Visual Tracking Technology Research Articles

FQTrack:Object Tracking Method Based on a Feature-Enhanced Memory Network and Memory Quality Selection Mechanism

Visual object tracking technology is widely used in intelligent security, automatic driving and other fields, and also plays an important role in frontier fields such as human–computer interactions and virtual reality. The memory network improves the stability and accuracy of tracking by using historical frame information to assist in the positioning of the current frame in object tracking. However, the memory network is still insufficient in feature mining and the accuracy and robustness of the model may be reduced when using noisy observation samples to update it. In view of the above problems, we propose a new tracking framework, which uses the attention mechanism to establish a feature-enhanced memory network and combines cross-attention to aggregate the spatial and temporal context information of the target. The former introduces spatio-temporal adaptive attention and cross-spatial attention, embeds spatial location information into channels, realizes multi-scale feature fusion, dynamically emphasizes target location information, and obtains richer feature maps. The latter guides the tracker to focus on the area with the largest amount of information in the current frame to better distinguish the foreground and background. In addition, through the memory quality selection mechanism, the accuracy and richness of the feature samples are improved, thereby enhancing the adaptability and discrimination ability of the tracking model. Experiments on benchmark test sets such as OTB2015, TrackingNet, GOT-10k, LaSOT and UAV 123 show that this method achieves comparable performance with advanced trackers.

MATI: Multimodal Adaptive Tracking Integrator for Robust Visual Object Tracking.

Visual object tracking, pivotal for applications like earth observation and environmental monitoring, encounters challenges under adverse conditions such as low light and complex backgrounds. Traditional tracking technologies often falter, especially when tracking dynamic objects like aircraft amidst rapid movements and environmental disturbances. This study introduces an innovative adaptive multimodal image object-tracking model that harnesses the capabilities of multispectral image sensors, combining infrared and visible light imagery to significantly enhance tracking accuracy and robustness. By employing the advanced vision transformer architecture and integrating token spatial filtering (TSF) and crossmodal compensation (CMC), our model dynamically adjusts to diverse tracking scenarios. Comprehensive experiments conducted on a private dataset and various public datasets demonstrate the model's superior performance under extreme conditions, affirming its adaptability to rapid environmental changes and sensor limitations. This research not only advances visual tracking technology but also offers extensive insights into multisource image fusion and adaptive tracking strategies, establishing a robust foundation for future enhancements in sensor-based tracking systems.

Advances in twin network research in visual tracking technology

Advances in twin network research in visual tracking technology

Design of smart operating table based on HCI and virtual visual tracking technology

Design of smart operating table based on HCI and virtual visual tracking technology

Anti-Similar Visual Target Tracking Algorithm Based on Filter Peak Guidance and Fusion Network

Visual tracking is a key research area in computer vision, as tracking technology is increasingly being applied in daily life, it has high-research significance. Visual tracking technology usually faces various challenging interference factors, among which, a similar background is one of the factors that has a greater impact on the tracking process. Kernelized Correlation Filter (KCF) tracking algorithm can track targets quickly by using circulant matrix, and has good tracking effect, so it is widely used in the tracking field. However, when the target is interfered by similar objects, the filter template in KCF cannot effectively distinguish between the target and the interfering object. This is because the filter only uses the texture gradient feature as the description object of the target, which will make the KCF algorithm extremely sensitive to the change of the target; therefore, the filter has difficultly making a judgment in the unstable scene, cannot accurately describe the target state, and finally leads to tracking failure. Therefore, this paper fuses Color Names (CN) on the basis of the original Histogram of Oriented Gradients (HOG) feature of KCF, which can obtain a more comprehensive feature representation, and realize the application of combined features to improve the anti-interference ability of KCF in complex scenes. In addition, this paper also uses the peak response of correlation filtering as the judgment condition to determine whether the current tracking result is stable. When the filter is in an unstable tracking state, the proposed algorithm will select the value with high confidence from its multiple responses as the candidate target of the Siamese network, and the deep learning network is used as the incremental learning method of the filter. The Channel Attention is introduced into the network layer, so that the network can adaptively reason and adjust the extracted universal features, and the enhanced feature information is used as the final discriminant basis. Finally, according to the response, the target with the smallest error compared with the target template is selected from multiple candidate targets as the final tracking result. The experimental results show that the average accuracy and average success rate of the proposed algorithm are significantly improved compared with the classical tracking algorithm, especially in dealing with similar target interference.

Adversarial Examples in Visual Object Tracking in Satellite Videos: Cross-Frame Momentum Accumulation for Adversarial Examples Generation

The visual object tracking technology of remote sensing images has important applications in areas with high safety performance such as national defense, homeland security, and intelligent transportation in smart cities. However, previous research demonstrates that adversarial examples pose a significant threat to remote sensing imagery. This article first explores the impact of adversarial examples in the field of visual object tracking in remote sensing imagery. We design a classification- and regression-based loss function for the popular Siamese RPN series of visual object tracking models and use the PGD gradient-based attack method to generate adversarial examples. Additionally, we consider the temporal consistency of video frames and design an adversarial examples attack method based on momentum continuation. We evaluate our method on the remote sensing visual object tracking datasets SatSOT and VISO and the traditional datasets OTB100 and UAV123. The experimental results show that our approach can effectively reduce the performance of the tracker.

An Automated Skill Assessment Framework Based on Visual Motion Signals and a Deep Neural Network in Robot-Assisted Minimally Invasive Surgery.

Surgical skill assessment can quantify the quality of the surgical operation via the motion state of the surgical instrument tip (SIT), which is considered one of the effective primary means by which to improve the accuracy of surgical operation. Traditional methods have displayed promising results in skill assessment. However, this success is predicated on the SIT sensors, making these approaches impractical when employing the minimally invasive surgical robot with such a tiny end size. To address the assessment issue regarding the operation quality of robot-assisted minimally invasive surgery (RAMIS), this paper proposes a new automatic framework for assessing surgical skills based on visual motion tracking and deep learning. The new method innovatively combines vision and kinematics. The kernel correlation filter (KCF) is introduced in order to obtain the key motion signals of the SIT and classify them by using the residual neural network (ResNet), realizing automated skill assessment in RAMIS. To verify its effectiveness and accuracy, the proposed method is applied to the public minimally invasive surgical robot dataset, the JIGSAWS. The results show that the method based on visual motion tracking technology and a deep neural network model can effectively and accurately assess the skill of robot-assisted surgery in near real-time. In a fairly short computational processing time of 3 to 5 s, the average accuracy of the assessment method is 92.04% and 84.80% in distinguishing two and three skill levels. This study makes an important contribution to the safe and high-quality development of RAMIS.

Efficacy of Computerized Visual Tracking Technology Throughout Concussion Recovery: A Case Series

<h3>Research Objectives</h3> To compare results of computerized eye tracking assessments to concussion patient reported outcomes and other objective oculomotor function tests throughout the concussion recovery. <h3>Design</h3> Retrospective case series of three physical therapy plan of cares completed between April 2021 and September 2021. <h3>Setting</h3> Outpatient physical rehabilitation clinic. <h3>Participants</h3> Included three female patients (mean age 34.7 years). Brain injury conditions vary from sub-acute to chronic. Selected via volunteer sample. <h3>Interventions</h3> Manual therapy, postural stabilization, aerobic conditioning, ocular motor training, and balance exercises. Average physical therapy visit count of 15.3. <h3>Main Outcome Measures</h3> RightEye™ Dynamic Visual Acuity (DVA) Test, Concussion Clinical Profile Screen (CCPS), Clinical DVA, Somatosensory Organization Test (SOT), and Vestibular Ocular Motor Screen (VOMS). <h3>Results</h3> All final RightEye™ DVA composite scores declined or had minimal change compared to evaluation scores. Initial VOMS similar findings to initial RightEye™ DVA subdomain scores. CCPS composite and ocular profile scores improved with each re-assessment. Clinical DVA scores improved and within normal limits at final assessments. 2/3 of participants had normal composite scores on SOT at re-evaluation. <h3>Conclusions</h3> In this case series subjective recovery of concussion symptoms did not correlate with performance on computerized ocular motor assessments. There were conflicting results on several other objective tests compared to results of RightEye™ DVA. Some confounding factors that may have impacted scores are co-morbidities of cervical pain, anxiety, depression, and migraine. Even though the assessments did not correlate, it is important to note the tracking assessments and games were engaging and offered repetition. In conclusion, clinicians should not rely on one single measurement for concussion screening and determination of readiness for return to prior activities. More research is needed to determine the efficacy of computerized visual tracking assessments for individuals with complex medical history and post-concussion. <h3>Author(s) Disclosures</h3> The author has nothing to disclose.

Surgical instrument detection and tracking technologies: Automating dataset labeling for surgical skill assessment.

Surgical skills can be improved by continuous surgical training and feedback, thus reducing adverse outcomes while performing an intervention. With the advent of new technologies, researchers now have the tools to analyze surgical instrument motion to differentiate surgeons' levels of technical skill. Surgical skills assessment is time-consuming and prone to subjective interpretation. The surgical instrument detection and tracking algorithm analyzes the image captured by the surgical robotic endoscope and extracts the movement and orientation information of a surgical instrument to provide surgical navigation. This information can be used to label raw surgical video datasets that are used to form an action space for surgical skill analysis. Instrument detection and tracking is a challenging problem in MIS, including robot-assisted surgeries, but vision-based approaches provide promising solutions with minimal hardware integration requirements. This study offers an overview of the developments of assessment systems for surgical intervention analysis. The purpose of this study is to identify the research gap and make a leap in developing technology to automate the incorporation of new surgical skills. A prime factor in automating the learning is to create datasets with minimal manual intervention from raw surgical videos. This review encapsulates the current trends in artificial intelligence (AI) based visual detection and tracking technologies for surgical instruments and their application for surgical skill assessment.

Application of Computational Digital Technology in the Improvement of Art Creation

In order to promote the simultaneous development of art creation and modern information technology, this paper studies the application of digital technology in the improvement of art creation. Moreover, this paper combines image analysis technology and computer simulation technology to improve point cloud digital technology and build a human-computer interaction system for art creation based on digital technology. The system uses the visual computer to communicate, gives instructions through actions, and uses the computer’s visual dynamic tracking technology to make the computer recognize the instructions and information sent by the user so as to provide visual feedback. In addition, this visual interactive art creation application uses the real-time nature of the camera to capture real images of interaction between the environment and the work and then interacts the captured images with virtual bubbles. Finally, this paper studies the method proposed in this paper through case analysis. The research results show that digital technology can effectively promote the development of art creation.

The Pacific as the world’s greatest theater of bird migration: Extreme flights spark questions about physiological capabilities, behavior, and the evolution of migratory pathways

AbstractThe Pacific Basin, by virtue of its vastness and its complex aeroscape, provides unique opportunities to address questions about the behavioral and physiological capabilities and mechanisms through which birds can complete spectacular flights. No longer is the Pacific seen just as a formidable barrier between terrestrial habitats in the north and the south, but rather as a gateway for specialized species, such as shorebirds, to make a living on hemispherically distributed seasonal resources. This recent change in perspective is dramatic, and the research that underpins it has presented new opportunities to learn about phenomena that often challenge a sense of normal. Ancient Polynesians were aware of the seasonal passage of shorebirds and other landbirds over the Pacific Ocean, incorporating these observations into their navigational “tool kit” as they explored and colonized the Pacific. Some ten centuries later, systematic visual observations and tracking technology have revealed much about movement of these shorebirds, especially the enormity of their individual nonstop flights. This invites a broad suite of questions, often requiring comparative studies with bird migration across other ocean basins, or across continents. For example, how do birds manage many days of nonstop exercise apparently without sleep? What mechanisms explain birds acting as if they possess a Global Positioning System? How do such extreme migrations evolve? Through advances in both theory and tracking technology, biologists are poised to greatly expand the horizons of movement ecology as we know it. In this integrative review, we present a series of intriguing questions about trans-Pacific migrant shorebirds and summarize recent advances in knowledge about migratory behavior operating at temporal scales ranging from immediate decisions during a single flight, to adaptive learning throughout a lifetime, to evolutionary development of migratory pathways. Recent advances in this realm should stimulate future research across the globe and across a broad array of disciplines.

Psychological Cognitive Factors Affecting Visual Behavior and Satisfaction Preference for Forest Recreation Space

Background: People are paying increasing attention to urban forest landscapes, and recreational landscape spaces (providing recreation and viewing functions) are an important part of the urban forest landscape. Visual tracking technology is a flexible and accurate modern research method. When this technology is applied to forest landscape evaluation, it can assist in explaining the content that could not be studied in depth in the past and has high application value. However, although an eye tracker can tell us what the user is looking at, it cannot tell us why they are looking at it or how they feel after seeing it. To this end, we combined a 7-point spatial cognition questionnaire and satisfaction preference to understand the visual behavior (fixation point time, number of fixation points, etc.) and preference satisfactions of users in recreational landscape spaces to help designers understand what elements attract people’s visual attention and improve the design of these spaces. Methods: We used eye-tracking and cognitive questionnaires to obtain experimental data and used factor analysis and linear regression analysis of SPPS 23.0 to analyze data. Main purpose: Clarify the factors affecting people’s visual behavior and satisfaction preferences in forest recreation spaces to provide theoretical guidance for planning and designing forest landscapes. Main results: (1) Places with more frequent eye movements have relatively lower satisfaction preferences; (2) The spatial perception factors affect participants’ visual behavior, and satisfaction preference is different based on many indicators (WCB, WSO, WSN, SSH, etc.) in forest recreation space; (3) The professional background education affects the participants’ visual-behavior evaluation of the recreational landscape space and also affects the participants’ focus on the landscape preference. When the spatial type of forest recreation space changes, the spatial perception factors that affect the participants’ visual behavior and satisfaction preferences also change. Based on the above, we suggest that in forest recreation space, the spatial perception indicators should be improved according to the characteristics of space itself, then improve the satisfaction preferences for the scene in a targeted manner to make participants produce effective and positive visual behavior. Meanwhile, for a well-built forest park, we should provide the landscape node with the best visual effect and satisfaction preference for tourists from different professional backgrounds on the park’s tour route map based on the characteristics of the forest recreational landscape space.

Visual detection and tracking algorithms for minimally invasive surgical instruments: A comprehensive review of the state-of-the-art

Minimally invasive surgical instrument visual detection and tracking is one of the core algorithms of minimally invasive surgical robots. With the development of machine vision and robotics, related technologies such as virtual reality, three-dimensional reconstruction, path planning, and human–machine collaboration can be applied to surgical operations to assist clinicians or use surgical robots to complete clinical operations. The minimally invasive surgical instrument vision detection and tracking algorithm analyzes the image transmitted by the surgical robot endoscope, extracting the position of the surgical instrument tip in the image, so as to provide the surgical navigation. This technology can greatly improve the accuracy and success rate of surgical operations. The purpose of this paper is to further study the visual detection and tracking technology of minimally invasive surgical instruments, summarize the existing research results, and apply it to the surgical robot project. By reading the literature, the author summarized the theoretical basis and related algorithms of this technology in recent years. Finally, the author compares the accuracy, speed and application scenario of each algorithm, and analyzes the advantages and disadvantages of each algorithm. The papers included in the review were selected through Web of Science, Google Scholar, PubMed and CNKI searches using the keywords: “object detection”, “object tracking”, “surgical tool detection”, “surgical tool tracking”, “surgical instrument detection” and “surgical instrument tracking” limiting results to the year range 1985–2021. Our study shows that this technology will have a great development prospect in the aspects of accuracy and real-time improvement in the future.

Research on Control System of Delta Robot Based on Visual Tracking Technology

Delta parallel robot has the advantages of fast motion speed, accurate positioning, low cost and high efficiency. In this paper, OMRON Adapt Hornet 565 3 axis parallel robot is taken as the research object and the control system of Delta robot based on visual tracking technology is studied. The control flow such as camera configuration, model configuration, and process configuration is described in detail, the control system was tested finally. Through the tests, The parallel robot can grasp different shapes of models accurately and quickly under the action of visual tracking.

Research on Single Damage Identification of Multi-span Bridge Based on Influence Line

Bridges are an important part of traffic engineering. They play an irreplaceable role in developing national economy, promoting cultural exchanges and consolidating national defense. The structural safety of bridges is the primary prerequisite for their role. However, due to the influence of many factors such as material aging, external environmental corrosion, longterm load action and accidental impact, the bridge structure will be damaged to different degrees, and the bridge will be destroyed when the damage accumulates to a certain degree. Once the bridge is damaged, it will have a great negative impact on human life safety, property safety, and social stability. Therefore, studying the method of rapid and accurate identification of bridge structure damage has great theoretical significance and engineering value. Based on the current status and existing problems of existing bridge structure damage identification, this paper proposes a continuous beam bridge structure damage identification technology based on deflection influence lines. Firstly, using graph multiplication and other theories, the expression of influence line function on the deflection of multi-span continuous beam bridge is derived. The influence line function of continuous beam bridge without structural damage is derived from the theoretical level, and the graph is drawn. Through the formula of the deflection influence line of healthy structure, it can be confirmed that the deflection influence line obtained quickly under the visual tracking technology can identify the damage of the structure. We use software modeling to find the best identification parameters. Using MIDAS/Civil software can establish the model and simulate the deflection influence lines of different measuring points of continuous beam bridge structures with different positions and different degrees of damage under the action of moving loads. Taking the continuous beam bridge deflection influence line, the difference between the deflection influence line of the first derivative and the second derivative, the first derivative and the second derivative and other parameters as the research objects, we explore how to use the deflection influence line to identify damage. Finally, after the comparison of multiple working conditions and multiple measuring points, it is found that the damage identification effect of the first derivative of the deflection influence line difference is the best.

Research on the improvement of vision target tracking algorithm for Internet of things technology and Simple extended application in pellet ore phase

With the extensive application of Internet of things technology and visual object tracking technology in various neighborhoods, the traditional visual object tracking algorithm can no longer meet the needs of Internet of things. The Internet of things with its powerful perception, multi-information transmission ability and super intelligent processing ability force the traditional visual object tracking algorithm to innovate and improve. In order to improve the tracking algorithm’s ability to cope with complex and drastic changes in the target’s appearance, in this paper, an accurate and robust visual object tracking algorithm (visual object tracking) based on K-means clustering algorithm on the integrated model ENS is studied. The tracking target is divided into several sample packets, and the size of the sample packet is compressed to match different weights of the filter in frequency domain. Finally, a more accurate and robust filter is built to realize the tracking of the target. Experimental simulation results show that the improved visual object tracking algorithm ENS-CSK approximately conforms to two-dimensional gaussian distribution in tracking effect, and the tracking success rate and accuracy are higher than the AdaBoost algorithm and KCF algorithm mentioned in the paper. Therefore, the improved visual object tracking algorithm ENS-CSK algorithm in this paper can better match the visual object tracking under the Internet of things technology. Therefore, it can be extended to the process of ore phase transformation of pellet under continuous calcination with varying temperature. Thus, the pressure resistance of pellets at different calcining temperatures can be predicted more accurately.

On-line classroom visual tracking and quality evaluation by an advanced feature mining technique

With the rapid development of computer vision and multimedia technology, especially the visual tracking technology and network transmission, teacher-centered education is popular nowadays. The shortcomings of the conventional classroom teaching mode by manually student behavior analysis are gradually becoming less effective. Aiming at the main problems existing in the application of classroom teaching video resources in multimedia teaching, in this paper, we proposed an online classroom visual data tracking system, associated with an advanced tracking quality evaluation method based on data mining. Our proposed framework can offer a scientific basis for improving the quality of online education by discovering students’ learning patterns from their online learning data. The evaluation results can effectively demonstrated that the mining of various learning information of students is useful, and obtained the classification rules that affect the learning effect toward students. These clues can be adopted to uncover the learning effect of students and provide individual guidance for students’ learning behaviors. This work can reveal the pattern online classroom image teaching behavior from the perspective of behavior chain. We also noticed the online classroom visual tracking behavior can be divided into several components: selection, presentation, mapping, analysis and collection, as well as the analysis from students facial expression.

Temporal–spatial consistency of self-adaptive target response for long-term correlation filter tracking

Owning to the impressive performance and high speed of the correlation filter (CF) visual tracking technology, the CF-based tracking gets a significant amount of attentions and obtains a large number of researches. But the traditional CF-based trackers have two inherent issues needed to be solved. On the one hand, the boundary effect caused by the circulant structure will affect the performance. On the other hand, the target response is assumed as Gaussian response and the value is fixed. In order to deal with the boundary effect, a spatially regularized method by imposing space penalties to the spatial coefficients is proposed. About the fixed target response, some researchers propose a framework that can adaptively change the response to deal with it, but the two issues only be coped with separately. We propose a tracker that utilizes the two merits jointly to win a better performance and a more robustness model which can cope with the complex environment to achieve a long-term tracking. We use an iteration solution to solve the joint cost function and ADMM algorithm to solve temporal–spatial consistency problem which can obtain a global solution and fast computation. We evaluate our method on the well-known visual tracking benchmark dataset called OTB50 and get a competitive performance result compared with the relevant trackers.

Concurrent-learning-based visual servo tracking and scene identification of mobile robots

Purpose The purpose of this paper is to present a visual servo tracking strategy for the wheeled mobile robot, where the unknown feature depth information can be identified simultaneously in the visual servoing process. Design/methodology/approach By using reference, desired and current images, system errors are constructed by measurable signals that are obtained by decomposing Euclidean homographies. Subsequently, by taking the advantage of the concurrent learning framework, both historical and current system data are used to construct an adaptive updating mechanism for recovering the unknown feature depth. Then, the kinematic controller is designed for the mobile robot to achieve the visual servo trajectory tracking task. Lyapunov techniques and LaSalle’s invariance principle are used to prove that system errors and the depth estimation error converge to zero synchronously. Findings The concurrent learning-based visual servo tracking and identification technology is found to be reliable, accurate and efficient with both simulation and comparative experimental results. Both trajectory tracking and depth estimation errors converge to zero successfully. Originality/value On the basis of the concurrent learning framework, an adaptive control strategy is developed for the mobile robot to successfully identify the unknown scene depth while accomplishing the visual servo trajectory tracking task.

Intelligent visual object tracking with particle filter based on Modified Grey Wolf Optimizer

In a visual object tracking technology the particle filter (PF) is frequently used. The main drawback of the particle filter is that a large quantity of particles is required. This paper objectives to propose an evolutionary particle filter based upon Modified Grey Wolf Optimizer (MGWO) which will overcome the impoverishment of the sample problem in the regular PF. For this, firstly a new variant of GWO named as Modified Grey Wolf Optimizer (MGWO) is proposed. This variant works an active trigonometric sine truncated function for confirming the enhanced exploitation and exploration properties. Secondly, the MGWO algorithm is embedded in the PF structure. Before the resampling, by using MGWO, the particles in the PF are optimized. Accordingly, the more significant particles can be expanded, and the particles can estimate the actual state of the target object more precisely. Performance of proposed Modified GWO based particle filter (MGWO-PF) is evaluated on standard visual tracking benchmark databases. Also, the MGWO-PF tracker is compared with the Particle filter (PF), Particle swarm optimization based particle filter (PSO-PF), Firefly algorithm based particle filter (FAPF) and Spider monkey optimization assisted particle filter (SMO-PF). We show that visual object tracking using MGWO-PF provides more reliable and efficient tracking results than other compared methods.