Object Tracking Method Research Articles

An Overview of Correlation-Filter-Based Object Tracking

In the last two decades, object tracking has been one of the prevalent fields in social media. Object tracking uses a dynamic model to track the same target, aiming to analyze the same social object and its behavior in a set of consecutive video frames. In this article, we provide a comprehensive survey on some representative and latest correlation-filter-based object tracking methods and compare their respective strengths and weaknesses under the theoretical and experimental analyses. First of all, we divide these correlation-filter-based object tracking methods into four categories according to their characteristics, including categorized features, space weight factors, scale factors, and expert strategies. Second, extensive experiments on benchmark datasets with 11 tracking challenges are performed and discussed. Finally, this article also attempts to provide some insights for the readers to comprehend and improve the involved tracking algorithms. It is expected that the overview would present a detailed framework and some enlightenments of object tracking to readers who are new in this area.

Robust DCF object tracking with adaptive spatial and temporal regularization based on target appearance variation

To alleviate the boundary effect and constrain the update of the tracking model, current object tracking methods based on Discriminative Correlation Filter (DCF) usually introduce spatial and temporal regularization constraints in the filter training objective function. However, these regularization constraints with fixed coefficients greatly limit the adaptability of the tracker with respect to target appearance variation. This paper proposes a spatial-temporal regularization model based on the real-time target appearance variation for the filter training, improving the adaptability of the filter related to target appearance variation. Moreover, the filter training objective function with the adaptive spatial-temporal regularization is proposed to enhance the robustness of the filter. Finally, an iterative optimization method based on the alternating direction method of multipliers (ADMM) is proposed to update the filter, and the convergence proof of the optimization method is also presented. Comparison experiments with some representative trackers including ASRCF,ARCF, CSR_CF, DSAR_CF and SSR_CF etc. on OTB2015, UAV123 and LaSOT databases show that the proposed algorithm effectively improves the tracking accuracy.

Remote Sensing Object Tracking With Deep Reinforcement Learning Under Occlusion

Object tracking is an important research direction of space Earth observation in the field of remote sensing. Although the existing correlation filter-based and deep learning (DL)-based object tracking algorithms have achieved great success, they are still unsatisfactory for the problem of object occlusion. The occlusion caused by the complex change in background, and the deviation of the tracking lens, causes object information to go missing, which leads to the omission of detection. Traditionally, most methods for object tracking under occlusion adopt a complex network model, which redetects the occluded object. To address this issue, we propose a novel object tracking approach. First, an action decision-occlusion handling network (AD-OHNet) based on deep reinforcement learning (DRL) is built to achieve low computational complexity for object tracking under occlusion. Second, the temporal and spatial context, the object appearance model, and the motion vector are adopted to provide the occlusion information, which drives actions in reinforcement learning under complete occlusion and contributes to improving the accuracy of tracking while maintaining speed. Finally, the proposed AD-OHNet is evaluated on three remote sensing video datasets of Bogota, Hong Kong, and San Diego taken from Jilin-1 commercial remote sensing satellites. The video datasets all shared problems of low spatial resolution, background clutter, and small objects. Experimental results on the three video datasets validate the effectiveness and efficiency of the proposed tracker.

Comprehensive Underwater Object Tracking Benchmark Dataset and Underwater Image Enhancement With GAN

Current state-of-the-art object tracking methods have largely benefited from the public availability of numerous benchmark datasets. However, the focus has been on open-air imagery and much less on underwater visual data. Inherent underwater distortions, such as color loss, poor contrast, and underexposure, caused by attenuation of light, refraction, and scattering, greatly affect the visual quality of underwater data, and as such, existing open-air trackers perform less efficiently on such data. To help bridge this gap, this article proposes a first comprehensive underwater object tracking (UOT100) benchmark dataset to facilitate the development of tracking algorithms well-suited for underwater environments. The proposed dataset consists of 104 underwater video sequences and more than 74 000 annotated frames derived from both natural and artificial underwater videos, with great varieties of distortions. We benchmark the performance of 20 state-of-the-art object tracking algorithms and further introduce a cascaded residual network for underwater image enhancement model to improve tracking accuracy and success rate of trackers. Our experimental results demonstrate the shortcomings of existing tracking algorithms on underwater data and how our generative adversarial network (GAN)-based enhancement model can be used to improve tracking performance. We also evaluate the visual quality of our model's output against existing GAN-based methods using well-accepted quality metrics and demonstrate that our model yields better visual data.

Various object detection algorithms and their comparison

This paper presents a detailed and comparative analysis of various object detection algorithms. The challenge of object detection is taken care of while studying various algorithms. Throughout the year various methods have been discovered in this field, each having its advantages and drawbacks. This paper aims at providing the systematic study of all the popular algorithms including the conventional ones. Although many methods and techniques come up each year and each of them having superiority other the previous models but at the same time even complexity increases. In this paper, some famous and basic methods of object detection and tracking are discussed. Using these developed techniques good results can be obtained and also the comparison of the efficiency of all the models can be done. Real-time applications and the outcomes are also discussed.

Development and experimental verification of search and rescue ROV

This paper presents the design of a new type of search and rescue remotely operated vehicle (ROV) system. The goal is to achieve the underwater target search and detection and small target capture and rescue operation requirements. First, the overall design of the whole underwater surface system and the layout design of the propulsion system are given. On this basis, the ROV frame structure, electronic cabin, and power cabin are designed and analyzed. To accomplish the grasping task, a grasping hand is designed based on a multifunctional manipulator to achieve underwater grasping. To make the ROV more intelligent, different kinds of underwater object detection and tracking methods are adopted and analyzed. Finally, it was tested in a pool and the sea to verify the reliability and stability of the designed search and rescue ROV.

HM-Net: A Regression Network for Object Center Detection and Tracking on Wide Area Motion Imagery

Wide Area Motion Imagery (WAMI) yields high resolution images with a large number of extremely small objects. Target objects have large spatial displacements throughout consecutive frames. This nature of WAMI images makes object tracking and detection challenging. In this paper, we present our deep neural network-based combined object detection and tracking model, namely, Heat Map Network (HM-Net). HM-Net is significantly faster than state-of-the-art frame differencing and background subtraction-based methods, without compromising detection and tracking performances. HM-Net follows object center-based joint detection and tracking paradigm. Simple heat map-based predictions support unlimited number of simultaneous detections. The proposed method uses two consecutive frames and the object detection heat map obtained from the previous frame as input, which helps HM-Net monitor spatio-temporal changes between frames and keeps track of previously predicted objects. Although reuse of prior object detection heat map acts as a vital feedback-based memory element, it can lead to unintended surge of false positive detections. To increase robustness of the method against false positives and to eliminate low confidence detections, HM-Net employs novel feedback filters and advanced data augmentations. HM-Net outperforms state-of-the-art WAMI moving object detection and tracking methods on WPAFB dataset with its 96.2% F1 and 94.4% mAP detection scores, while achieving a 61.8% mAP tracking score on the same dataset.

Spatial–Spectral Weighted and Regularized Tensor Sparse Correlation Filter for Object Tracking in Hyperspectral Videos

Hyperspectral video camera captures spatial, spectral and temporal information of moving objects. Traditional object tracking methods developed for color videos have been applied to hyperspectral videos after compressing hundreds of spectral bands into three, which does not fully utilize the wealth spectral information. In order to address this issue, we present a tensor sparse correlation filter with a spatial-spectral weighted regularizer for object tracking. First, tensor processing is employed to reduce the spectral differences of homogeneous background, thereby producing robust spectral structure features. Second, a spatial-spectral weighted regularizer is designed in the correlation filter framework to penalize filter template by suppressing spectral features dissimilar to the center pixel in tracking. Third, a sparse constraint term and tracking context information are incorporated to suppress unexpected peaks in the response map. Finally, a reformulated stacked HOG feature extractor and a two-dimensional adaptive scale search strategy are developed to further improve the tracker’s feature discrimination and scale adaptation capability. Experimental results demonstrate that the proposed method achieves superior tracking performance than traditional correlation filter-based trackers.

Multivehicle Object Tracking in Satellite Video Enhanced by Slow Features and Motion Features

With the development of video satellites, multimoving object tracking in satellite video is possible and has become a new challenging task. The difficulties are mainly caused by the characteristics of satellite videos: 1) small objects; 2) low contrast between objects and background; and 3) background in a state of continuous motion. These characteristics make it difficult for the advanced multiobject tracking algorithms in the natural video to give full play to their advantages, resulting in vast false alarms, missed objects, ID switches, and low-confidence bounding boxes. To tackle these problems, a novel multimoving object tracking method considering slow features (SFs) and motion features has been proposed in this research, named SF and motion feature-guided multiobject tracking (SFMFMOT), which realizes the continuous tracking of moving vehicles in satellite videos. A nonmaximum suppression (NMS) module guided by bounding box proposals based on SFs is designed to assist the object detection part by utilizing the sensitivity of SF analysis to the changed pixels. While removing a large number of static false alarms and supplementing missed objects, it improves the recall rate by increasing the confidence score of the correctly detected object bounding boxes. In order to improve the tracking performance, a set of optimization strategies based on motion features and time accumulation information are proposed to smooth the trajectory, remove static false alarms, and duplicate bounding boxes. The proposed method is evaluated in three satellite videos and its superiority is demonstrated.

Selective part‐based correlation filter tracking algorithm with reinforcement learning

In visual object tracking methods, improving both the run time and the accuracy in the face of complex situations has always been an important issue. Many complex tracking algorithms, such as part-based algorithms, have better accuracy when facing occlusions, but they have much greater computational complexity. In response to the above problems, this paper proposes a selective part-based correlation filter (SPCF) tracking algorithm with a reinforcement learning to achieve more stable and efficient tracking of targets. First, according to the conditions of the response map of the correlation filter (CF), the entire tracking process is divided into three states: simple environments, complex environments, and harsh environments. Second, this paper uses reinforcement learning to determine the states of frames in different situations to improve the tracking effect of the algorithm. Third, the process of the online selection of states is transformed into a Markov decision process (MDP), where the policy learning of the MDP is achieved by reinforcement learning. Additionally, different strategies are used to track a target in different states: the overall filter is used to increase the speed in simple environments; part-based filters are used to improve the accuracy in complex environments; and in harsh environments where the target completely disappears, a redetection algorithm is used to find the target when it reappears. Finally, the performance of the tracking algorithm is verified on the VOT2018, OTB-2015, and LaSOT datasets.

A PERUSAL STUDY OF METHODS FOR ENERGY EFFICIENT MULTI OBJECT TRACKING IN WIRELESS SENSOR NETWORKS

Wireless sensor networks (WSNs) has various applications in different areas such as object detection and target tracking, industrial process monitoring, environmental monitoring, wildlife monitoring, Robot control and security applications for buildings. In WSNs, Energy efficiency is one of the important research issues, as it determines the lifetime of the sensor network deployed for the specific applications. Object tracking is one of the dominant applications of wireless sensor networks and many energy-efficient multi object tracking algorithms are used for precise or exact object tracking. The main focus this paper is the perusal study of all different energy-efficient object tracking methods and algorithms for Wireless Sensor Network.

Distributed System for Objects Localization in the Working Area of a Modular Reconfigurable Mobile Robot

The paper proposes a novel approach to the objects localization in the working area of a modular reconfigurable robot (MRR), which implies the installation of stationary monitoring points (SMP), consisting of detachable robot’s modules and in- stalled by robot itself. This approach is based on the architecture of the MRR control system previously proposed by the authors and a new method for comparing information about the speed and position obtained from various sensors. The key steps of the approach are following. Upon arriving in the target area, the MRR places SMPs, which consist of a power source, a computing device, a wireless transceiver and a sensor, detached from the robot. Then SMPs monitor the working area using different types of sensors (cameras, rangefinders, etc.), perform segmentation of the measured data and transfer this information to the robot. Further a sensor fusion is performed using a novel object tracking method, which makes it possible to localize target objects even in those cases when they are not visible by some of the SMPs. One of the key advantages of the new approach is a possibility of implementation in the distributed architecture of a MRR. The simulation results show that proposed method has Multiple Object Tracking Accuracy (MOTA) metric of 86 %, which is higher than the most of its analogues, while the estimated dynamic object localization error in a 8x7 m working area using 2 cameras and 1 rangefinder does not exceed 10 cm.

Visual Tracking With Object Center Displacement and CenterNet

Modern artificial intelligence systems have revolutionized approaches to scientific and technological challenges in a variety of fields, thus remarkable improvements in the quality of state-of-the-art computer vision and other techniques are observed; object tracking in video frames is a vital field of research that provides information about objects and their trajectories. This paper presents an object tracking method basing on optical flow generated between frames and a ConvNet method. Initially, optical center displacement is employed to detect possible the bounding box center of the tracked object. Then, CenterNet is used for object position correction. Given the initial set of points (i.e., bounding box) in first frame, the tracker tries to follow the motion of center of these points by looking at its direction of change in calculated optical flow with next frame, a correction mechanism takes place and waits for motions that surpass a correction threshold to launch position corrections.

A Novel Tracking Algorithm Using Thermal and Optical Cameras Fused With mmWave Radar Sensor Data

Tracking of moving objects in pan-tilt-zoom (PTZ) cameras is a critical feature for automated surveillance applications. The PTZ auto tracking function enables the camera to control its electric motor mechanisms to adjust the course of the optical sensor field of view (FOV) to track moving objects automatically. In this paper, a proposed novel object tracking method based on the fusion of thermal, optical sensor and millimeter-wave data is implemented. The implementation of the proposed method is performed on a pan-tilt setup, which ultimately tracks the object of interest based on thermal data while keeping the optical image resolution the same as the thermal image resolution and provides valuable distance measurements to the target based on the millimeter-wave radar readings. The proposed method offers improvements over conventional optical sensor tracking by adding an extra layer to object tracking through additional thermal and millimeter-wave sensor data, which in turn provides a surplus of information of the object of interest that is being tracked. The proposed method compares favorably with commercially available surveillance systems.

Object Tracking in Video Using the TLD and CMT Fusion Model

Object tracking has been an attractive study topic in computer vision in recent years, thanks to the development of video monitoring systems. Tracking-Learning Detection (TLD), Compressive Tracking (CT), and Clustering of Static-Adaptive Correspondences for Deformable Object Tracking are some of the state-of-the-art methods for motion object tracking (CMT). We present a fusion model that combines TLD and CMT in this study. To restrict the calculation time of the CMT technique, the fusion TLD CMT model enhanced the TLD benefits of computation time and accuracy on t no deformable objects. The experimental results on the Vojir dataset for three techniques (TLD, CMT, and TLD CMT) demonstrated that our fusion proposal successfully trades off CMT accuracy for computing time.

Object Tracking Based on Global Context Attention

Previous research has shown that tracking algorithms cannot capture long-distance information and lead to the loss of the object when the object was deformed, the illumination changed, and the background was disturbed by similar objects. To remedy this, this article proposes an object-tracking method by introducing the Global Context attention module into the Multi-Domain Network (MDNet) tracker. This method can learn the robust feature representation of the object through the Global Context attention module to better distinguish the background from the object in the presence of interference factors. Extensive experiments on OTB2013, OTB2015, and UAV20L datasets show that the proposed method is significantly improved compared with MDNet and has competitive performance compared with more mainstream tracking algorithms. At the same time, the method proposed in this article achieves better results when the video sequence contains object deformation, illumination change, and background interference with similar objects.

Infrared object tracking method based on kernel correlation filters

Benefiting from the superiority visual capacity of infrared imaging system, infrared object tracking is widely applied in military, weapon guidance, security protection and other fields. Recently, correlation filter has attracted considerable attention within the tracking community due to its high computational efficiency. However, traditional correlation filter based trackers use the single feature, which has poor stability in low resolution and complex background. Aiming at the low resolution, poor contrast, low signal-to-noise and insufficient texture information of infrared image, we propose an Infrared object tracking method based on Kernel Correlation Filters, named Inf-KCF. We design a Multi-Feature Fusion structure to improve the expression ability for infrared targets, and separate the target from the background well. Experimental results on public infrared dataset show that, the Inf-KCF achieves promising performance.

Vehicle Classification and Counting System Using YOLO Object Detection Technology

The intelligent transportation system is one of the most important constructions of urban modernization. Traffic flow monitoring technology is the most essential information in the intelligent transportation system. With the advancements in instrumentation, computer image processing and communication technology, computerized traffic monitoring technologies have become feasible. This study captures traffic information using surveillance cameras installed at higher locations. The YOLO object detection technology is used to identify vehicle types. The system principle uses image processing and deep convolutional neural networks for object detection training. Vehicle type identification and counting are carried out in this study for straight-line bidirectional roads, and T-shaped and cross-type intersections. A counting line is defined in the vehicle path direction using the object tracking method. The center coordinate of the object moves through the counting line. The number of motorcycles, small vehicles, and large vehicles were counted in different road sections. The actual number of vehicles on the road was compared with the number of vehicles measured by the system. Three separate counting periods were used to define the results using the confusion matrix.

Channel Exchanging for RGB-T Tracking.

It is difficult to achieve all-weather visual object tracking in an open environment only utilizing single modality data input. Due to the complementarity of RGB and thermal infrared (TIR) data in various complex environments, a more robust object tracking framework can be obtained using video data of these two modalities. The fusion methods of RGB and TIR data are the core elements to determine the performance of the RGB-T object tracking method, and the existing RGB-T trackers have not solved this problem well. In order to solve the current low utilization of information intra single modality in aggregation-based methods and between two modalities in alignment-based methods, we used DiMP as the baseline tracker to design an RGB-T object tracking framework channel exchanging DiMP (CEDiMP) based on channel exchanging. CEDiMP achieves dynamic channel exchanging between sub-networks of different modes hardly adding any parameters during the feature fusion process. The expression ability of the deep features generated by our data fusion method based on channel exchanging is stronger. At the same time, in order to solve the poor generalization ability of the existing RGB-T object tracking methods and the poor ability in the long-term object tracking, more training of CEDiMP on the synthetic dataset LaSOT-RGBT is added. A large number of experiments demonstrate the effectiveness of the proposed model. CEDiMP achieves the best performance on two RGB-T object tracking benchmark datasets, GTOT and RGBT234, and performs outstandingly in the generalization testing.

Moving Camera-Based Object Tracking Using Adaptive Ground Plane Estimation and Constrained Multiple Kernels

Moving camera-based object tracking method for the intelligent transportation system (ITS) has drawn increasing attention. The unpredictability of driving environments and noise from the camera calibration, however, make conventional ground plane estimation unreliable and adversely affecting the tracking result. In this paper, we propose an object tracking system using an adaptive ground plane estimation algorithm, facilitated with constrained multiple kernel (CMK) tracking and Kalman filtering, to continuously update the location of moving objects. The proposed algorithm takes advantage of the structure from motion (SfM) to estimate the pose of moving camera, and then the estimated camera’s yaw angle is used as a feedback to improve the accuracy of the ground plane estimation. To further robustly and efficiently tracking objects under occlusion, the constrained multiple kernel tracking technique is adopted in the proposed system to track moving objects in 3D space (depth). The proposed system is evaluated on several challenging datasets, and the experimental results show the favorable performance, which not only can efficiently track on-road objects in a dashcam equipped on a free-moving vehicle but also can well handle occlusion in the tracking.