Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.8
3.9
Journals
Sensors
Special Issues
Object Tracking and Motion Analysis
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Object Tracking and Motion Analysis

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensing and Imaging".

Deadline for manuscript submissions: closed (16 September 2021) | Viewed by 41872

Special Issue Editor

Dr. SangMin Yoon

E-Mail Website
Guest Editor
Kookmin University, Seoul, Korea
Interests: computer vision, data fusion

Special Issue Information

Dear Colleagues,

Visual object tracking has been one of the most important topics in the field of computer vision and image processing. Deep-learning-based object-tracking algorithms especially have provided a robust performance compared to traditional object-tracking approaches. However, a large number of tracking algorithms still have problems to follow a moving object in a given image sequence, while simultaneously keeping track of target identities through the significant pose changes, illumination variations, and occlusions by focusing on finding appearance and motion models. Motion analysis and pose estimation are needed to understand the intention of the target objects. 

The main objective of this Special Issue is to analyze and measure the quantitative and qualitative performance of the visual object tracking and its 2D and 3D motion analysis using various sensors including cameras. Original papers describing completed and unpublished work that are not currently under review by any other journal, magazine or conference, are solicited.

Dr. SangMin Yoon
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • object tracking
  • motion analysis
  • pose estimation
  • sensor fusion

Published Papers (16 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

20 pages, 125434 KiB  
Article
Development of a Hybrid Method to Generate Gravito-Inertial Cues for Motion Platforms in Highly Immersive Environments
by Jose V. Riera, Sergio Casas, Marcos Fernández, Francisco Alonso and Sergio A. Useche
Sensors 2021, 21(23), 8079; https://doi.org/10.3390/s21238079 - 02 Dec 2021
Cited by 2 | Viewed by 2004
Abstract
Motion platforms have been widely used in Virtual Reality (VR) systems for decades to simulate motion in virtual environments, and they have several applications in emerging fields such as driving assistance systems, vehicle automation and road risk management. Currently, the development of new [...] Read more.
Motion platforms have been widely used in Virtual Reality (VR) systems for decades to simulate motion in virtual environments, and they have several applications in emerging fields such as driving assistance systems, vehicle automation and road risk management. Currently, the development of new VR immersive systems faces unique challenges to respond to the user’s requirements, such as introducing high-resolution 360° panoramic images and videos. With this type of visual information, it is much more complicated to apply the traditional methods of generating motion cues, since it is generally not possible to calculate the necessary corresponding motion properties that are needed to feed the motion cueing algorithms. For this reason, this paper aims to present a new method for generating non-real-time gravito-inertial cues with motion platforms using a system fed both with computer-generated—simulation-based—images and video imagery. It is a hybrid method where part of the gravito-inertial cues—those with acceleration information—are generated using a classical approach through the application of physical modeling in a VR scene utilizing washout filters, and part of the gravito-inertial cues—the ones coming from recorded images and video, without acceleration information—were generated ad hoc in a semi-manual way. The resulting motion cues generated were further modified according to the contributions of different experts based on a successive approximation—Wideband Delphi-inspired—method. The subjective evaluation of the proposed method showed that the motion signals refined with this method were significantly better than the original non-refined ones in terms of user perception. The final system, developed as part of an international road safety education campaign, could be useful for developing further VR-based applications for key fields such as driving assistance, vehicle automation and road crash prevention. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

21 pages, 69642 KiB  
Article
Channel Exchanging for RGB-T Tracking
by Long Zhao, Meng Zhu, Honge Ren and Lingjixuan Xue
Sensors 2021, 21(17), 5800; https://doi.org/10.3390/s21175800 - 28 Aug 2021
Cited by 3 | Viewed by 2119
Abstract
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 [...] Read more.
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. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

22 pages, 5631 KiB  
Article
Spatio-Temporal Context, Correlation Filter and Measurement Estimation Collaboration Based Visual Object Tracking
by Khizer Mehmood, Abdul Jalil, Ahmad Ali, Baber Khan, Maria Murad, Khalid Mehmood Cheema and Ahmad H. Milyani
Sensors 2021, 21(8), 2841; https://doi.org/10.3390/s21082841 - 17 Apr 2021
Cited by 6 | Viewed by 2306
Abstract
Despite eminent progress in recent years, various challenges associated with object tracking algorithms such as scale variations, partial or full occlusions, background clutters, illumination variations are still required to be resolved with improved estimation for real-time applications. This paper proposes a robust and [...] Read more.
Despite eminent progress in recent years, various challenges associated with object tracking algorithms such as scale variations, partial or full occlusions, background clutters, illumination variations are still required to be resolved with improved estimation for real-time applications. This paper proposes a robust and fast algorithm for object tracking based on spatio-temporal context (STC). A pyramid representation-based scale correlation filter is incorporated to overcome the STC’s inability on the rapid change of scale of target. It learns appearance induced by variations in the target scale sampled at a different set of scales. During occlusion, most correlation filter trackers start drifting due to the wrong update of samples. To prevent the target model from drift, an occlusion detection and handling mechanism are incorporated. Occlusion is detected from the peak correlation score of the response map. It continuously predicts target location during occlusion and passes it to the STC tracking model. After the successful detection of occlusion, an extended Kalman filter is used for occlusion handling. This decreases the chance of tracking failure as the Kalman filter continuously updates itself and the tracking model. Further improvement to the model is provided by fusion with average peak to correlation energy (APCE) criteria, which automatically update the target model to deal with environmental changes. Extensive calculations on the benchmark datasets indicate the efficacy of the proposed tracking method with state of the art in terms of performance analysis. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

13 pages, 4774 KiB  
Communication
Effect of Enhanced ADAS Camera Capability on Traffic State Estimation
by Hoe Kyoung Kim, Younshik Chung and Minjeong Kim
Sensors 2021, 21(6), 1996; https://doi.org/10.3390/s21061996 - 12 Mar 2021
Cited by 3 | Viewed by 2329
Abstract
Traffic flow data, such as flow, density and speed, are crucial for transportation planning and traffic system operation. Recently, a novel traffic state estimating method was proposed using the distance to a leading vehicle measured by an advanced driver assistance system (ADAS) camera. [...] Read more.
Traffic flow data, such as flow, density and speed, are crucial for transportation planning and traffic system operation. Recently, a novel traffic state estimating method was proposed using the distance to a leading vehicle measured by an advanced driver assistance system (ADAS) camera. This study examined the effect of an ADAS camera with enhanced capabilities on traffic state estimation using image-based vehicle identification technology. Considering the realistic distance error of the ADAS camera from the field experiment, a microscopic simulation model, VISSIM, was employed with multiple underlying parameters such as the number of lanes, traffic demand, the penetration rate of ADAS vehicles and the spatiotemporal range of the estimation area. Although the enhanced functions of the ADAS camera did not affect the accuracy of the traffic state estimates significantly, the ADAS camera can be used for traffic state estimation. Furthermore, the vehicle identification distance of the ADAS camera and traffic conditions with more lanes did not always ensure better accuracy of the estimates. Instead, it is recommended that transportation planners and traffic engineering practitioners carefully select the relevant parameters and their range to ensure a certain level of accuracy for traffic state estimates that suit their purposes. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

20 pages, 9057 KiB  
Article
Learning Local–Global Multiple Correlation Filters for Robust Visual Tracking with Kalman Filter Redetection
by Jianming Zhang, Yang Liu, Hehua Liu and Jin Wang
Sensors 2021, 21(4), 1129; https://doi.org/10.3390/s21041129 - 05 Feb 2021
Cited by 50 | Viewed by 2894
Abstract
Visual object tracking is a significant technology for camera-based sensor networks applications. Multilayer convolutional features comprehensively used in correlation filter (CF)-based tracking algorithms have achieved excellent performance. However, there are tracking failures in some challenging situations because ordinary features are not able to [...] Read more.
Visual object tracking is a significant technology for camera-based sensor networks applications. Multilayer convolutional features comprehensively used in correlation filter (CF)-based tracking algorithms have achieved excellent performance. However, there are tracking failures in some challenging situations because ordinary features are not able to well represent the object appearance variations and the correlation filters are updated irrationally. In this paper, we propose a local–global multiple correlation filters (LGCF) tracking algorithm for edge computing systems capturing moving targets, such as vehicles and pedestrians. First, we construct a global correlation filter model with deep convolutional features, and choose horizontal or vertical division according to the aspect ratio to build two local filters with hand-crafted features. Then, we propose a local–global collaborative strategy to exchange information between local and global correlation filters. This strategy can avoid the wrong learning of the object appearance model. Finally, we propose a time-space peak to sidelobe ratio (TSPSR) to evaluate the stability of the current CF. When the estimated results of the current CF are not reliable, the Kalman filter redetection (KFR) model would be enabled to recapture the object. The experimental results show that our presented algorithm achieves better performances on OTB-2013 and OTB-2015 compared with the other latest 12 tracking algorithms. Moreover, our algorithm handles various challenges in object tracking well. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

17 pages, 1760 KiB  
Article
Efficient and Practical Correlation Filter Tracking
by Chengfei Zhu, Shan Jiang, Shuxiao Li and Xiaosong Lan
Sensors 2021, 21(3), 790; https://doi.org/10.3390/s21030790 - 25 Jan 2021
Cited by 4 | Viewed by 1781
Abstract
Visual tracking is a basic task in many applications. However, the heavy computation and low speed of many recent trackers limit their applications in some computing power restricted scenarios. On the other hand, the simple update scheme of most correlation filter-based trackers restricts [...] Read more.
Visual tracking is a basic task in many applications. However, the heavy computation and low speed of many recent trackers limit their applications in some computing power restricted scenarios. On the other hand, the simple update scheme of most correlation filter-based trackers restricts their robustness during target deformation and occlusion. In this paper, we explore the update scheme of correlation filter-based trackers and propose an efficient and adaptive training sample update scheme. The training sample extracted in each frame is updated to the training set according to its distance between existing samples measured with a difference hashing algorithm or discarded according to tracking result reliability. In addition, we expand our new tracker to long-term tracking. On the basis of the proposed model updating mechanism, we propose a new tracking state discrimination mechanism to accurately judge tracking failure, and resume tracking after the target is recovered. Experiments on OTB-2015, Temple Color 128 and UAV123 (including UAV20L) demonstrate that our tracker performs favorably against state-of-the-art trackers with light computation and runs over 100 fps on desktop computer with Intel i7-8700 CPU(3.2 GHz). Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

18 pages, 2996 KiB  
Article
Real-Time Multiobject Tracking Based on Multiway Concurrency
by Xuan Gong, Zichun Le, Yukun Wu and Hui Wang
Sensors 2021, 21(3), 685; https://doi.org/10.3390/s21030685 - 20 Jan 2021
Cited by 4 | Viewed by 2500
Abstract
This paper explored a pragmatic approach to research the real-time performance of a multiway concurrent multiobject tracking (MOT) system. At present, most research has focused on the tracking of single-image sequences, but in practical applications, multiway video streams need to be processed in [...] Read more.
This paper explored a pragmatic approach to research the real-time performance of a multiway concurrent multiobject tracking (MOT) system. At present, most research has focused on the tracking of single-image sequences, but in practical applications, multiway video streams need to be processed in parallel by MOT systems. There have been few studies on the real-time performance of multiway concurrent MOT systems. In this paper, we proposed a new MOT framework to solve multiway concurrency scenario based on a tracking-by-detection (TBD) model. The new framework mainly focuses on concurrency and real-time based on limited computing and storage resources, while considering the algorithm performance. For the former, three aspects were studied: (1) Expanded width and depth of tracking-by-detection model. In terms of width, the MOT system can support the process of multiway video sequence at the same time; in terms of depth, image collectors and bounding box collectors were introduced to support batch processing. (2) Considering the real-time performance and multiway concurrency ability, we proposed one kind of real-time MOT algorithm based on directly driven detection. (3) Optimization of system level—we also utilized the inference optimization features of NVIDIA TensorRT to accelerate the deep neural network (DNN) in the tracking algorithm. To trade off the performance of the algorithm, a negative sample (false detection sample) filter was designed to ensure tracking accuracy. Meanwhile, the factors that affect the system real-time performance and concurrency were studied. The experiment results showed that our method has a good performance in processing multiple concurrent real-time video streams. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

16 pages, 3259 KiB  
Article
SynPo-Net—Accurate and Fast CNN-Based 6DoF Object Pose Estimation Using Synthetic Training
by Yongzhi Su, Jason Rambach, Alain Pagani and Didier Stricker
Sensors 2021, 21(1), 300; https://doi.org/10.3390/s21010300 - 05 Jan 2021
Cited by 10 | Viewed by 3838
Abstract
Estimation and tracking of 6DoF poses of objects in images is a challenging problem of great importance for robotic interaction and augmented reality. Recent approaches applying deep neural networks for pose estimation have shown encouraging results. However, most of them rely on training [...] Read more.
Estimation and tracking of 6DoF poses of objects in images is a challenging problem of great importance for robotic interaction and augmented reality. Recent approaches applying deep neural networks for pose estimation have shown encouraging results. However, most of them rely on training with real images of objects with severe limitations concerning ground truth pose acquisition, full coverage of possible poses, and training dataset scaling and generalization capability. This paper presents a novel approach using a Convolutional Neural Network (CNN) trained exclusively on single-channel Synthetic images of objects to regress 6DoF object Poses directly (SynPo-Net). The proposed SynPo-Net is a network architecture specifically designed for pose regression and a proposed domain adaptation scheme transforming real and synthetic images into an intermediate domain that is better fit for establishing correspondences. The extensive evaluation shows that our approach significantly outperforms the state-of-the-art using synthetic training in terms of both accuracy and speed. Our system can be used to estimate the 6DoF pose from a single frame, or be integrated into a tracking system to provide the initial pose. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

12 pages, 1779 KiB  
Article
Wavelet Decomposition in Analysis of Impact of Virtual Reality Head Mounted Display Systems on Postural Stability
by Piotr Wodarski, Jacek Jurkojć and Marek Gzik
Sensors 2020, 20(24), 7138; https://doi.org/10.3390/s20247138 - 12 Dec 2020
Cited by 14 | Viewed by 2521
Abstract
This study investigated how spatial projection systems influences body balance including postural stability. Analyzing precisely defined frequency bands of movements of the center of pressure makes it possible to determine the effectiveness of the balance system’s response to disruptions and disorders and may [...] Read more.
This study investigated how spatial projection systems influences body balance including postural stability. Analyzing precisely defined frequency bands of movements of the center of pressure makes it possible to determine the effectiveness of the balance system’s response to disruptions and disorders and may be used as an indicator in the diagnosis of motor dysfunction. The study involved 28 participants for whom the center of pressure was assessed in a test with open eyes, closed eyes and with virtual reality projection. Percent distributions of energy during wavelet decomposition were calculated. Changes in body stability were determined for the virtual reality tests and these changes were classified as an intermediate value between the open-eyes test and the closed-eyes test. The results indicate the importance of using safety support systems in therapies involving Virtual Reality. The results also show the necessity of measurements times in stabilographic evaluations in order to conduct a more thorough analysis of very low frequencies of the center of pressure signal. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

29 pages, 27753 KiB  
Article
TensorMoG: A Tensor-Driven Gaussian Mixture Model with Dynamic Scene Adaptation for Background Modelling
by Synh Viet-Uyen Ha, Nhat Minh Chung, Hung Ngoc Phan and Cuong Tien Nguyen
Sensors 2020, 20(23), 6973; https://doi.org/10.3390/s20236973 - 06 Dec 2020
Cited by 7 | Viewed by 3496
Abstract
Decades of ongoing research have shown that background modelling is a very powerful technique, which is used in intelligent surveillance systems, in order to extract features of interest, known as foregrounds. In order to work with the dynamic nature of different scenes, many [...] Read more.
Decades of ongoing research have shown that background modelling is a very powerful technique, which is used in intelligent surveillance systems, in order to extract features of interest, known as foregrounds. In order to work with the dynamic nature of different scenes, many techniques of background modelling adopted the unsupervised approach of Gaussian Mixture Model with an iterative paradigm. Although the technique has had much success, a problem occurs in cases of sudden scene changes with high variation (e.g., illumination changes, camera jittering) that the model unknowingly and unnecessarily takes into account those effects and distorts the results. Therefore, this paper proposes an unsupervised, parallelized, and tensor-based approach that algorithmically works with entropy estimations. These entropy estimations are used in order to assess the uncertainty level of a constructed background, which predicts both the present and future variations from the inputs, thereby opting to use either the incoming frames to update the background or simply discard them. Our experiments suggest that this method is highly integrable into a surveillance system that consists of other functions and can be competitive with state-of-the-art methods in terms of processing speed. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

18 pages, 8557 KiB  
Article
LPCF: Robust Correlation Tracking via Locality Preserving Tracking Validation
by Yixuan Zhou, Weimin Zhang, Yongliang Shi, Ziyu Wang, Fangxing Li and Qiang Huang
Sensors 2020, 20(23), 6853; https://doi.org/10.3390/s20236853 - 30 Nov 2020
Cited by 1 | Viewed by 1618
Abstract
In visual tracking, the tracking model must be updated online, which often leads to undesired inclusion of corrupted training samples, and hence inducing tracking failure. We present a locality preserving correlation filter (LPCF) integrating a novel and generic decontamination approach, which mitigates the [...] Read more.
In visual tracking, the tracking model must be updated online, which often leads to undesired inclusion of corrupted training samples, and hence inducing tracking failure. We present a locality preserving correlation filter (LPCF) integrating a novel and generic decontamination approach, which mitigates the model drift problem. Our decontamination approach maintains the local neighborhood feature points structures of the bounding box center. This proposed tracking-result validation approach models not only the spatial neighborhood relationship but also the topological structures of the bounding box center. Additionally, a closed-form solution to our approach is derived, which makes the tracking-result validation process could be accomplished in only milliseconds. Moreover, a dimensionality reduction strategy is introduced to improve the real-time performance of our translation estimation component. Comprehensive experiments are performed on OTB-2015, LASOT, TrackingNet. The experimental results show that our decontamination approach remarkably improves the overall performance by 6.2%, 12.6%, and 3%, meanwhile, our complete algorithm improves the baseline by 27.8%, 34.8%, and 15%. Finally, our tracker achieves the best performance among most existing decontamination trackers under the real-time requirement. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Graphical abstract

17 pages, 4015 KiB  
Article
Influence of Neighborhood Size and Cross-Correlation Peak-Fitting Method on Location Accuracy
by María-Baralida Tomás, Belén Ferrer and David Mas
Sensors 2020, 20(22), 6596; https://doi.org/10.3390/s20226596 - 18 Nov 2020
Cited by 6 | Viewed by 1744
Abstract
A known technique to obtain subpixel resolution by using object tracking through cross-correlation consists of interpolating the obtained correlation function and then refining peak location. Although the technique provides accurate results, peak location is usually biased toward the closest integer coordinate. This effect [...] Read more.
A known technique to obtain subpixel resolution by using object tracking through cross-correlation consists of interpolating the obtained correlation function and then refining peak location. Although the technique provides accurate results, peak location is usually biased toward the closest integer coordinate. This effect is known as the peak-locking error and it strongly limits this calculation technique’s experimental accuracy. This error may differ depending on the scene and algorithm used to fit and interpolate the correlation peak, but in general, it may be attributed to a sampling problem and the presence of aliasing. Many studies in the literature analyze this effect in the Fourier domain. Here, we propose an alternative analysis on the spatial domain. According to our interpretation, the peak-locking error may be produced by a non-symmetrical sample distribution, thus provoking a bias in the result. According to this, the peak interpolant function, the size of the local domain and low-pass filters play a relevant role in diminishing the error. Our study explores these effects on different samples taken from the DIC Challenge database, and the results show that, in general, peak fitting with a Gaussian function on a relatively large domain provides the most accurate results. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

20 pages, 5031 KiB  
Article
Study on the Moving Target Tracking Based on Vision DSP
by Xuan Gong, Zichun Le, Hui Wang and Yukun Wu
Sensors 2020, 20(22), 6494; https://doi.org/10.3390/s20226494 - 13 Nov 2020
Cited by 6 | Viewed by 2046
Abstract
The embedded visual tracking system has higher requirements for real-time performance and system resources, and this is a challenge for visual tracking systems with available hardware resources. The major focus of this study is evaluating the results of hardware optimization methods. These optimization [...] Read more.
The embedded visual tracking system has higher requirements for real-time performance and system resources, and this is a challenge for visual tracking systems with available hardware resources. The major focus of this study is evaluating the results of hardware optimization methods. These optimization techniques provide efficient utilization based on limited hardware resources. This paper also uses a pragmatic approach to investigate the real-time performance effect by implementing and optimizing a kernel correlation filter (KCF) tracking algorithm based on a vision digital signal processor (vision DSP). We examine and analyze the impact factors of the tracking system, which include DP (data parallelism), IP (instruction parallelism), and the characteristics of parallel processing of the DSP core and iDMA (integrated direct memory access). Moreover, we utilize a time-sharing strategy to increase the system runtime speed. These research results are also applicable to other machine vision algorithms. In addition, we introduced a scale filter to overcome the disadvantages of KCF for scale transformation. The experimental results demonstrate that the use of system resources and real-time tracking speed also satisfies the expected requirements, and the tracking algorithm with a scale filter can realize almost the same accuracy as the DSST (discriminative scale space tracking) algorithm under a vision DSP environment. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

20 pages, 6755 KiB  
Article
Application of Crowd Simulations in the Evaluation of Tracking Algorithms
by Michał Staniszewski, Paweł Foszner, Karol Kostorz, Agnieszka Michalczuk, Kamil Wereszczyński, Michał Cogiel, Dominik Golba, Konrad Wojciechowski and Andrzej Polański
Sensors 2020, 20(17), 4960; https://doi.org/10.3390/s20174960 - 02 Sep 2020
Cited by 12 | Viewed by 2730
Abstract
Tracking and action-recognition algorithms are currently widely used in video surveillance, monitoring urban activities and in many other areas. Their development highly relies on benchmarking scenarios, which enable reliable evaluations/improvements of their efficiencies. Presently, benchmarking methods for tracking and action-recognition algorithms rely on [...] Read more.
Tracking and action-recognition algorithms are currently widely used in video surveillance, monitoring urban activities and in many other areas. Their development highly relies on benchmarking scenarios, which enable reliable evaluations/improvements of their efficiencies. Presently, benchmarking methods for tracking and action-recognition algorithms rely on manual annotation of video databases, prone to human errors, limited in size and time-consuming. Here, using gained experiences, an alternative benchmarking solution is presented, which employs methods and tools obtained from the computer-game domain to create simulated video data with automatic annotations. Presented approach highly outperforms existing solutions in the size of the data and variety of annotations possible to create. With proposed system, a potential user can generate a sequence of random images involving different times of day, weather conditions, and scenes for use in tracking evaluation. In the design of the proposed tool, the concept of crowd simulation is used and developed. The system is validated by comparisons to existing methods. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

16 pages, 3887 KiB  
Article
A Compact High-Speed Image-Based Method for Measuring the Longitudinal Motion of Living Tissues
by Ruilin Yang, Heqin Liao, Weng Ma, Jinhua Li and Shuxin Wang
Sensors 2020, 20(16), 4573; https://doi.org/10.3390/s20164573 - 14 Aug 2020
Cited by 1 | Viewed by 2198
Abstract
Intraoperative imaging of living tissue at the cell level by endomicroscopy might help surgeons optimize surgical procedures and provide individualized treatments. However, the resolution of the microscopic image is limited by the motion of living tissue caused by heartbeat and respiration. An active [...] Read more.
Intraoperative imaging of living tissue at the cell level by endomicroscopy might help surgeons optimize surgical procedures and provide individualized treatments. However, the resolution of the microscopic image is limited by the motion of living tissue caused by heartbeat and respiration. An active motion compensation (AMC) strategy has been recognized as an effective way to reduce, or even eliminate, the influence of tissue movement for intravital fluorescence microscopy (IVM). To realize the AMC system, a high-speed sensor for measuring the motion of tissues is needed. At present, state-of-the-art commercialized displacement sensors are not suitable to apply in minimally invasive imaging instruments to measure the motion of living tissues because of the size problem, range of measurement or the update rate. In this study, a compact high-speed image-based method for measuring the longitudinal motion of living tissues is proposed. The complexity of the proposed method is the same as that of the traditional wide-field fluorescent microscopy (WFFM) system, which makes it easy to be miniaturized and integrated into a minimally invasive imaging instrument. Experimental results reveal that the maximum indication error, range of measurement and the sensitivity of the laboratory-built experimental prototype is 150 μm, 6 mm and −211.46 mm−1 respectively. Experimental results indicate that the proposed optical method is expected to be used in minimally invasive imaging instruments to build an AMC system. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

19 pages, 2948 KiB  
Article
Future-Frame Prediction for Fast-Moving Objects with Motion Blur
by Dohae Lee, Young Jin Oh and In-Kwon Lee
Sensors 2020, 20(16), 4394; https://doi.org/10.3390/s20164394 - 06 Aug 2020
Cited by 1 | Viewed by 4230
Abstract
We propose a deep neural network model that recognizes the position and velocity of a fast-moving object in a video sequence and predicts the object’s future motion. When filming a fast-moving subject using a regular camera rather than a super-high-speed camera, there is [...] Read more.
We propose a deep neural network model that recognizes the position and velocity of a fast-moving object in a video sequence and predicts the object’s future motion. When filming a fast-moving subject using a regular camera rather than a super-high-speed camera, there is often severe motion blur, making it difficult to recognize the exact location and speed of the object in the video. Additionally, because the fast moving object usually moves rapidly out of the camera’s field of view, the number of captured frames used as input for future-motion predictions should be minimized. Our model can capture a short video sequence of two frames with a high-speed moving object as input, use motion blur as additional information to recognize the position and velocity of the object, and predict the video frame containing the future motion of the object. Experiments show that our model has significantly better performance than existing future-frame prediction models in determining the future position and velocity of an object in two physical scenarios where a fast-moving two-dimensional object appears. Full article
(This article belongs to the Special Issue Object Tracking and Motion Analysis)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-16
Back to TopTop