Search

Maintaining stable gaze while tracking moving objects is commonplace across animal taxa, yet how diverse ecological needs impact these processes is poorly understood. During flight, the fruit-eating fly Drosophila melanogaster maintains course by making smooth steering adjustments to fixate the image of the distant visual background on the retina, while executing body saccades to investigate nearby objects such as food sources. Cactophilic Drosophila mojavensis live where there is no canopy; rather, the flora forming visual "background" and "objects" are one and the same. We tested whether D. mojavensis have adapted their flight control strategies for a visually sparse landscape. We used a magnetic tether that allows free movement in the yaw axis. In response to a textured bar moving across a similarly textured stationary background, D. melanogaster fixates the background, thereby stabilizing gaze while integrating bar dynamics to trigger tracking saccades. By contrast, two mojavensis subspecies in the repleta subgroup and one species in the melanogaster subgroup steer to smoothly fixate the bar, seemingly ignoring the stationary surround. Desert flies execute frequent bar-tracking saccades, but theirs are triggered when rotational velocity lags the bar. Thus, D. melanogaster , which lives in visually cluttered cosmopolitan habitats, leverages the optical disparities between nearby objects and distant foliage for a hybrid control strategy: "ground-fixate, object-saccade." Flies in distant phylogenetic subgroups with similar visual ecology use a "fixate-and-saccade" strategy, which would be adaptive in a visually sparse environment where individual landscape features are both approached and used to maintain a straight course. • Related species often have vastly visual ecological constraints • Drosophila species from different visual habitats show divergent visual behaviors • D. melanogaster use a "ground-fixate, object-saccade" strategy to track objects • D. mojavensis use a fused fixate-and-saccade strategy to track objects Related species can have different visual ecology. Rimniceanu et al. show that desert Drosophila species adapt their flight control to combine smooth pursuit and saccades to track sparse visual features of the landscape. Cosmopolitan flies fix their gaze on the cluttered visual background and then track objects with saccades. [ABSTRACT FROM AUTHOR]

Within the area of environmental perception, automatic navigation, object detection, and computer vision are crucial and demanding fields with many applications in modern industries, such as multi-target long-term visual tracking in automated production, defect detection, and driverless robotic vehicles. The performance of computer vision has greatly improved recently thanks to developments in deep learning algorithms and hardware computing capabilities, which have spawned the creation of a large number of related applications. At the same time, with the rapid increase in autonomous systems in the market, energy consumption has become an increasingly critical issue in computer vision and SLAM (Simultaneous Localization and Mapping) algorithms. This paper presents the results of a detailed review of over 100 papers published over the course of two decades (1999–2024), with a primary focus on the technical advancement in computer vision. To elucidate the foundational principles, an examination of typical visual algorithms based on traditional correlation filtering was initially conducted. Subsequently, a comprehensive overview of the state-of-the-art advancements in deep learning-based computer vision techniques was compiled. Furthermore, a comparative analysis of conventional and novel algorithms was undertaken to discuss the future trends and directions of computer vision. Lastly, the feasibility of employing visual SLAM algorithms in the context of autonomous vehicles was explored. Additionally, in the context of intelligent robots for low-carbon, unmanned factories, we discussed model optimization techniques such as pruning and quantization, highlighting their importance in enhancing energy efficiency. We conducted a comprehensive comparison of the performance and energy consumption of various computer vision algorithms, with a detailed exploration of how to balance these factors and a discussion of potential future development trends. [ABSTRACT FROM AUTHOR]

To address the limitations of traditional footstep vibration signal localization algorithms, such as limited accuracy, single feature extraction, and cumbersome parameter adjustment, a motion target localization method for step vibration signals based on deep learning is proposed. Velocity vectors are used to describe human motion and adapt it to the nonlinear motion and complex interactions of moving targets. In the feature extraction stage, a one-dimensional residual convolutional neural network is constructed to extract the time–frequency domain features of the signals, and a channel attention mechanism is introduced to enhance the model's focus on different vibration sensor signal features. Furthermore, a bidirectional long short-term memory network is built to learn the temporal relationships between the extracted signal features of the convolution operation. Finally, regression operations are performed through fully connected layers to estimate the position and velocity vectors of the moving target. The dataset consists of footstep vibration signal data from six experimental subjects walking on four different paths and the actual motion trajectories of the moving targets obtained using a visual tracking system. Experimental results show that compared to WT-TDOA and SAE-BPNN, the positioning accuracy of our method has been improved by 37.9% and 24.8%, respectively, with a system average positioning error reduced to 0.376 m. [ABSTRACT FROM AUTHOR]

Object tracking is a challenging task which is required for different problems such as surveillance, traffic analysis and human-computer interaction. The problem of tracking an object can be considered in different categories such as single object tracking, multiple object tracking, short-term tracking, long-term tracking, tracking by detection and detection-free tracking. This study focuses on detection-free tracking for ground targets on aerial images. The studies in the literature show that correlation filter and deep learning based object trackers perform well recently. This paper proposes a new correlation filter-based tracker containing a strategy for re-detection issue. We improve the performance of correlation filter-based tracker by adding a lightweight re-detection ability to the correlation filter tracker in case of a long occlusion or complete loss of target. We use deep features to train Discriminative Correlation Filter(DCF) by integrating sub-networks from pre-trained ResNet and SAND models. The experimental results on the popular UAV123L dataset show that the proposed method(MADCF) improves the performance of DCF tracker and have a reasonable performance for long-term tracking problem. Moreover, we prepare a new tracking dataset (PESMOD tracking) consisting of UAV images, and we evaluate the proposed method and state-of-the-art method in this dataset. We observed that the proposed method performs much better in ground target tracking from VIVID and PESMOD aerial datasets. The proposed MADCF tracker performs better for small targets tracked by UAVs compared to the deep learning-based trackers. The source code and prepared dataset are available at http://github.com/mribrahim/MADCF [ABSTRACT FROM AUTHOR]

In visual tracking, the target always undergoes appearance variations due to a variety of challenging situations, such as deformation and rotation. In this paper, we propose the target-guided feature modulation network based on siamese network to extract the more target-relevant features, which is guided by a template to modulate the search features that can be directly used for classification and localization. Specifically, we customize two target-guided feature modulation subnetworks for visual tracking, which are called template-guided spatial-attention modulation subnetwork and template-guided channel-attention modulation subnetwork, to achieve this proposal. The former controls the discriminative region based on the correlation of each search feature position with all template feature positions, whereas the latter readjusts the importance of each channel based on the response value of each channel feature of the template feature and the response value of each channel of the search feature. Extensive experiments on multiple datasets have demonstrated the effectiveness of the proposed approach in this paper. [ABSTRACT FROM AUTHOR]

Human-Robot Interaction is an increasingly important topic in both research and industry fields. Since human safety must be always guaranteed and accidental contact with the operator avoided, it is necessary to investigate real-time obstacle avoidance strategies. The transfer from simulation environments, where algorithms are tested, to the real world is challenging from different points of view, e.g., the continuous tracking of the obstacle and the configuration of different manipulators. In this paper, the authors describe the implementation of a collision avoidance strategy based on the potential field method for off-line trajectory planning and on-line motion control, paired with the Motion Capture system Optitrack PrimeX 22 for obstacle tracking. Several experiments show the performance of the proposed strategy in the case of a fixed and dynamic obstacle, disturbing the robot’s trajectory from multiple directions. Two different avoidance modalities are adapted and tested for both standard and redundant robot manipulators. The results show the possibility of safely implementing the proposed avoidance strategy on real systems. [ABSTRACT FROM AUTHOR]

Query decoders have been shown to achieve good performance in object detection. However, they suffer from insufficient object tracking performance. Sequence-to-sequence learning in this context has recently been explored, with the idea of describing a target as a sequence of discrete tokens. In this study, we experimentally determine that, with appropriate representation, a parallel approach for predicting a target coordinate sequence with a query decoder can achieve good performance and speed. We propose a concise query-based tracking framework for predicting a target coordinate sequence in a parallel manner, named QPSTrack. A set of queries are designed to be responsible for different coordinates of the tracked target. All the queries jointly represent a target rather than a traditional one-to-one matching pattern between the query and target. Moreover, we adopt an adaptive decoding scheme including a one-layer adaptive decoder and learnable adaptive inputs for the decoder. This decoding scheme assists the queries in decoding the template-guided search features better. Furthermore, we explore the use of the plain ViT-Base, ViT-Large, and lightweight hierarchical LeViT architectures as the encoder backbone, providing a family of three variants in total. All the trackers are found to obtain a good trade-off between speed and performance; for instance, our tracker QPSTrack-B256 with the ViT-Base encoder achieves a 69.1% AUC on the LaSOT benchmark at 104.8 FPS. [ABSTRACT FROM AUTHOR]

Siamese-like trackers expose considerable shortcomings in the case of brief occlusion due mainly to the inadequate consideration of the correlation information between adjacent frames. The precision of predicted bounding boxes still has much room for further improvement because the traditional regression loss cannot effectively handle the case where one box contains the other. To address these shortages, the paper proposes a novel pre-frame auxiliary and fusion tracking framework. Within this framework, a retained variable is first introduced to avoid some additional twin branches while retaining the previously obtained deep features of the search frames. Based on such a variable, a pre-frame auxiliary module is constructed to establish the relationship between encoding features and the retained pre-frame information. Furthermore, a decoding fusion module is designed to fuse the generated similarity relationship between the template patch and the search patch and the one between the search frame and previous frames. Moreover, the Efficient IoU (EIoU) loss is employed to increase the precision of predicted bounding boxes by adding three penalty terms for the differences in the center point, length, and width of the two bounding boxes. Finally, the superiority over state-of-the-art methods is verified by numerous tests on visual tracking benchmarks. [ABSTRACT FROM AUTHOR]

Knowledge distillation techniques have been successfully used in computer vision in recent years. The two main distillation techniques now in use are logit-based distillation and middle layer feature-based distillation. Logit-based distillation does not handle the features of the middle layer of the teacher network well. The extraction of middle layer based features is mainly on local information. In this paper, we design a backbone network based on dual knowledge distillation. Dual knowledge distillation enables the student network to mimic the teacher predictions while learning the teacher middle layer features. A trained Resnet50 is used as a lightweight student network (feature extraction network) trained by the teacher network. Lightweight feature extraction networks can effectively reduce memory and improve tracking accuracy. Since different students have different comprehension abilities, in order to facilitate communication between student networks, we propose feature sharing between student networks in the template and search branches. Then, we propose a new tracking algorithm based on double knowledge extraction of backbone networks. Experimental results on five tracking datasets show that the tracking algorithm has good tracking performance and real-time tracking speed. [ABSTRACT FROM AUTHOR]

Visual tracking is a fundamental task in computer vision with significant practical applications in various domains, including surveillance, security, robotics, and human-computer interaction. However, it may face limitations in visible light data, such as low-light environments, occlusion, and camouflage, which can significantly reduce its accuracy. To cope with these challenges, researchers have explored the potential of combining the visible and infrared modalities to improve tracking performance. By leveraging the complementary strengths of visible and infrared data, RGB-infrared fusion tracking has emerged as a promising approach to address these limitations and improve tracking accuracy in challenging scenarios. In this article, we present a review on RGB-infrared fusion tracking. Specifically, we categorize existing RGBT tracking methods into four categories based on their underlying architectures, feature representations, and fusion strategies, namely feature decoupling based method, feature selecting based method, collaborative graph tracking method, and traditional fusion method. Furthermore, we provide a critical analysis of their strengths, limitations, representative methods, and future research directions. To further demonstrate the advantages and disadvantages of these methods, we present a review of publicly available RGBT tracking datasets and analyze the main results on public datasets. Moreover, we discuss some limitations in RGBT tracking at present and provide some opportunities and future directions for RGBT visual tracking, such as dataset diversity, unsupervised and weakly supervised applications. In conclusion, our survey aims to serve as a useful resource for researchers and practitioners interested in the emerging field of RGBT tracking, and to promote further progress and innovation in this area. [ABSTRACT FROM AUTHOR]

Visual object tracking is an important technology in camera-based sensor networks, which has a wide range of practicability in auto-drive systems. A transformer is a deep learning model that adopts the mechanism of self-attention, and it differentially weights the significance of each part of the input data. It has been widely applied in the field of visual tracking. Unfortunately, the security of the transformer model is unclear. It causes such transformer-based applications to be exposed to security threats. In this work, the security of the transformer model was investigated with an important component of autonomous driving, i.e., visual tracking. Such deep-learning-based visual tracking is vulnerable to adversarial attacks, and thus, adversarial attacks were implemented as the security threats to conduct the investigation. First, adversarial examples were generated on top of video sequences to degrade the tracking performance, and the frame-by-frame temporal motion was taken into consideration when generating perturbations over the depicted tracking results. Then, the influence of perturbations on performance was sequentially investigated and analyzed. Finally, numerous experiments on OTB100, VOT2018, and GOT-10k data sets demonstrated that the executed adversarial examples were effective on the performance drops of the transformer-based visual tracking. White-box attacks showed the highest effectiveness, where the attack success rates exceeded 90% against transformer-based trackers. [ABSTRACT FROM AUTHOR]

This paper proposes a model-based method for real-time automatic mood estimation in video sequences. The approach is customized by learning the person's specific facial parameters, which are transformed into facial Action Units (AUs). A model mapping for mood representation is used to describe moods in terms of the PAD space: Pleasure, Arousal, and Dominance. From the intersection of these dimensions, eight octants represent fundamental mood categories. In the experimental evaluation, a stimulus video randomly selected from a set prepared to elicit different moods was played to participants, while the participant's facial expressions were recorded. From the experiment, Dominance is the dimension least impacted by facial expression, and this dimension could be eliminated from mood categorization. Then, four categories corresponding to the quadrants of the Pleasure–Arousal (PA) plane, "Exalted", "Calm", "Anxious" and "Bored", were defined, with two more categories for the "Positive" and "Negative" signs of the Pleasure (P) dimension. Results showed a 73% of coincidence in the PA categorization and a 94% in the P dimension, demonstrating that facial expressions can be used to estimate moods, within these defined categories, and provide cues for assessing users' subjective states in real-world applications. [ABSTRACT FROM AUTHOR]

Appearance modeling plays a pivotal role in both object detection and visual tracking applications, making it a focal point for researchers due to its profound impact on real-world scenarios. It typically comprises components such as visual target representation and online learning update modeling. In this study, we embark on a comprehensive examination of generative online learning models, providing an in-depth review of existing methods with a detailed exploration of their strengths and weaknesses. The overarching objective of this research is to offer an extensive analysis of approaches grounded in generative online learning. Furthermore, we conduct a critical assessment that not only highlights the pros and cons of established techniques but also culminates in an evaluation and performance comparison to discern the most effective generative online learning method for the task of appearance modeling. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle (UAV) or aerial drone, video, and image analysis is a developing application that has attracted substantial academic interest in several computer vision-related fields. Visual target tracking is one of the most popular and difficult study areas in computer vision. Recent deep learning (DL)-based approaches have resulted in many methods being developed and presented. This study reviewed and investigated the possibilities of using drones and computer vision techniques to undertake visual tracking in aerial video applications. Additionally, benchmark datasets, assessment criteria, and contemporary deep learning-based visual raking approaches are studied. This study aims to assess current accomplishments, emphasize the disadvantages and benefits of various existing approaches in each module, and deal with pressing research questions and difficult problems using visual tracking techniques. Finally, the direction for the next research is addressed, and the research foundation of this work is presented in aerial visual tracking. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have been the dominant architectures for feature extraction tasks, but CNNs do not look for and focus on some specific image features. Correlation operations play an important role in visual tracking. However, the correlation operation reserves a large amount of unfavorable background information. In this paper, we propose an effective feature recognizer including channel and spatial attention modules to focus on important object feature information. Thus, the representation power of the feature extraction network is improved. Further, we design a multi-scale feature fusion network. The fusion network performs feature fusion on template feature and encoded feature branches to establish connections between features at different scales. Experiments on six benchmarks demonstrate that the proposed tracker outperforms the state-of-the-art trackers. In particular, the proposed tracker achieves an 80.4% AUC on TrackingNet and a 68.4% AUC on GOT-10k while running at a real-time speed. [ABSTRACT FROM AUTHOR]

Most Siamese-based trackers adopt correlation operation to perform similarity matching on feature fusion of template branch and search branch. However, the correlation operation directly uses the template feature to slide the window on the search area feature, and it is difficult to distinguish the target and background information when encountering similar target interference and background clutter, which can easily lead to tracking failure. In this paper, a mixed attention Siamese Network (MASNet) is proposed, which neatly integrates the modelling of global information and mutual information into the Siamese tracking framework. Specifically, through the learnable attention module, the local and global dependencies are adaptively integrated, and the rich context information is captured to improve the discrimination of the network for similar targets. After that, the correlation of the context information of the two branches is aggregated and adaptively encoded into the two branches, which makes up for the shortcomings of single correlation operation. In addition, the framework adopts a three-layer feature fusion method, which enables the tracker to better adapt to object deformation and similar object interference. Extensive experiments on OTB100, UAV123, GOT-10k and LaSOT show that the proposed tracking method achieves comparable performance to the advanced trackers.

In this work, we propose a visual tracking algorithm based on structural-appearance information fusion that aims to distinguish the target from distractors, including both semantical and visual distractors. It measures the similarity of targets using both appearance information and structural information, with the former extracted from siamese networks and the latter learned from appearance information using a target-cross attention mechanism. The structural and appearance information can be dynamically fused by using a gating recurrent unit, which can control the fusion ratio between them.Additionally, we introduce a similarity matching loss function to explicitly guide feature extraction. Our proposed method can extract discriminative features that facilitate the identification of the target, thus improving tracking performance. Extensive experimental results show that our proposed similarity feature extraction method can improve the tracking performance. [ABSTRACT FROM AUTHOR]

Single object tracking (SOT) is a fundamental problem in computer vision, with a wide range of applications, including autonomous driving, augmented reality, and robot navigation. The robustness of SOT faces two main challenges: tiny target and fast motion. These challenges are especially manifested in videos captured by unmanned aerial vehicles (UAV), where the target is usually far away from the camera and often with significant motion relative to the camera. To evaluate the robustness of SOT methods, we propose BioDrone—the first bionic drone-based visual benchmark for SOT. Unlike existing UAV datasets, BioDrone features videos captured from a flapping-wing UAV system with a major camera shake due to its aerodynamics. BioDrone hence highlights the tracking of tiny targets with drastic changes between consecutive frames, providing a new robust vision benchmark for SOT. To date, BioDrone offers the largest UAV-based SOT benchmark with high-quality fine-grained manual annotations and automatically generates frame-level labels, designed for robust vision analyses. Leveraging our proposed BioDrone, we conduct a systematic evaluation of existing SOT methods, comparing the performance of 20 representative models and studying novel means of optimizing a SOTA method (KeepTrack Mayer et al. in: Proceedings of the IEEE/CVF international conference on computer vision, pp. 13444–13454, 2021) for robust SOT. Our evaluation leads to new baselines and insights for robust SOT. Moving forward, we hope that BioDrone will not only serve as a high-quality benchmark for robust SOT, but also invite future research into robust computer vision. The database, toolkits, evaluation server, and baseline results are available at http://biodrone.aitestunion.com. [ABSTRACT FROM AUTHOR]

CNN (convolutional neural network) based real time trackers usually do not carry out online network update in order to maintain rapid tracking speed. This inevitably influences the adaptability to changes in object appearance. Correlation filter based trackers can update the model parameters online in real time. In this paper, we present an end-to-end lightweight network architecture, namely Discriminant Correlation Filter Network (DCFNet). A differentiable DCF (discriminant correlation filter) layer is incorporated into a Siamese network architecture in order to learn the convolutional features and the correlation filter simultaneously. The correlation filter can be efficiently updated online. In previous work, we introduced a joint scale-position space to the DCFNet, forming a scale DCFNet which carries out the predictions of object scale and position simultaneously. We combine the scale DCFNet with the convolutional-deconvolutional network, learning both the high-level embedding space representations and the low-level fine-grained representations for images. The adaptability of the fine-grained correlation analysis and the generalization capability of the semantic embedding are complementary for visual tracking. The back-propagation is derived in the Fourier frequency domain throughout the entire work, preserving the efficiency of the DCF. Extensive evaluations on the OTB (Object Tracking Benchmark) and VOT (Visual Object Tracking Challenge) datasets demonstrate that the proposed trackers have fast speeds, while maintaining tracking accuracy. [ABSTRACT FROM AUTHOR]

Manual motor performance declines with age, but the extent to which age influences the acquisition of new skills remains a topic of debate. Here, we examined whether older healthy adults show less training-dependent performance improvements during a single session of a bimanual pinch task than younger adults. We also explored whether physical and cognitive factors, such as grip strength or motor-cognitive ability, are associated with performance improvements. Healthy younger (n = 16) and older (n = 20) adults performed three training blocks separated by short breaks. Participants were tasked with producing visually instructed changes in pinch force using their right and left thumb and index fingers. Task complexity was varied by shifting between bimanual mirror-symmetric and inverse-asymmetric changes in pinch force. Older adults generally displayed higher visuomotor force tracking errors during the more complex inverse-asymmetric task compared to younger adults. Both groups showed a comparable net decrease in visuomotor force tracking error over the entire session, but their improvement trajectories differed. Young adults showed enhanced visuomotor tracking error only in the first block, while older adults exhibited a more gradual improvement over the three training blocks. Furthermore, grip strength and performance on a motor-cognitive test battery scaled positively with individual performance improvements during the first block in both age groups. Together, the results show subtle age-dependent differences in the rate of bimanual visuomotor skill acquisition, while overall short-term learning ability is maintained. [ABSTRACT FROM AUTHOR]

Pupil size is a significant biosignal for human behavior monitoring and can reveal much underlying information. This study explored the effects of task load, task familiarity, and gaze position on pupil response during learning a visual tracking task. We hypothesized that pupil size would increase with task load, up to a certain level before decreasing, decrease with task familiarity, and increase more when focusing on areas preceding the target than other areas. Fifteen participants were recruited for an arrow tracking learning task with incremental task load. Pupil size data were collected using a Tobii Pro Nano eye tracker. A 2 × 3 × 5 three-way factorial repeated measures ANOVA was conducted using R (version 4.2.1) to evaluate the main and interactive effects of key variables on adjusted pupil size. The association between individuals' cognitive load, assessed by NASA-TLX, and pupil size was further analyzed using a linear mixed-effect model. We found that task repetition resulted in a reduction in pupil size; however, this effect was found to diminish as the task load increased. The main effect of task load approached statistical significance, but different trends were observed in trial 1 and trial 2. No significant difference in pupil size was detected among the three gaze positions. The relationship between pupil size and cognitive load overall followed an inverted U curve. Our study showed how pupil size changes as a function of task load, task familiarity, and gaze scanning. This finding provides sensory evidence that could improve educational outcomes. [ABSTRACT FROM AUTHOR]

In the popular Siamese network tracker, cross-correlation is based on the similarity to find the exact location of the template in the search region. However, due to cross-correlation primarily focuses on the spatial neighborhoods, so it often falls into local optimum. Additionally, multiple fusions of features results in a degrade of the target position information. To address these issues, we purpose a novel transformer-variant tracker. We make cross-attention play a central role in our tracker, and thus propose a novel symmetric cross-attention that effectively fuses the features of the template and the search region. The symmetric cross-attention only uses the cross-attention mechanism so as to get rid of the cross-correlation operation, which avoids local optimum and captures more global information. We also propose a position information enhancement module preserving more horizontal and vertical position information, which avoids the loss of position information caused by multiple fusions of features and helps the tracker to locate the target more accurately. Our proposed tracker achieves state-of-the-art performance on six benchmarks including GOT-10k, TrackingNet, LaSOT, UAV123, OTB100, and VOT2020, and is able to run at real-time speed. [ABSTRACT FROM AUTHOR]

Autonomous mobile robots play a vital role in the mechanized production of orchards, where human-following is a crucial collaborative function. In unstructured orchard environments, obstacles often obscure the path, and personnel may overlap, leading to significant disruptions to human-following. This paper introduces the KCF-YOLO fusion visual tracking method to ensure stable tracking in interference environments. The YOLO algorithm provides the main framework, and the KCF algorithm intervenes in assistant tracking. A three-dimensional binocular-vision reconstruction method was used to acquire personnel positions, achieving stabilized visual tracking in disturbed environments. The robot was guided by fitting the personnel's trajectory using an unscented Kalman filter algorithm. The experimental results show that, with 30 trials in multi-person scenarios, the average tracking success rate is 96.66%, with an average frame rate of 8 FPS. Additionally, the mobile robot is capable of maintaining a stable following speed with the target individuals. Across three human-following experiments, the horizontal offset Error Y does not exceed 1.03 m. The proposed KCF-YOLO tracking method significantly bolsters the stability and robustness of the mobile robot for human-following in intricate orchard scenarios, offering an effective solution for tracking tasks. [ABSTRACT FROM AUTHOR]

Visual object tracking has been drawing increasing attention in recent years, as a fundamental task in computer vision. To extend the range of tracking applications, researchers have been introducing information from multiple modalities to handle specific scenes, with promising research prospects for emerging methods and benchmarks. To provide a thorough review of multi-modal tracking, different aspects of multi-modal tracking algorithms are summarized under a unified taxonomy, with specific focus on visible-depth (RGB-D) and visible-thermal (RGB-T) tracking. Subsequently, a detailed description of the related benchmarks and challenges is provided. Extensive experiments were conducted to analyze the effectiveness of trackers on five datasets: PTB, VOT19-RGBD, GTOT, RGBT234, and VOT19-RGBT. Finally, various future directions, including model design and dataset construction, are discussed from different perspectives for further research. [ABSTRACT FROM AUTHOR]

Appearance variations are a challenging issue in visual tracking systems. Typically, appearance modeling is used to deal with the challenge of representing and detecting objects in these systems. Appearance modeling is generally structured of parts such as visual target representation and online learning update modeling. Various online learning methods have been proposed to perform the task of object representation and update the model. The discriminative online learning model, as the main focus of the study, is investigated in this paper. Correspondingly, describe current procedures fully, highlighting their benefits and drawbacks. This study aims to give in-depth research into methodologies based on discriminative online learning. A critical review of current approaches' benefits and drawbacks is covered. The finding of this research is investigation of discriminative online learning methods for appearance modeling in visual tracking systems. It provides a comprehensive analysis of current approaches, evaluating their benefits and drawbacks, and comparing their performance to identify the most effective approach for addressing appearance variations in object tracking. The approaches are evaluated, and performance comparisons are made to identify the most effective approach to discriminative online learning for appearance modeling. [ABSTRACT FROM AUTHOR]

Visual tracking in aerial videos refers to the process of automatically tracking an object of interest in a video captured from an aerial platform such as a drone or aircraft. One of the key challenges in visual tracking is dealing with appearance variations caused by changes in illumination, viewpoint, occlusion, and background clutter. While there have been some review papers in the literature that have reviewed previous studies on visual tracking in aerial videos, there is still a need for a comprehensive review of existing methods. This paper presents a comprehensive study of existing methods and previous studies on visual target tracking. The visual tracking framework consists of four modules: target region extraction, visual target representation, statistical measuring, and target motion representation and localization. The main contributions of this study is to review the current achievements, highlight the weaknesses and advantages of various existing methods in each module, and address current research issues and challenging tasks in each module. The literature review focuses on articles published in highly cited, peer-reviewed journals, with particular emphasis on high-quality techniques. The aim of this study is to conduct a comprehensive review of visual tracking methods. The findings of this paper address the advantages and disadvantages of existing visual tracking methods, challenges, and potential solutions on visual representation and appearance modeling methods. Finally, the visual tracking methods are investigated on aerial videos, and their highlighted points are addressed to guide future researchers. [ABSTRACT FROM AUTHOR]

In this paper, a marker and its real-time tracking method are proposed. Different from existing technologies that recognize the markers by spatial event features, which lead to many practical problems, we discover the possibility of using temporal features. Strobe LEDs (light emitting diode) are used as markers to produce periodically flipping events, and a fast clustering-based algorithm is designed to track and recognize these markers simultaneously. Experiments demonstrate that our methods have superior speed and accuracy compared to state-of-the-arts. The markers can be stably tracked in many challenging situations, thus can be used in various visual tracking applications. The proposed method introduces a new marker and its corresponding recognition algorithm for event camera-based targets tracking, offering a reliable solution for various applications. [ABSTRACT FROM AUTHOR]

The combined use of Uncrewed Aerial Vehicles (UAVs) with an integrated Real Time Kinematic (RTK) Global Navigation Satellite System (GNSS) module and an external GNSS base station allows photogrammetric surveys with centimeter accuracy to be obtained without the use of ground control points. This greatly reduces acquisition and processing time, making it possible to perform rapid monitoring of landslides by installing permanent and clearly recognizable optical targets on the ground. In this contribution, we show the results obtained in the Ca' Lita landslide (Northern Apennines, Italy) by performing multi-temporal RTK-aided UAV surveys. The landslide is a large-scale roto-translational rockslide evolving downslope into an earthslide–earthflow. The test area extends 60 × 103 m2 in the upper track zone, which has recently experienced two major reactivations in May 2022 and March 2023. A catastrophic event took place in May 2023, but it goes beyond the purpose of the present study. A total of eight UAV surveys were carried out from October 2020 to March 2023. A total of eight targets were installed transversally to the movement direction. The results, in the active portion of the landslide, show that between October 2020 and March 2023, the planimetric displacement of targets ranged from 0.09 m (in the lateral zone) to 71.61 m (in the central zone). The vertical displacement values ranged from −2.05 to 5.94 m, respectively. The estimated positioning errors are 0.01 (planimetric) and 0.03 m (vertical). The validation, performed by using data from a permanent GNSS receiver, shows maximum differences of 0.18 m (planimetric) and 0.21 m (vertical). These results, together with the rapidity of image acquisition and data processing, highlight the advantages of using this rapid method to follow the evolution of relatively rapid landslides such as the Ca' Lita landslide. [ABSTRACT FROM AUTHOR]

The application of visual tracking to the performance analysis of sports players in dynamic competitions is vital for effective coaching. In doubles matches, coordinated positioning is crucial for maintaining control of the court and minimizing opponents' scoring opportunities. The analysis of such teamwork plays a vital role in understanding the dynamics of the game. However, previous studies have primarily focused on analyzing and assessing singles players without considering occlusion in broadcast videos. These studies have relied on discrete representations, which involve the analysis and representation of specific actions (e.g., strokes) or events that occur during the game while overlooking the meaningful spatial distribution. In this work, we present the first annotated drone dataset from top and back views in badminton doubles and propose a framework to estimate the control area probability map, which can be used to evaluate teamwork performance. We present an efficient framework of deep neural networks that enables the calculation of full probability surfaces. This framework utilizes the embedding of a Gaussian mixture map of players' positions and employs graph convolution on their poses. In the experiment, we verify our approach by comparing various baselines and discovering the correlations between the score and control area. Additionally, we propose a practical application for assessing optimal positioning to provide instructions during a game. Our approach offers both visual and quantitative evaluations of players' movements, thereby providing valuable insights into doubles teamwork. The dataset and related project code is available at https://github.com/Ning-D/Drone_BD_ControlArea [ABSTRACT FROM AUTHOR]

Transformer architecture has made breakthrough in various downstream computer vision tasks and has shown its great potential in visual object tracking. However, existing transformer-based approaches adopt pixel-to-pixel attention strategy to integrate the domain knowledge, but fail to explore the channel and location information from object features, which limits the expressivity of the tracker. To address the above problems, we propose a novel tracking framework, where we propose 2 attention blocks that fuses with Transformer (dubbed EVOTA). It has 4 modules: the feature extraction module, the enhanced attention module, a transformer module and a model predictor. Specifically, a channel-wise attention module re-calibrates the channel-wise feature responses in an adaptive way by modelling interdependencies explicitly between channels. A local cross-channel interaction scheme learns strong channel context information. Meanwhile, an energy function is developed to analyze the importance of each neuron and infers their 3D weights. Extensive experiments have been carried out on 5 prevalent tracking benchmarks to testify the effectiveness of our model, in which EVOTA outperforms several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Understanding animal movement and behaviour can aid spatial planning and inform conservation management. However, it is difficult to directly observe behaviours in remote and hostile terrain such as the marine environment. Different underlying states can be identified from telemetry data using hidden Markov models (HMMs). The inferred states are subsequently associated with different behaviours, using ecological knowledge of the species. However, the inferred behaviours are not typically validated due to difficulty obtaining 'ground truth' behavioural information. We investigate the accuracy of inferred behaviours by considering a unique data set provided by Joint Nature Conservation Committee. The data consist of simultaneous proxy movement tracks of the boat (defined as visual tracks as birds are followed by eye) and seabird behaviour obtained by observers on the boat. We demonstrate that visual tracking data is suitable for our study. Accuracy of HMMs ranging from 71% to 87% during chick‐rearing and 54% to 70% during incubation was generally insensitive to model choice, even when AIC values varied substantially across different models. Finally, we show that for foraging, a state of primary interest for conservation purposes, identified missed foraging bouts lasted for only a few seconds. We conclude that HMMs fitted to tracking data have the potential to accurately identify important conservation‐relevant behaviours, demonstrated by a comparison in which visual tracking data provide a 'gold standard' of manually classified behaviours to validate against. Confidence in using HMMs for behavioural inference should increase as a result of these findings, but future work is needed to assess the generalisability of the results, and we recommend that, wherever feasible, validation data be collected alongside GPS tracking data to validate model performance. This work has important implications for animal conservation, where the size and location of protected areas are often informed by behaviours identified using HMMs fitted to movement data. [ABSTRACT FROM AUTHOR]

Tracking failure in state-of-the-art visual SLAM has been reported to be frequent and hampers real-world deployment of SLAM solutions. Very recently, efforts have been made to avoid tracking failure using various methods (e.g. using deep reinforcement learning to plan a path where the risk of tracking failure is minimal). The results of those approaches are encouraging but are far from producing a failure-free visual system. Failure is inevitable in vision-based systems. Therefore, developing recovery (post-failure) solutions might be a better approach in developing more reliable systems. To this end, we propose a novel, easily trainable, deep recovery maneuver algorithm. Instead of predicting tracking failures, our algorithm predicts the back stepping move, post failure, which helps regain tracking. With our proposed simple approach, state-of-the-art SLAM manages to complete 13 out of 50 navigation episodes (13x improvement over the baseline). Furthermore, even for cases where our algorithm fails to complete the route, it traverses 2x longer distances as compared to baseline methods. [ABSTRACT FROM AUTHOR]

Because of the complexity and difficulty of aerobic exercise, the physical quality and technical level of athletes have higher requirements. Therefore, how to accurately evaluate and analyze the situation of aerobic athletes has become an important task in training and competition. The aim of this study is to develop a vision tracking system based on infrared target imaging for the evaluation of aerobics movements. In the system, the infrared camera is used to capture the movement of aerobics athletes, and the infrared image is processed and analyzed by computer vision algorithm to extract the key body nodes to track and measure the athlete's posture. Through the experimental verification of a group of aerobics movements, the system can effectively track the athletes' body posture and accurately evaluate the quality of their movements. Through quantitative indicators and visual results, we can get the evaluation results of whether the athlete's posture and movement are accurate and in line with the norms. Compared with traditional motion evaluation methods, the proposed method has higher accuracy and real-time performance. [ABSTRACT FROM AUTHOR]

Abstract Convolutional neural networks (CNNs) have been the dominant architectures for feature extraction tasks, but CNNs do not look for and focus on some specific image features. Correlation operations play an important role in visual tracking. However, the correlation operation reserves a large amount of unfavorable background information. In this paper, we propose an effective feature recognizer including channel and spatial attention modules to focus on important object feature information. Thus, the representation power of the feature extraction network is improved. Further, we design a multi-scale feature fusion network. The fusion network performs feature fusion on template feature and encoded feature branches to establish connections between features at different scales. Experiments on six benchmarks demonstrate that the proposed tracker outperforms the state-of-the-art trackers. In particular, the proposed tracker achieves an 80.4% AUC on TrackingNet and a 68.4% AUC on GOT-10k while running at a real-time speed.

Abstract Visual object tracking has been drawing increasing attention in recent years, as a fundamental task in computer vision. To extend the range of tracking applications, researchers have been introducing information from multiple modalities to handle specific scenes, with promising research prospects for emerging methods and benchmarks. To provide a thorough review of multi-modal tracking, different aspects of multi-modal tracking algorithms are summarized under a unified taxonomy, with specific focus on visible-depth (RGB-D) and visible-thermal (RGB-T) tracking. Subsequently, a detailed description of the related benchmarks and challenges is provided. Extensive experiments were conducted to analyze the effectiveness of trackers on five datasets: PTB, VOT19-RGBD, GTOT, RGBT234, and VOT19-RGBT. Finally, various future directions, including model design and dataset construction, are discussed from different perspectives for further research.

Recently, Siamese-based trackers have emerged as the predominant focus in single object tracking research. However, the majority of these works concentrate on improving the backbone network of the tracker to enhance its performance, thereby overlooking the significant impact that the template and search region of the input to the tracker have on tracking accuracy. To address the aforementioned issues, we propose an Asymmetrical Transformer Tracker with Prior Templates (AtptTrack), consisting of a tracking branch and a template update branch. The function of the tracking branch is to receive input image pairs and tracking results to complete the tracking task. In the template update branch, an updating strategy is employed to compute the cosine similarity between the template and the tracking result. Based on this, four prior templates are generated, serving as essential supplementary features for the template. These prior templates are concatenated with the tracking results to create a hybrid template for subsequent tracking, enhancing the richness and accuracy of the template features. To further enrich the information content of the template and search region, we propose multi-scale patch embeddings to process input image pairs, which can enhance the completeness and continuity of the object features. Our tracker has been extensively tested on five benchmarks. The experiments demonstrate that our tracker achieves the state-of-the-art performance. Particularly on the OTB100 dataset, our tracker AtptTrack achieves an AUC score of 0.709, and it outperformed the second-place tracker in the deformation and occlusion challenges by 2.99% and 0.5%, respectively.

Objectives: This study aims to design a dead-angle-free smart desk lamp. Methods: The convolutional neural network (CNN) algorithm was used to realize the identification and positioning of objects. Then, the desk lamp arm was driven according to positioning to realize dead-angle-free illumination. In the subsequent testing, the designed desk lamp was compared with others driven by the support vector machine (SVM) and back-propagation neural network (BPNN) algorithms. Findings: The CNN algorithm implemented in the smart desk lamp demonstrated superior target recognition performance and positioning accuracy when compared to the other two algorithms. Moreover, with this algorithm, the smart desk lamp efficiently generated tracking responses for targets and displayed minimal positioning errors once tracking became stable. Novelty:The novelty of this article lies in the utilization of the CNN algorithm to achieve visual tracking for a smart desk lamp, which serves as the basis for its automatic adjustment. Doi: 10.28991/HIJ-2023-04-04-05 Full Text: PDF