of Region of Interest (RROI), a New Kernel-Based Algorithm for Video Object Tracking Applications

This paper presents a new kernel-based algorithm for video object tracking called rebound of region of interest (RROI). The novel algorithm uses a rectangle-shaped section as region of interest (ROI) to represent and track specific objects in videos. The proposed algorithm is constituted by two stages. The first stage seeks to determine the direction of the object’s motion by analyzing the changing regions around the object being tracked between two consecutive frames. Once the direction of the object’s motion has been predicted, it is initialized an iterative process that seeks to minimize a function of dissimilarity in order to find the location of the object being tracked in the next frame. The main advantage of the proposed algorithm is that, unlike existing kernel-based methods, it is immune to highly cluttered conditions. The results obtained by the proposed algorithm show that the tracking process was successfully carried out for a set of color videos with different challenging conditions such as occlusion, illumination changes, cluttered conditions, and object scale changes.

A New Algorithm for Tracking Objects in Videos of Cluttered Scenes

The work presented in this paper describes a novel algorithm for aut omatic video object tracking based on a process of subtraction of successive frames, where the prediction of the direction of movement of the object being tracked is carried out by analyzing the changing areas generated as result of the object’s motion, specifically in regions of interest defined inside the object being tracked in both the current and the next frame. Simultaneously, it is initiated a minimization process which seeks to determine the location of the object being tracked in the next frame usi ng a function which measures the grade of dissimilarity between the region of interest defined inside the object being tracked in the current frame and a moving region in a next frame. This moving region is displaced in the direction of the object’s motion predicted on the process of subtraction of successive frames. Finally, the location of the moving region of interest in the next frame that minimizes the proposed function of dissimilarity corresponds to the predicted location of the object being trackedin the next frame. On the other hand, it is also designed a testing platform which is used to create virtual scenarios that allow us to assess the performance of the proposed algorithm. These virtual scenarios are exposed to heavily cluttered conditions w here areas which surround the object being tracked present a high variability. The results obtained with the proposed algorithm show that the tracking process was successfully carried out in a set of virtual scenarios under different challenging conditions .

A Simple Algorithm for Video Object Tracking

As one of the crucial issues of computer vision, video object tracking is widely used in many applications, such as visual surveillance, human-computer interaction, visual transportation, visual navigation of robots, military guidance, etc. The existing object tracking algorithms in engineering applications have the huge amount of computation, which can not meet the needs of real-time system applications, and the tracking accuracy is not high. So a simple and practical video object tracking algorithm is proposed in this paper. The Otsu algorithm is used for image binarization to filter the background, and the object edge is further processed based on mathematical morphology, and thus the tracking object is more clearly. The centroid weighted method determines the location of the center of the object only by one step calculation, which makes the location more accurate. The experimental results show that the algorithm of the paper is effective for detecting and tracking of a moving object in a static scene and it has a low complexity.

Filling the gap in quality assessment of video object tracking

Current evaluation methods either rely heavily on reference information manually annotated or, by completely avoiding human input, provide only a rough evaluation of the performance of video object tracking algorithms. The main objective of this paper is to present a novel approach to the problem of evaluating video object tracking algorithms. It is proposed the use different types of reference information and the combination of heterogeneous metrics for the purpose of approximating the ideal error. This will enable a significant decrease of the required reference information, thus bridging the gap between metrics with different requirements concerning this type of data. As a result, evaluation frameworks can aggregate the benefits from individual approaches while overcoming their weaknesses, providing a flexible and powerful tool to assess and characterize the behavior of the tracking algorithms.

A New Method For Video Object Tracking

In this paper, a new video moving object tracking method is proposed. In initialization, a moving object selected by the user is segmented and the dominant color is extracted from the segmented target. In tracking step, a motion model is constructed to set the system model of adaptive Kalman filter firstly. Then, the dominant color of the moving object in HSI color space will be used as feature to detect the moving object in the consecutive video frames. The detected result is fed back as the measurement of adaptive Kalman filter and the estimate parameters of adaptive Kalman filter are adjusted by occlusion ratio adaptively. The proposed method has the robust ability to track the moving object in the consecutive frames under some kinds of real-world complex situations such as the moving object disappearing totally or partially due to occlusion by other ones, fast moving object, changing lighting, changing the direction and orientation of the moving object, and changing the velocity of moving object suddenly. The proposed method is an efficient video object tracking algorithm.

Toward Automating Hammersmith Pulled-To-Sit Examination of Infants Using Feature Point Based Video Object Tracking

Hammersmith Infant Neurological Examination (HINE) is a set of tests used for grading neurological development of infants on a scale of 0 to 3. These tests help in assessing neurophysiological development of babies, especially preterm infants who are born before (the fetus reaches) the gestational age of 36 weeks. Such tests are often conducted in the follow-up clinics of hospitals for grading infants with suspected disabilities. Assessment based on HINE depends on the expertise of the physicians involved in conducting the examinations. It has been noted that some of these tests, especially pulled-to-sit and lateral tilting, are difficult to assess solely based on visual observation. For example, during the pulled-to-sit examination, the examiner needs to observe the relative movement of the head with respect to torso while pulling the infant by holding wrists. The examiner may find it difficult to follow the head movement from the coronal view. Video object tracking based automatic or semi-automatic analysis can be helpful in this case. In this paper, we present a video based method to automate the analysis of pulled-to-sit examination. In this context, a dynamic programming and node pruning based efficient video object tracking algorithm has been proposed. Pulled-to-sit event detection is handled by the proposed tracking algorithm that uses a 2-D geometric model of the scene. The algorithm has been tested with normal as well as marker based videos of the examination recorded at the neuro-development clinic of the SSKM Hospital, Kolkata, India. It is found that the proposed algorithm is capable of estimating the pulled-to-sit score with sensitivity (80%-92%) and specificity (89%-96%).

Tracking Video Object Based on Central Macroblocks

Since the approaches suggested so far for video moving object tracking are sensitive to the accuracy of object segmentation,we propose a new video object tracking algorithm that provides the strength of robustness to the problems of both under-segmentation and over-segmentation.The proposed tracking algorithm introduces a concept of central macroblock,which is used to establish the correspondences between objects inside neighboring frames via two levels of similarity measurement and observations.Furthermore,MPEG motion estimation and compensation and Kalman filtering techniques are also exploited to enhance the tracking performances.While the first level of similarity measurements is limited to local texture matching via SAD(Sum of Absolute Differences) values between central macroblocks,the second level is established upon objects via directional vectors,characterizing the internal structure of the segmented objects.And both levels of similarity measurements are integrated by Kalman filtering.Experimental results carried out on PETS2001 and PETS2006 database show that the proposed algorithm achieves successful tracking performances robust to inaccuracy of object segmentation as well as other distracting factors such as occlusion,deformation,lighting effect,object disappearances and appearances etc.

Online Selection of Tracking Features Using AdaBoost

This paper presents an online feature selection algorithm for video object tracking. Using the object and background pixels from the previous frame as training samples, we model the feature selection problem as finding a good subset of features to better classify object from background in current frame. This paper aims to improve existing methods by taking correlation between features into consideration. We propose to use AdaBoost algorithm to iteratively select one feature which best compensates the previously selected features. Using the selected features, we then construct a compound likelihood image, which shows the ability to discriminate better than the original frame, as the input for the tracking process. We also propose to use ellipse fitting to eliminate mislabeled pixels from our training process. In addition, we propose an online feature validity test to monitor the selected features and only re-select features when the previously selected features become out-of-date. Experimental results demonstrate that the proposed algorithm combined with mean-shift based tracking algorithm achieves very promising results.

Video object tracking using adaptive Kalman filter

In this paper, a new video moving object tracking method is proposed. In initialization, a moving object selected by the user is segmented and the dominant color is extracted from the segmented target. In tracking step, a motion model is constructed to set the system model of adaptive Kalman filter firstly. Then, the dominant color of the moving object in HSI color space will be used as feature to detect the moving object in the consecutive video frames. The detected result is fed back as the measurement of adaptive Kalman filter and the estimate parameters of adaptive Kalman filter are adjusted by occlusion ratio adaptively. The proposed method has the robust ability to track the moving object in the consecutive frames under some kinds of real-world complex situations such as the moving object disappearing totally or partially due to occlusion by other ones, fast moving object, changing lighting, changing the direction and orientation of the moving object, and changing the velocity of moving object suddenly. The proposed method is an efficient video object tracking algorithm.

An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture

In this paper, an unsupervised video object (VO) segmentation and tracking algorithm is proposed based on an adaptable neural-network architecture. The proposed scheme comprises: 1) a VO tracking module and 2) an initial VO estimation module. Object tracking is handled as a classification problem and implemented through an adaptive network classifier, which provides better results compared to conventional motion-based tracking algorithms. Network adaptation is accomplished through an efficient and cost effective weight updating algorithm, providing a minimum degradation of the previous network knowledge and taking into account the current content conditions. A retraining set is constructed and used for this purpose based on initial VO estimation results. Two different scenarios are investigated. The first concerns extraction of human entities in video conferencing applications, while the second exploits depth information to identify generic VOs in stereoscopic video sequences. Human face/ body detection based on Gaussian distributions is accomplished in the first scenario, while segmentation fusion is obtained using color and depth information in the second scenario. A decision mechanism is also incorporated to detect time instances for weight updating. Experimental results and comparisons indicate the good performance of the proposed scheme even in sequences with complicated content (object bending, occlusion).

A semi-automatic seeded region growing algorithm for video object localization and tracking

This paper describes a semi-automatic method for moving object segmentation and tracking. This method is suitable when a few objects have to be tracked, while the camera moves and fixates on them. The user delineates approximately the initial locations in a selected frame and specifies the depth ordering of the objects to be tracked. First, motion-based segmentation is obtained through an initial application of a region growing algorithm. The partition map is sequentially tracked from frame to frame using motion compensation and location prediction. The segmentation map is obtained by the region growing algorithm. Translational motion is assumed for the moving objects, and local intensity or color average may be used as additional features. A post-processing procedure regularizes the object boundaries over time.