Search

WiFi-based passive gesture tracking plays a crucial role in promoting human-computer interface, due to its pervasive availability and cost-effectiveness. Prior works focus on tracking gestures on 2D sensing plane by aggregating multiple WiFi links (typically 2), with Uniform Linear Arrays (ULAs). However, gestures actually contain 3D spatial information instead of just 2D, thus interpreting the 3D traces as 2D may lead to enormous tracking errors. This paper aims at exploring the possibility of passively tracking 3D hand traces likewise leveraging two WiFi links with standard 3-element ULAs, and presents a generic 3D centimeter-level passive gesture tracking system, called CentiTrack-3D. To this end, we make two key observations: (1) The ULA-resolved angle contains the integrated information of the azimuth and elevation in 3D space, despite its inability to estimate azimuth and elevation separately. (2) The radial motion deviating from the sensing plane also leads to length variations of paths. Motivated by the observations, a 3D tracking model named Chaos is elaborately designed to deduce the hand 3D coordinates, so as to track the traces. Extensive experiments yield that CentiTrack-3D achieves an overall median tracking granularity of 2.5 cm in 3D space in case of diverse users and environment conditions.

Gesture recognition by using Inertial Measurement Unit (IMU) sensors plays an important role in various Internet of Things (IOT) applications, e.g., smart home, intelligent medical system and so on. Traditional technologies usually utilize machine learning algorithms to train different gestures during the offline phase, then recognize the gesture during the online phase. However, such technologies cannot recognize these gestures without prior training. Even for the same gesture, with different gesture amplitude may result in unsuccessful recognition. Also if we change the person to perform the same gesture, the algorithms fails. In order to overcome these drawbacks, we propose an approach, which will be able to track the human body motion in realtime and also recognize complicated gestures. It utilizes the accelerometer information and proposes comprehensive localization algorithms for each deployed sensor attached on the human body. Then, it takes the correlation and limitation among body parts into account to recognize the gesture. Our experiments results show that, the successful recognition rate of our algorithm is 100%. Furthermore, any part of the human body can be well tracked, the tracking accuracy can reach 0.06m.

Recently, multi-task correlation filters has drawn much attention in the object tracking field, which utilizes the multi-task learning (MTL) approach to explore the interdependencies among deep features for object tracking. However, the existing multi-task correlation filters based method fails to consider the relations between the correlation filters. To address this problem, a novel correlation filters based visual tracking method is proposed in this paper, with the integration of multi-task convolution operators and object detection. In our method, convolution and correction filters are jointly learnt through using the MTL technique, with the purpose of exploring not only the interdependencies of deep features but also the internal relevance of the convolution filters. In addition, object detection is introduced into our algorithm to handle the problem of object missing to ensure a better performance of our tracking method. Experiments on five benchmark datasets demonstrate that the proposed visual tracking method outperforms existing state-of-the-art approaches.

In spatial augmented reality, a widely dynamic projection mapping system has been developed as a novel approach to graphics presentation for widely moving objects in dynamic situations. However, this method necessitates a novel tracking marker design that is resistant to random and complex occlusion and out-of-focus blurring, which conventional markers have not achieved. This article presents a uniform circumferential marker that becomes an ellipse in perspective projection and expresses geometric information. It can track the relative posture of a dynamically moving sphere with high speed, high accuracy, and robustness owing to continuous contour lines, thereby supporting both wide-range movement in the depth direction and human interaction. Moreover, a biased circumferential marker is proposed to embed unique coding, where the absolute posture is decoded with a novel recognition algorithm. Moreover, rough initialization using the geometry of multiple ellipses is proposed for both markers to start the automatic and precise tracking. Real-time rotation visualization onto the surface of a moving sphere is made possible with the high-speed, widely dynamic projection mapping system. The tracking performance is demonstrated to exhibit sufficient basic tracking performance as well as robustness against blurring and occlusion compared to conventional dot-based markers.

Object tracking is a fundamental task for the visual perception system on the intelligent unmanned aerial vehicle (UAV). The high efficiency of correlation filter (CF) based trackers has advanced the widespread development of online UAV object tracking. This kind of method can effectively train a filter to discriminate the target from the background. However, most CF-based methods require a fixed label function over all the previous samples, leading to over-fitting and filter degradation, especially in complex drone scenarios. To address this problem, a novel adaptive response reasoning approach is proposed for CF learning. It can leverage temporal information in filter training and significantly promote the robustness of the tracker. Specifically, the proposed response reasoning method goes beyond the standard response consistency requirement and constructs an auxiliary label of the current sample. Besides, it helps learn a generic relationship between the previous and current filters, thereby realizing self-regulated filter updating and enhancing the discriminability of the filter. Extensive experiments on four well-known challenging UAV tracking benchmarks with 278 videos sequences show that the presented method yields superior results to 40 state-of-the-art trackers with real-time performance on a single CPU, which is suitable for UAV online tracking missions.

Night time vehicle detection and tracking using traditional visible light cameras is a challenging task due to the limited visibility. The current state-of-the-art systems treat the vehicles at night time as paired vehicle headlights or taillights, with no ability to determine the contour of the vehicle or its spatial occupancy. Therefore, this paper proposes the first night time framework that combines the vehicle headlights and taillights to localize the vehicle contours. This new framework includes a novel multi-camera vehicle representation that groups and reconstructs vehicle headlights and taillights following mutual geometric distances between different vehicle components. This novel vehicle contour representation successfully removes duplicated vehicle lights and also compensates for the missing vehicle lights in the detection process. Eventually, vehicle headlight alignment and contour adjustment are used to further refine the vehicle contours. The proposed multi-camera system considers typical four-wheel vehicles, e.g., cars and SUVs, in the monitoring and might not be able to handle large trucks, e.g., 18-wheelers. The experiments are conducted on night time traffic videos under various scenarios and the proposed system attains an average of 0.896 in Multiple Object Tracking Accuracy (MOTA) and an average of 0.904 in Jaccard Coefficient (JC), which indicates 19.2% and 15.9% increases over the baseline system. The night time traffic datasets used in this paper are available at https://github.com/JustMeZXX/Intelligent-Night-Time- Traffic-Surveillance

Thermal sensors play an important role in intelligent transportation system. This paper studies the problem of RGB and thermal (RGBT) tracking in challenging situations by leveraging multimodal data. A RGBT object tracking method is proposed in correlation filter tracking framework based on short term historical information. Given the initial object bounding box, hierarchical convolutional neural network (CNN) is employed to extract features. The target is tracked for RGB and thermal modalities separately. Then the backward tracking is implemented in the two modalities. The difference between each pair is computed, which is an indicator of the tracking quality in each modality. Considering the temporal continuity of sequence frames, we also incorporate the history data into the weights computation to achieve a robust fusion of different source data. Experiments on three RGBT datasets show the proposed method achieves comparable results to state-of-the-art methods.

Simulating shadow interactions between real and virtual objects is important for augmented reality (AR), in which accurately and efficiently detecting real shadows from live videos is a crucial step. Most of the existing methods are capable of processing only scenes captured under a fixed viewpoint. In contrast, this paper proposes a new framework for shadow detection in live outdoor videos captured under moving viewpoints. The framework splits each frame into a tracked region, which is the region tracked from the previous video frame through optical flow analysis, and an emerging region, which is newly introduced into the scene due to the moving viewpoint. The framework subsequently extracts features based on the intensity profiles surrounding the boundaries of candidate shadow regions. These features are then utilized to both correct erroneous shadow boundaries for the tracked region and to detect shadow boundaries for the emerging region by a Bayesian learning module. To remove spurious shadows, spatial layout constraints are further considered for emerging regions. The experimental results demonstrate that the proposed framework outperforms the state-of-the-art shadow tracking and detection algorithms on a variety of challenging cases in real time, including shadows on backgrounds with complex textures, nonplanar shadows, fast-moving shadows with changing typologies, and shadows cast by nonrigid objects. The quantitative experiments show that our method outperforms the best existing method, achieving a 33.3% increase in the average F_{measure}. Coupled with an image-based shadow-casting method, the proposed framework generates realistic shadow interaction results. This capability will be particularly beneficial for supporting AR.

Pedestrians represent acutely complex and agile targets whose accident prevention has the highest priority concerning highly automated vehicles in urban traffic. Consequently, detection and tracking methods are necessary to determine motion behavior quickly and with high precision. With advancing microelectronics, powerful radar sensors and novel antenna structures are available for pedestrian detection systems, which can utilize unique features such as micro-Doppler signatures in several dimensions and high resolution. This paper presents a micro-Doppler based leg tracking framework that enables behavioral indications in a few sensor cycles. An adaptive motion model representing the kinematic locomotion of a human is derived to propagate the foot motion. Joint probabilistic data association assigns the detections to the respective leg and allows its temporal filtering of the position, micro-Doppler velocity, and kinematic parameters using an extended Kalman filter yielding real-time implementation capability. The presented approach provides the entire signal chain from raw radar data processing to extended multi-object state estimation based on highly relevant safety-critical motion maneuvers measured with radar parameterization corresponding to current serial short-range sensors.

Radar and camera information fusion sensing methods are used to solve the inherent shortcomings of the single sensor in severe weather. Our fusion scheme uses radar as the main hardware and camera as the auxiliary hardware framework. At the same time, the Mahalanobis distance is used to match the observed values of the target sequence. Data fusion based on the joint probability function method. Moreover, the algorithm was tested using actual sensor data collected from a vehicle, performing real-time environment perception. The test results show that radar and camera fusion algorithms perform better than single sensor environmental perception in severe weather, which can effectively reduce the missed detection rate of autonomous vehicle environment perception in severe weather. The fusion algorithm improves the robustness of the environment perception system and provides accurate environment perception information for the decision-making system and control system of autonomous vehicles.

Automatic 3D navigation control of microrobot in large microenvironment is one of the primary challenges hindering its applications. In this article, we present a systematic approach to use an electromagnetic manipulation system to deal with this challenge. Two movable orthogonal microscopic cameras scan the microenvironment on the top view and side view to build a stereo occupancy map automatically. The initial position of microrobot can be located on the basis of the similarity curves generated by the scanning sequences. In accordance with the distribution characteristic of electromagnetic fields in workspace, an enhanced rapidly exploring random tree algorithm is proposed to avoid obstacles in the complex environment. To ensure continuous visual servo in wide range, a field-of-view tracking method is developed using a specific image definition evaluation algorithm. A prescribed performance controller with disturbance observer is designed, which guarantees that the microrobot can remain in the view of microscopic cameras, and the transient and steady-state performance of the system can satisfy the expected requirements. A set of experiments are performed to verify the effectiveness of the proposed automatic 3D navigation strategy. Experimental results show that the microrobot can navigate automatically in a $\bm {12\,\times 10\,\times \text{10-mm}}$ microenvironment containing obstacles, and achieve reliable field-of-view tracking and path following at high speed.

To shorten the scanning time by focusing on the local scanning for such specimens as cells, this paper proposes an advanced scanning strategy based on autonomous exploration, so as to detect the specimen in real time and achieve fast imaging for an atomic force microscopy (AFM). More specifically, fast raster scanning is first performed to locate the initial boundary point of the specimen. On this basis, a boundary tracking algorithm is proposed to construct the internal boundary of the specimen online through the autonomous exploration of the probe. Afterwards, the boundary is expanded according to the internal boundary tracking direction, based on which a convex hull of the specimen is further constructed for the local scanning. Furthermore, the local slow scanning is performed for the specimen according to the generated scanning trajectory. Subsequently, unscanned areas in the sample can also be scanned by this autonomous method. Experimental results verify that the proposed method can achieve fast scanning while ensuring high-quality imaging.

As a sort of model-free tracking approach, discriminative correlation filter (DCF)-based trackers have shown prominent performance in unmanned aerial vehicle (UAV) tracking. Nevertheless, typical DCFs acquire all samples oriented to filter training merely from the current frame by cyclic shift operation in the spatial domain but ignore the consistency between samples across the timeline. The lack of temporal cues restricts the performance of DCFs under object appearance variations arising from object/UAV motion, scale variations, and viewpoint changes. Besides, many existing methods commonly neglect the channel discrepancy in object position estimation and generally treat all channels equally, thus limiting the further promotion of the tracking discriminability. This work proposes a novel tracking approach based on a multi-regularized correlation filter, i.e., MRCF tracker. By regularizing the deviation of responses and the reliability of channels, the tracker enables smooth response variations and adaptive channel weight distributions simultaneously, leading to favorable adaption to object appearance variations and enhancement of discriminability. Exhaustive experiments on five authoritative UAV-specific benchmarks validate the competitiveness and efficiency of MRCF against top-ranked trackers. Furthermore, we apply our proposed tracker to monocular UAV self-localization under air-ground robot coordination. Evaluations indicate the practicability of the presented method in UAV localization applications.

In active object tracking, given a visual observation as input, the goal is to lockup the target by autonomously adjusting camera’s position and posture. Previous works on active tracking assume that there is only one object (person) in the environment without distractors. In this work, towards realistic setting, we move forward to a more challenging scenario, where the tracker moves freely in 3D space like unmanned aerial vehicles (UAV) to track a person in various complex scenes with multiple distractors. To this end, we propose a novel end-to-end anti-distractor active object tracking framework by introducing multiple attention modules. On one hand, we take the target template to learn an embedding as channel-wise attention for current observation to distinguish the target from the distractors. On the other hand, temporal attention is introduced to fuse the observation history to extract a feature representation, which is then fed into a reinforcement learning network to output the action of the tracker. To evaluate our method, we build several multi-object 3D environments in Unreal Engine and extensive experiments demonstrate the effectiveness of our approach.

This paper proposes a new 3D multi-object tracker to more robustly track objects that are temporarily missed by detectors. Our tracker can better leverage object features for 3D Multi-Object Tracking (MOT) in point clouds. The proposed tracker is based on a novel data association scheme guided by prediction confidence, and it consists of two key parts. First, we design a new predictor that employs a constant acceleration (CA) motion model to estimate future positions, and outputs a prediction confidence to guide data association through increased awareness of detection quality. Second, we introduce a new aggregated pairwise cost to exploit features of objects in point clouds for faster and more accurate data association. The proposed cost consists of geometry, appearance and motion components. Specifically, we formulate the geometry cost using resolutions (lengths, widths and heights), centroids, and orientations of 3D bounding boxes (BBs), the appearance cost using appearance features from the deep learning-based detector backbone network, and the motion cost by associating different motion vectors. Extensive multi-object tracking experiments on the KITTI tracking benchmark demonstrated that our method outperforms, by a large margin, the state-of-the-art methods in both tracking accuracy and speed.

Gaze tracking is widely used in fatigue driving detection, eye disease diagnosis, mental illness diagnosis, website or advertising design, virtual reality, gaze-control devices and human-computer interaction. However, the influence of light, specular reflection and occlusion, the change of head pose, especially the ever-changing human pose in natural scenes, have brought great challenges to the accurate gaze tracking. In this paper, gaze tracking in natural scenes is studied, and a method based on Convolutional Neural Network (CNN) with residual blocks is proposed, in which attention mechanism is integrated into the network to improve the accuracy of gaze tracking. Furthermore, it is tested on the GazeFollow database which contains six kinds of databases. The results show that the performance of proposed method outperforms that of other state-of-the-art methods in natural scenes. Moreover, the proposed method has better real-time performance and is more suitable for practical applications.

Most of siamese network and correlation filter (CF) based trackers usually employ the context regression scheme to achieve appealing performance in both accuracy and efficiency. However, they are prone to drifting in challenging situations exhibiting occlusion, out-of-view and large-scale variations due to the lack of failure correction ability in these regressors. Particle filter based trackers can help to recover from tracking failures since several particles of high confidence about the target can be remained for the probability estimation of next frames, but need the large numbers of particles for each frame. In this paper, we propose a generic dynamic particle filter framework, which can reasonably control the number of particles in different scenarios, to improve the robustness of siamese and CF trackers by jointing the target classifier to relieve drifting. Our fundamental insight is that general scenarios are processed efficiently by the context regressor with few particles, while special scenarios are handled effectively by the target classifier with many particles. We propose a novel measure to determine whether to adopt the regressor and few particles to estimate target states with high measure scores, or increase the number of particles to prevent drifting with the proposed multi-template matching strategy in the classifier. In extensive experiments on eight large-scale benchmarks including OTB, UAV, TC128, VOT2017, VOT2019, LaSOT, TrackingNet and Got-10k, the proposed framework enables many basic siamese and CF trackers to operate at least over 24 frames per second and achieve superior tracking performance than themself, as well as the comparable accuracy with the state-of-the-art trackers. Furthermore, our framework is flexible and still has great potential for improvement and generalization.

This letter shows the first acquisition, Doppler tracking, and positioning results with Starlinks low Earth orbit (LEO satellite signals. A generalized likelihood ratio (GLR -based test is proposed to acquire Starlinks downlink signals. A Kalman filter (KF -based algorithm for tracking the Doppler frequency from the unknown Starlink signals is developed. Experimental results show Doppler tracking of six Starlink satellites, achieving a horizontal positioning error of 10 m.

The robot-held laparoscope efficiently maintains the stability of the surgical screen in comparison with the laparoscope held by the assistant. The collaboration between the robot-held laparoscope with the surgeon is achieved without the artificial manipulation by tracking surgical instruments automatically. In this work, a visual tracking space vector method is proposed to autonomously control the field-of-view (FOV) by tracking multiple surgical instruments. In the proposed method, a visual tracking space vector is introduced to track the motion of multiple instruments, and a constraint vector is defined to ensure that the laparoscope is always within the safe working space. In addition, a modified YOLOv3 algorithm is proposed to robustly detect and classify the surgical instruments. The proposed method automatically adapts to the changes in the number of surgical instruments, as compared to other visual servoing methods for tracking surgical instruments. The proposed method does not require the depth information of the tracked surgical instruments. Experimental and simulation results verify that the proposed method accurately and efficiently controls the robot-held laparoscope to track the motion of multiple surgical instruments and ensure safe tracking movement.

This paper considers the problem of tracking the players in handball videos using a single video source. Tracking of handball players in the video is a difficult task as they can frequently leave and re-enter the camera field of view, often change directions quickly and occlude each other. Players wear similar team uniforms, play indoor under artificial illumination, with the background than can vary significantly as the handball court is often painted in various colors. The continually improving accuracy of CNN-based object detectors makes tracking-by-detection methods an attractive choice for tracking players in sports videos as they can perform online and with low computational requirements on top of object detection. Here we consider the use of three tracking-by-detection methods in conjunction with the YOLO object detector, namely the standard Hungarian assignment algorithm, the Simple Online, and Real-time Tracking (SORT) algorithm that adds a motion model, and its extension Deep SORT. The methods are tested on a custom dataset of handball video scenes.

To date, the majority of positioning systems have been designed to operate within environments that have a long-term stable macro-structure with potential small-scale dynamics. These assumptions allow the existing positioning systems to produce and utilize stable maps. However, in highly dynamic industrial settings these assumptions are no longer valid and the task of tracking people is more challenging due to the rapid large-scale changes in structure. In this paper, we propose a novel positioning system for tracking people in highly dynamic industrial environments, such as construction sites. The proposed system leverages the existing CCTV camera infrastructure found in many industrial settings along with radio and inertial sensors within each worker’s mobile phone to accurately track multiple people. This multi-target multi-sensor tracking framework also allows our system to use cross-modality training in order to deal with the environment dynamics. In particular, we show how our system uses cross-modality training in order to automatically keep track environmental changes (i.e., new walls) by utilizing occlusion maps. In addition, we show how these maps can be used in conjunction with social forces to accurately predict human motion and increase the tracking accuracy. We have conducted extensive real-world experiments in a construction site showing significant accuracy improvement via cross-modality training and the use of social forces.

Deblurring can not only provide visually more pleasant pictures and make photography more convenient, but also can improve the performance of objection detection as well as tracking. However, removing dynamic scene blur from images is a non-trivial task as it is difficult to model the non-uniform blur mathematically. Several methods first use single or multiple images to estimate optical flow (which is treated as an approximation of blur kernels) and then adopt non-blind deblurring algorithms to reconstruct the sharp images. However, these methods cannot be trained in an end-to-end manner and are usually computationally expensive. In this paper, we explore optical flow to remove dynamic scene blur by using the multi-scale spatially variant recurrent neural network (RNN). We utilize FlowNets to estimate optical flow from two consecutive images in different scales. The estimated optical flow provides the RNN weights in different scales so that the weights can better help RNNs to remove blur in the feature spaces. Finally, we develop a convolutional neural network (CNN) to restore the sharp images from the deblurred features. Both quantitative and qualitative evaluations on the benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of accuracy, speed, and model size., accepted by tcsvt

Pedestrian positioning with wearable devices is a significant application of attitude tracking. It tracks the attitude (with heading angle being the most important part) of the device in real time and provides positioning services for users based on the information of step length provided by Pedestrian Dead-Reckon (PDR), which is a cheap and efficient positioning method at present. However, amid a train of positioning methods, the joint estimate of tracking is given by a train of methods based on the direction of gravity and the earths magnetic field direction. Considering the measurement of gravity that the gravity accelerometer is exposed to heavy noise due to the complex movement of human body during walking with uniform swing arm posture and forward speed, this paper proposed a novel estimate method based on the Kalman filter with multi-state constraints and the usage of low-cost sensors, which fulfills the estimation with the sequential observation of magnetic field. Compared with other related work, this method proposed in this paper eliminates the dependence on gravity direction, avoiding the influence of heavy noise caused by additional linear acceleration in motion state, and reduces the influence of insufficient observation when using magnetic field observation alone. The performance of the proposed method is evaluated by real-world experimentation results.

Since vision-based methods are vulnerable to challenging environmental conditions such as bad whether, shadows, occlusions and illumination, robustness is important. In this paper, a robust algorithm for detecting and tracking multiple lanes with arbitrary shape is proposed. We extend previous lane detection and tracking processes from the spatial domain to the temporal-spatial domain using our more robust and general multiple lane model. Distinct from traditional image pre-processing procedures, we adopt slice images generated from image sequence decomposition and reconstruction that contains important structured historical information. In this domain, we propose assumptions to reduce the algorithm's complexity and computation further. First, instead of common binarization, a more general lane marker detector is proposed with weak constraints to obtain cleaner binary image. Then, the lane marker candidates are used as the initialization of following particle filtering tracking process. We propose a confidence map computed from binary slice images by using an improved distance transform for particles sampling and weights calculation. The multi-lane model supports the use of multiple independent particle filters for tracking each lane boundary separately. Finally, a range of experimental results on testing dataset indicate that the proposed algorithm is effective with high performance and comparing with other methods, it has better tolerance to challenging environments.

We have proposed a novel method for vehicle speed estimation using a calibrated and synchronized pair of stereo cameras. In a newly proposed method, we first localize the vehicle by detecting and tracking its license plate in a series of stereo images; then, we triangulate the vehicle position along its trajectory; and finally, we compute its speed based on the trajectory and time. The experiments show that the proposed method overcomes state-of-the-art results with a mean error of approximately 0.05 km/h, a standard deviation of less than 0.20 km/h, and a maximum absolute error of less than 0.75 km/h. For the purpose of evaluation, we have recorded a dataset that contains over 600 vehicles whose trajectories were recorded and for which their ground truth speed was obtained from a pair of single beam LIDARs in optical gate configuration. Using the presented method, the speed was measured for over 99 % of the recorded vehicles. Others were rejected by the method mainly due to their short trajectories, obstructed license plates or frame errors that would adversely affect the precision of the measurement.

In this paper, we propose RF-Dial to realize a light-weight, battery-free and functional 2D human-computer interaction solution via RFID. What RF-Dial shines is that it can easily turn an ordinary object, e.g., a board eraser, into an intelligent interaction device. By deploying a tag array on the side face of the object together with a dipole tag on the top face, RF-Dial can track the rigid motion of the object and detect the touch gesture of a user on the surface of the object, including translation, rotation, click, press and hold, and swipe. To do the motion tracking, RF-Dial builds a phase-based model that captures the translation and rotation of the tagged object simultaneously. To detect the touch gesture, RF-Dial builds an RSSI-based model that uses the impact of the touching finger on the tag antenna's impedance to estimate the touch position. We implemented RF-Dial and evaluated its performance. Extensive experiments show that RF-Dial achieves an accurate rigid motion tracking, with a small error of 0.6cm for translation tracking, and a small error of 1.9 degrees for rotation estimation. Besides, RF-Dial can also detect the touch gesture accurately, as the 90 percent of touch position errors are less than 2.09mm.

Objective: Catheters and wires are used extensively in cardiac catheterization procedures. Detecting their positions in fluoroscopic X-ray images is important for several clinical applications such as motion compensation and co-registration between 2D and 3D imaging modalities. Detecting the complete length of a catheter or wire object as well as electrode positions on the catheter or wire is a challenging task. Method: In this paper, an automatic detection framework for catheters and wires is developed. It is based on path reconstruction from image tensors, which are eigen direction vectors generated from a multiscale vessel enhancement filter. A catheter or a wire object is detected as the smooth path along those eigen direction vectors. Furthermore, a real-time tracking method based on a template generated from the detection method was developed. Results: The proposed framework was tested on a total of 7,754 X-ray images. Detection errors for catheters and guidewires are 0.56 0.28 mm and 0.68 0.33 mm, respectively. The proposed framework was also tested and validated in two clinical applications. For motion compensation using catheter tracking, the 2D target registration errors (TRE) of 1.8 mm 0.9 mm was achieved. For co-registration between 2D X-ray images and 3D models from MRI images, a TRE of 2.3 0.9 mm was achieved. Conclusion: A novel and fully automatic detection framework and its clinical applications are developed. Significance: The proposed framework can be applied to improve the accuracy of image-guidance systems for cardiac catheterization procedures.

BACKGROUND: Hemophilia is an X-linked inherited disorder primarily affecting males, its major types are type A (deficiency in factor VIII) and B (deficiency in factor IX), and is considered to be the most common severe congenital coagulation factor deficiency. The present study was designed to test whether any differences in left ventricular (LV) rotational mechanics could be demonstrated between male patients with hemophilia and healthy controls using three-dimensional speckle-tracking echocardiography (3DSTE)-derived virtual LV models. METHODS: The present study consisted of 17 patients with hemophilia, however, 3 patients were excluded due to insufficient image quality. In the remaining patient population, 12 patients had hemophilia A and 2 patients had hemophilia B (mean age: 42.2±18.9 years, all males). The control group comprised 16 age-matched healthy subjects (46.0±5.9 years, all males). RESULTS: None of the routine two-dimensional echocardiographic data differ between patients with hemophilia and controls. None of the patients and controls showed ≥ grade 1 valvular regurgitations and had valvular stenoses. In one subject, the near absence of LV twist called as LV “rigid body rotation” could be detected, data of which were managed separately. While 3DSTE-derived apical LV rotation was 3.65 degrees, basal LV rotation proved to be 3.57 degrees leading to 0.08-degree LV apico-basal gradient suggesting counterclockwise LV “rigid body rotation”. In the remaining patients, both LV apical rotation (7.25±6.20 vs. 10.39±4.16 degrees, P

Introduction: An advanced, reliable and fast vehicle detection-and-tracking technique is proposed, implemented and tested. In this paper, an advanced-and-reliable vehicle detectionand- tracking technique is proposed and implemented. The Real-Time Vehicle Detection-and- Tracking (RT_VDT) technique is well suited for Advanced Driving Assistance Systems (ADAS) applications or Self-Driving Cars (SDC). Methods: The Real-Time Vehicle Detection-and-Tracking (RT_VDT) is proposed, and it is mainly a pipeline of reliable computer-vision and machine-learning algorithms that augment each other and take in raw RGB images to produce the required boundary boxes of the vehicles that appear in the front driving space of the car. The main emphasis is the careful fusion of the employed algorithms, where some of them work in parallel to strengthen each other in order to produce a precise and sophisticated real-time output. Results: The RT_VDT is tested and its performance is evaluated using actual road images and videos captured by the front-mounted camera of the car as well as on the KITTI benchmark. The evaluation of the RT_VDT shows that it reliably detects and tracks vehicle boundaries under various conditions. Discussion: Robust real-time vehicle detection and tracking is required for Advanced Driving Assistance Systems (ADAS) applications or Self-Driving Cars (SDC).

This paper aims to discuss fixed-time tracking control problem for a nonholonomic wheeled mobile robot based on visual servoing. At first, by making use of the pinhole camera model, the robot system model with uncalibrated camera parameters is given. Then, the tracking error system between the mobile robot and desired trajectory is proposed. Thirdly, on the basis of fixed-time control theory and Lyapunov stability analysis, fixed-time tracking control laws are proposed for the robot, which can make the robot achieve the desired value in a fixed time. Simulation results are given at the end.

Coastal ship tracking is significant for cargo transportation and route determination. However, there are few effective tracking methods for specialized ship tracking. Although Siamese networks have been commonly used for object tracking in the field of deep learning, the results for ship are not accurate due to the lack of contour and edge information. In addition, scale variation and seawater cause unstable ship movements, which aggravates the reduction in tracking accuracy. Therefore, we propose an enhanced SiamMask network for coastal ship tracking. Compared to the previous Siamese network, our algorithm has the following three advantages. (1) We apply the unity of visual object tracking and semi-supervised object segmentation to the ship tracking task, which completes target tracking while outputting edge shape information. (2) We propose a refined feature pyramid network, which utilizes a feature fusion module and Enhanced Residual Module (ERM) to solve the problems of scale variation in datasets. (3) We propose an attention-wise cross correlation with Multi-Dimension Attention Module (MDAM) to focus more on ship targets and suppress non-targets through autonomous learning at width, height and channel level, which creates a trade-off between the accuracy and the robustness of tracking algorithms. The experimental results show that our method achieves leading performance in LMD-TShips, outperforming most of the state-of-the-art trackers. Code is available at https://gitee.com/EnhancedSiamShipTracking/code.

A new variational Bayesian‐based adaptive distributed fusion unscented Kalman filter (ADFUKF‐VB) algorithm is proposed for the problem of state estimation in a distributed fusion target tracking system with unknown sensor measurement losses. First, the Bernoulli random variables are introduced as the judgement factors of the measurement losses in each local unscented Kalman filter (UKF) of the distributed fusion target tracking system, and the probability density function (PDF) of the measurement loss probability is modelled as a Beta distribution. Then, the variational Bayesian (VB) approach is used to infer the estimated variables in each local UKF. The measurement losses are judged according to the expectations of the Bernoulli random variables, and three ways are adopted to estimate the state vector based on the obtained judgement results. Finally, the covariance intersection (CI) fusion strategy is used to achieve the fusion of all local state estimates. The simulation results show that the proposed ADFUKF‐VB algorithm can accurately judge whether the measurement is lost and estimate the unknown measurement loss probability, moreover, effectively improve the accuracy of state estimation compared with the existing filtering algorithms with unknown measurement losses.

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.

Tracking moving objects in remote-sensing videos is becoming increasingly important in remote-sensing analysis. This letter presents a novel object tracking method for remote-sensing videos. We start with using the traditional robust principal component analysis (RPCA) model to extract the moving object from the background. To describe the continuity of moving objects in spatial and temporal directions, we incorporate a 3-D total variation (3DTV) regularization into the RPCA model. Considering that the background is not static and the captured videos will contain noise because of the instability of the sensing camera, our proposed method introduces a certain part of the function to model the noise and capture the changes in background. Experimental results on real videos provided by 2016 IEEE GRSS Data Fusion Contest and 2020 Hyperspectral Object Tracking Challenge demonstrate the advantages of the moving object-tracking method via 3-D TV.

The bottom tracking is to confirm the first bottom return signal in each ping to divide the data into the seabed area and the water column area, which is an essential part of side-scan sonar (SSS) data processing. More than that, SSS is usually affected by water flow or suspended solids, resulting in serious noises, which make the bottom tracking more difficult and complex. Some existing methods follow ideas such as abnormal point detection or filtering, resulting in unsatisfactory bottom tracking effects. Inspired by the semantic segmentation mission in deep learning, we innovatively transform the bottom tracking into a binary-class semantic segmentation mission on 1-D SSS data. Following this idea, we propose a semantic segmentation-based bottom tracking method and modify two image semantic segmentation models, SegNet and U-Net, so that they can achieve bottom tracking on 1-D SSS data. Benefiting from the large receptive field brought by convolution and down-sampling, our method has made significant progress in accuracy and antinoise performance compared with the existing method. According to the experimental result, our method has obvious improvement compared with the existing method on the testing set; not only that, our method also performs better on the unused data.

Multi-person tracking plays a vital role in intelligent video surveillance systems and has attracted researchers’ growing attention in recent years. This paper proposes a tracking-by-detection method to detect and track all existing persons in video sequences. The proposed method re-identifies detected persons in the latest video frame as observed persons in previous frames and thus generates their trajectories. Re-identification of the proposed approach uses a fusion of six distance metrics. Four metrics, i.e., position, scale, distance to estimated position, and tracklet continuity, are derived from two motion-based features, and two metrics, i.e., dominant colors and histogram of oriented gradients, are derived from corresponding appearance-based features. The proposed method performs tracking in two general steps per frame. In the first step, all persons in the video frame are detected using the state-of-the-art YOLOv3 object detector. In the second step, the re-identification algorithm generates correspondences between detected persons in the latest video frame and observed persons in previous frames, using the distance matrix built up from compound distances between all detected-observed person pairs. Experimental results show that our simple yet effective approach achieves significant performance in multi-person tracking compared to existing state-of-the-art methods.

Video synthetic aperture radar (SAR) has been found very useful in ground moving target indication (GMTI) and tracking. The dynamic shadows in video SAR imagery sequences indicate the real positions of moving targets, which can be utilized in target detection and tracking. Unfortunately, the shadow-based method often fails when the shadows are not sufficiently developed. On the other hand, the traditional energy-based GMTI methods exhibit performance degradation when SAR images of a moving target are distorted or smeared. Neither of these two methods can stand alone to provide robust detection and tracking of moving targets. This article presents a joint processing framework for video SAR GMTI and tracking by combining the target shadow and echo energy information, which effectively lowers the false alarm and miss-detection rate. This approach is very suitable for real-time surveillance of ground moving targets in a single-channel video SAR system. The proposed approach has been verified by using the simulated and the real video SAR data.

Multisensors multitargets tracking is an important task, and the difficulty is how to form the real trajectory of each target accurately. In this article, we construct a complete system for tracking highly maneuvering multitargets in the case of multisensors asynchronous sampling. Our system divides the entire tracking task into three modules: space-time calibration, point-trajectory data association, and trajectory data fusion. An improved least-squares (LS) virtual fusion method is proposed to correct the asynchronous sampling time, and the fast vector calibrates the multisensors' spatial state. In the point-trajectory data association module, an adaptive K-nearest neighbors (AK-NN) algorithm is proposed, which employs the adaptive threshold forming multiple trajectories. In trajectory data fusion, a CV+CT+S multimotion model is proposed with the multisensors' probabilistic data association filter (PDAF) algorithm to track highly maneuvering multitargets actively. The results show that our system performs accurately for moving maneuvering multitargets tracking in complex situations.

Object tracking approaches based on the Siamese network have demonstrated their huge potential in the remote sensing field recently. Nevertheless, due to the limited computing resource of aerial platforms and special challenges in aerial tracking, most existing Siamese-based methods can hardly meet the real-time and state-of-the-art performance simultaneously. Consequently, a novel Siamese-based method is proposed in this work for onboard real-time aerial tracking, i.e., SiamAPN. The proposed method is a no-prior two-stage method, i.e., Stage-1 for proposing adaptive anchors to enhance the ability of object perception and Stage-2 for fine-tuning the proposed anchors to obtain accurate results. Distinct from the traditional predefined anchors, the proposed anchors can adapt automatically to the tracking object. Besides, the internal information of adaptive anchors is utilized to feedback SiamAPN for enhancing the object perception. Attributing to the feature fusion network, different semantic information is integrated, enriching the information flow that is significant for robust aerial tracking. In the end, the regression and multiclassification operation refine the proposed anchors meticulously. Comprehensive evaluations on three well-known aerial tracking benchmarks have proven the superior performance of the presented approach. Moreover, to verify the practicability of the proposed method, SiamAPN is implemented onboard a typical embedded aerial tracking platform to conduct the real-world evaluations on specific aerial tracking scenarios, e.g., fast motion, long-term tracking, and low resolution. The results have demonstrated the efficiency and accuracy of the proposed approach, with a processing speed of over 30 frames/s. In addition, the image sequences in the real-world evaluations are collected and annotated as a new aerial tracking benchmark, i.e., UAVTrack112.