Visual Tracking Research Articles

Sex differences in the social motivation of rats: Insights from social operant conditioning, behavioural economics, and video tracking

BackgroundSocial behaviour plays a key role in mental health and wellbeing, and developing greater understanding of mechanisms underlying social interaction—particularly social motivation—holds substantial transdiagnostic impact. Common rodent behavioural assays used to assess social behaviour are limited in their assessment of social motivation, whereas the social operant conditioning model can provide unique and valuable insights into social motivation. Further characterisation of common experimental parameters that may influence social motivation within the social operant model, as well as complementary methodological and analytical approaches, are warranted.MethodsThis study investigated the effects of biological sex, housing condition, and time-of-day, on social motivation using the social operant model. This involved training rats to lever press (FR1) for 60-s access to a social reward (same-sex conspecific stimulus). Subjects were male and female Wistar rats, housed under individual or paired conditions, and sessions were conducted either in the mid-late light phase (ZT6-10) or early-mid dark phase (ZT13-17). A behavioural economics approach was implemented to measure social demand and the influence of stimulus partner sex (same- vs. opposite-sex stimulus) on social operant responding. Additionally, video tracking analyses were conducted to assess the degree of convergence between social appetitive and consummatory behaviours.ResultsBiological sex, housing conditions, the interaction between sex and housing, and stimulus partner sex potently influenced social motivation, whereas time-of-day did not. Behavioural economics demonstrated that sex, housing, and their interaction influence both the hedonic set-point and elasticity of social demand. Video analysis of social interaction during social operant sessions revealed that social appetitive and consummatory behaviours are not necessarily convergent, and indicate potential social satiety. Lastly, oestrus phase of female experimental and stimulus rats did not impact social motivation within the model.ConclusionsSocial isolation-dependent sex differences exist in social motivation for rats, as assessed by social operant conditioning. The social operant model represents an optimal preclinical assay that comprehensively evaluates social motivation and offers a platform for future investigations of neurobiological mechanisms underlying sex differences in social motivation. These findings highlight the importance of continued consideration and inclusion of sex as a biological variable in future social operant conditioning studies.Plain English summaryHumans are social creatures—our everyday interactions with others and the support this provides play a key role in our wellbeing. For those experiencing mental health conditions, people’s motivation to engage with others can wane, which can lead them to withdraw from those who support them. Therefore, to develop better treatment strategies for these conditions, we need to gain a deeper understanding of social motivation. Studying social behaviour in animals can facilitate this investigation of social motivation as it allows for a causal understanding of underlying neurobiology that is not possible in human experiments. An optimal way to study social motivation in animals is using the social operant conditioning model, where rats learn to press a lever that opens a door and allows them to interact with another rat for a short time. This study characterised the social operant model by testing whether sex, housing conditions, time-of-day, and the sex of the stimulus partner influence rats’ motivation to seek interaction with another rat. We found that female rats were more socially motivated than males, and that rats living alone were more motivated than those living with another rat; interestingly, this effect of housing affected females more than males. Regardless of sex, rats were more motivated to interact with a rat of the opposite sex. These findings provide insights into sex differences in social motivation in rats and new insights into the social operant model which will help guide future research into social motivation and other mental health conditions.

Neural mechanisms for secondary suppression of emotional distractors: Evidence from concurrent electroencephalography-magnetoencephalography data.

Distractor suppression allows us to remain on-task in the presence of distractions by filtering task-irrelevant information from ongoing cognitive processing and responding. Electrophysiological studies have revealed that this key feature of selective attention is a dynamic process that involves at least two distinct stages of processing. Two important aspects of these processing stages remain unclear: Whether the processing of emotional distractors at an earlier stage is automatic, as reflected in the N2/early posterior negativity (EPN) component; and what functional-anatomical brain systems are recruited in each stage. The present study addresses these issues by measuring brain activity with concurrent electroencephalography-magnetoencephalography (MEG) recordings while participants performed a combined rapid serial visual presentation and motion tracking task. Event-related potentials (ERP) showed significant effects of attentional capture and attentional modulation during two time windows marked by the N2/EPN and P3b ERP components. Source reconstruction of concurrent MEG measurements revealed activation of the left visual association cortex and anterior cingulate cortex during the N2/EPN time window, activation of the insula during the early phase of the P3b and anterior cingulate cortex activity during the later phase of the P3b. The findings provide novel evidence establishing a connection between the increased N2 response to negative pictures and the activation of the cingulate gyrus, which facilitates the suppression of distractions during demanding cognitive tasks. In addition, distinct activation patterns were observed in the insula and anterior cingulate cortex during the P3b time window, indicating that attentional control mediated by the anterior cingulate cortex operates to suppress the processing of distracting emotional stimuli. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Multi‐feature fusion and memory‐based mobile robot target tracking system

AbstractIn crowded settings, mobile robots face challenges like target disappearance and occlusion, impacting tracking performance. Despite existing optimisations, tracking in complex environments remains insufficient. To address this issue, the authors propose a tailored visual navigation tracking system for crowded scenes. For target disappearance, an autonomous navigation strategy based on target coordinates, utilising a path memory bank for intelligent search and re‐tracking is introduced. This significantly enhances tracking success. To handle target occlusion, the system relies on appearance features extracted by a target detection network and a feature memory bank for enhanced sensitivity. Servo control technology ensures robust target tracking by fully utilising appearance information and motion characteristics, even in occluded scenarios. Comprehensive testing on the OTB100 dataset validates the system's effectiveness in addressing target tracking challenges in diverse crowded environments, affirming algorithm robustness.

Visual Sensor Target Tracking and Localization Method for Automatic Excavators

Visual Sensor Target Tracking and Localization Method for Automatic Excavators

SiamDCFF: Dynamic Cascade Feature Fusion for Vision Tracking.

Establishing an accurate and robust feature fusion mechanism is key to enhancing the tracking performance of single-object trackers based on a Siamese network. However, the output features of the depth-wise cross-correlation feature fusion module in fully convolutional trackers based on Siamese networks cannot establish global dependencies on the feature maps of a search area. This paper proposes a dynamic cascade feature fusion (DCFF) module by introducing a local feature guidance (LFG) module and dynamic attention modules (DAMs) after the depth-wise cross-correlation module to enhance the global dependency modeling capability during the feature fusion process. In this paper, a set of verification experiments is designed to investigate whether establishing global dependencies for the features output by the depth-wise cross-correlation operation can significantly improve the performance of fully convolutional trackers based on a Siamese network, providing experimental support for rational design of the structure of a dynamic cascade feature fusion module. Secondly, we integrate the dynamic cascade feature fusion module into the tracking framework based on a Siamese network, propose SiamDCFF, and evaluate it using public datasets. Compared with the baseline model, SiamDCFF demonstrated significant improvements.

Six-Degree-of-Freedom Freehand 3D Ultrasound: A Low-Cost Computer Vision-Based Approach for Orthopedic Applications.

In orthopedics, X-rays and computed tomography (CT) scans play pivotal roles in diagnosing and treating bone pathologies. Machine bulkiness and the emission of ionizing radiation remain the main problems associated with these techniques. The accessibility and low risks related to ultrasound handling make it a popular 2D imaging method. Indeed, 3D ultrasound assembles 2D slices into a 3D volume. This study aimed to implement a probe-tracking method for 6 DoF 3D ultrasound. The proposed method involves a dodecahedron with ArUco markers attached, enabling computer vision tracking of the ultrasound probe's position and orientation. The algorithm focuses on the data acquisition phase but covers the basic reconstruction required for data generation and analysis. In the best case, the analysis revealed an average error norm of 2.858 mm with a standard deviation norm of 5.534 mm compared to an infrared optical tracking system used as a reference. This study demonstrates the feasibility of performing volumetric imaging without ionizing radiation or bulky systems. This marker-based approach shows promise for enhancing orthopedic imaging, providing a more accessible imaging modality for helping clinicians to diagnose pathologies regarding complex joints, such as the shoulder, replacing standard infrared tracking systems known to suffer from marker occlusion problems.

Real‐time visual tracking design for an unmanned aerial vehicle in cluttered environments

Real‐time visual tracking design for an unmanned aerial vehicle in cluttered environments

Visual tracking of real-time freshness of fish using an agar hydrogel colorimetric indicator containing CuNPs/NCQDs

A simple, selective, and affordable dual fluorescence-colorimetric indicator for hydrogen sulfide was developed based on a complex of copper nanoparticles and N-doped carbon quantum dots (CuNPs/NCQDs). Real-time and visual freshness tracking of fish was done using a colorimetric indicator by incorporating CuNPs/NCQDs into agar hydrogel (AH-CuNPs/NCQDs). The fluorescence response of the CuNPs/NCQDs solution is quenched upon exposure to H2S. The field-emission scanning electron microscopy image of the AH-CuNPs/NCQDs film revealed a unified structure. The prepared indicator exhibited a good and irreversible response to H2S, with a LOD of 91.36 and a LOQ of 276.86 μM, based on the localized surface plasmon resonance (LSPR) mechanism. The X-ray photoelectron spectrometer and Fourier transform infrared spectrometer results confirmed the formation of a CuS bond in the colorimetric indicator exposed to fish spoilage. The prepared indicator demonstrated good stability and remained unaffected by pH or other volatile compounds. Notably, there was a strong correlation between ΔΕ and fish freshness parameters (pH, TV-BN, and TVC). Light green, pale yellow, and dark yellow colors, respectively, indicated freshness, semi-freshness, and spoilage of fish during storage in the refrigerator. Overall, the prepared indicator can be effectively used for detecting spoilage in meat products as a highly sensitive freshness indicator.

Relationship between maternal biological features, environmental factors, and newborn neuromotor development associated with visual fixation abilities

Newborn visual fixation abilities predict future cognitive, perceptive, and motor skills. However, little is known about the factors associated with the newborn visual fixation, which is an indicator of neurocognitive abilities. We analyzed maternal biological and environmental characteristics associated with fine motor skills (visual tracking) in 1 month old infants. Fifty-one infants were tested on visual tracking tasks (Infant Visuomotor Behavior Assessment Scale/ Guide for the Assessment of Visual Ability in Infants) and classified according to visual conducts scores. Differences between groups were compared considering motor development (Alberta Infant Motor Scale) maternal mental health (Edinburgh Postnatal Depression Scale and Hamilton Anxiety Scale); home environment (Affordances in the Home Environment for Development Scale); maternal care (Coding Interactive Behavior); breastmilk composition (total fatty acids, proteins, and cortisol); and maternal metabolic profile (serum hormones and interleukins). Mothers of infants with lower visual fixation scores had higher levels of protein in breastmilk at 3 months. Mothers of infants with better visual conduct scores had higher serum levels of T4 (at 1 month) and prolactin (at 3 months). There were no associations between visual ability and motor development, home environment, or maternal care. Early newborn neuromotor development, especially visual and fine motor skills, is associated with maternal biological characteristics (metabolic factors and breastmilk composition), highlighting the importance of early detection of maternal metabolic changes for the healthy neurodevelopment of newborns.

A novel method for measurements of sleep/wake states, feeding and drinking behaviors using the tracking technique of 3D positions in freely moving mice

We have previously developed a 3D video tracking system which enables us to analyze long-term quantitative analysis of gene expression in freely moving mice. In the present study, we improved 3D video tracking and developed a system that analyzes more detailed behavioral data. We succeeded in simultaneously analyzing sleep-wake, feeding, and drinking behavior rhythms in the same individual using our tracking system. This system will make it possible to measure gene expression in each tissue in vivo in real time in relation to the various behavioral rhythms mentioned above.

Review and Analysis of RGBT Single Object Tracking Methods: A Fusion Perspective

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.

Efficient Vibration Measurement and Modal Shape Visualization Based on Dynamic Deviations of Structural Edge Profiles.

As a non-contact method, vision-based measurement for vibration extraction and modal parameter identification has attracted much attention. In most cases, artificial textures are crucial elements for visual tracking, and this feature limits the application of vision-based vibration measurement on textureless targets. As a computation technique for visualizing subtle variations in videos, the video magnification technique can analyze modal responses and visualize modal shapes, but the efficiency is low, and the processing results contain clipping artifacts. This paper proposes a novel method for the application of a modal test. In contrast to the deviation magnification that exaggerates subtle geometric deviations from only a single image, the proposed method extracts vibration signals with sub-pixel accuracy on edge positions by changing the perspective of deviations from space to timeline. Then, modal shapes are visualized by decoupling all spatial vibrations following the vibration theory of continuous linear systems. Without relying on artificial textures and motion magnification, the proposed method achieves high operating efficiency and avoids clipping artifacts. Finally, the effectiveness and practical value of the proposed method are validated by two laboratory experiments on a cantilever beam and an arch dam model.

An optically responsive cancer vaccine for inducing robust anti-tumor immunity by apoptotic body carrying nanoadjuvants

A cancer vaccine based on nano-adjuvant fusion represents an effective strategy for anti-tumor immunity. Compared with other cancer vaccine formulations, the ones based on apoptotic bodies not only possess higher load-bearing capacity and biosafety, but also present greater clinical translational potential. In this study, we developed an optically responsive cancer vaccine that induced robust anti-tumor immunity by encapsulating genipin-crosslinked nano-adjuvants in tumor cell apoptotic bodies. The vaccine may potentially be used for prophylactic or therapeutic purposes. As an antigen source and a cargo vehicle, apoptotic bodies can co-deliver antigens and adjuvants simultaneously to antigen-presenting cells to activate T cells. Nano-adjuvants promote the targeted delivery of adjuvants for effective immune responses. Genipin-crosslinked nano-adjuvants enable visual tracking of the tumor vaccine. In addition, the photothermal properties of genipin-crosslinked nano-adjuvants promote lysosomal escape of tumor antigens to enhance cross-presentation. These characteristics enable visualization and controllability of cancer vaccines, thereby avoiding the need for exogenous photosensitive reagents. Apoptotic body-based vaccines can be used to prevent or treat tumors by triggering a strong systemic immune response by promoting T-cell infiltration and improving the tumor immune microenvironment.

Measuring activity-rest rhythms under different acclimation periods in a marine fish using automatic deep learning-based video tracking

ABSTRACT Most organisms synchronize to an approximately 24-hour (circadian) rhythm. This study introduces a novel deep learning-powered video tracking method to assess the stability, fragmentation, robustness and synchronization of activity rhythms in Xyrichtys novacula. Experimental X. novacula were distributed into three groups and monitored for synchronization to a 14/10 hours of light/dark to assess acclimation to laboratory conditions. Group GP7 acclimated for 1 week and was tested from days 7 to 14, GP14 acclimated for 14 days and was tested from days 14 to 21 and GP21 acclimated for 21 days and was tested from days 21 to 28. Telemetry data from individuals in the wild depicted their natural behavior. Wild fish displayed a robust and minimally fragmented rhythm, entrained to the natural photoperiod. Under laboratory conditions, differences in activity levels were observed between light and dark phases. However, no differences were observed in activity rhythm metrics among laboratory groups related to acclimation period. Notably, longer acclimation (GP14 and GP21) led to a larger proportion of individuals displaying rhythm synchronization with the imposed photoperiod. Our work introduces a novel approach for monitoring biological rhythms in laboratory conditions, employing a specifically engineered video tracking system based on deep learning, adaptable for other species.

Correlation filter based single object tracking: A review

In recent years, correlation filter-based (CF) tracking algorithms have gained momentum in the field of visual tracking. CF tracking algorithms have achieved compelling performance by addressing its limitations such as boundary effect and filter corruption during various tracking and target appearance variations. Many researchers have attempted to provide better efficiency and tracking results by extracting handcrafted and deep features either from vision sensors or specialized sensors in the CF tracking framework. Handcrafted features are integrated with deep features, thermal features, and depth features to prevent tracking failures during dense tracking challenges. To provide a detailed understanding of CF-based trackers, the tracking algorithms are categorized either as kernelized CF trackers or fusion-based CF trackers in this work. This is the first review of its kind, which categorizes various correlation-based tracking algorithms based on the key methodologies and the exploited features in the appearance model. Under each category, salient features, detailed overview, and current advancement are discussed and tabulated to provide future research directions. In addition, the performance of CF-based state-of-the-art is experimentally evaluated on multiple datasets namely, OTB100 and VOT2017 under tough tracking situations.

Decoder-ROI based Versatile Video Coding for Multi-Object Tracking Vision Task

The video encoding standards High Efficiency Video Coding (HEVC) and, more recently, Versatile Video Coding (VVC) have introduced significant advancements in multimedia communication applications, such as video conferencing, broadcasting, and notably, E-learning. However, recent developments in artificial intelligence (AI) and big data have given rise to an urgent need for a specialized video encoding model designed specifically for image and video analysis applications using machine vision. In this paper, we propose a novel video encoding approach that effectively combines the ROI Coding algorithm and the VVC encoding model. The proposed method identifies regions of interest within video frames through fundamental and deep features. Based on this, we propose an adaptive compression method for each frame block, ensuring both the execution performance of machine learning applications and minimal data encoding requirements. To achieve new coding scheme without adding bitrate, New feature extraction approach are utilizing only decoded information (Decoder-ROI). The results demonstrate that the Decoder-ROI achieved significant compression rate improvement when compared to standard and relevant VCM schemes. Furthermore, ROI exploitation contributes to a 3.25\% reduction in encoding time compared to the baseline VVC encoding standard.

LSOTB-TIR: A Large-Scale High-Diversity Thermal Infrared Single Object Tracking Benchmark.

Unlike visual object tracking, thermal infrared (TIR) object tracking methods can track the target of interest in poor visibility such as rain, snow, and fog, or even in total darkness. This feature brings a wide range of application prospects for TIR object-tracking methods. However, this field lacks a unified and large-scale training and evaluation benchmark, which has severely hindered its development. To this end, we present a large-scale and high-diversity unified TIR single object tracking benchmark, called LSOTB-TIR, which consists of a tracking evaluation dataset and a general training dataset with a total of 1416 TIR sequences and more than 643 K frames. We annotate the bounding box of objects in every frame of all sequences and generate over 770 K bounding boxes in total. To the best of our knowledge, LSOTB-TIR is the largest and most diverse TIR object tracking benchmark to date. We spilt the evaluation dataset into a short-term tracking subset and a long-term tracking subset to evaluate trackers using different paradigms. What's more, to evaluate a tracker on different attributes, we also define four scenario attributes and 12 challenge attributes in the short-term tracking evaluation subset. By releasing LSOTB-TIR, we encourage the community to develop deep learning-based TIR trackers and evaluate them fairly and comprehensively. We evaluate and analyze 40 trackers on LSOTB-TIR to provide a series of baselines and give some insights and future research directions in TIR object tracking. Furthermore, we retrain several representative deep trackers on LSOTB-TIR, and their results demonstrate that the proposed training dataset significantly improves the performance of deep TIR trackers. Codes and dataset are available at https://github.com/QiaoLiuHit/LSOTB-TIR.

A study on dual quaternion based cooperative relative navigation of multiple UAVs with monocular vision-inertial integration

This paper addresses a cooperative relative navigation problem for multiple aerial agents, relying on visual tracking information between vehicles. The research aims to investigate a sensor fusion architecture and algorithm that leverages partially available absolute navigation knowledge while exploiting collaborative visual interaction between vehicles in mission flight areas, where satellite navigation-denied regions are irregularly located. To achieve this, the paper introduces a new approach to defining the relative poses of cameras and develops a corresponding process to secure the relative pose information. This contrasts with previous research, which simply linearized the relative pose information of aircraft cameras into navigation states defined in an absolute coordinate system. Specifically, the target pose in relative navigation is defined, and the pose of the camera and feature points are directly derived using dual quaternion representation, which compactly represents both translation and rotation. Furthermore, a mathematical model for the relative pose of the camera is derived through the dual quaternion framework, enabling an explicit pose formulation of relative navigation. The study investigates navigation performance in typical mission flight scenarios using an in-house high-fidelity simulator and quantitatively highlights the contributions of the proposed scheme by comparing the navigation error performance. Consequently, the proposed method demonstrates to have navigation accuracy in decimeter level even in GNSS-denied environments and an improved 3D Root Mean Square (RMS) error by 30% smaller than the conventional absolute navigation framework.

Probabilistic Assignment With Decoupled IoU Prediction for Visual Tracking

Probabilistic Assignment With Decoupled IoU Prediction for Visual Tracking

Self-Supervised Tracking via Target-Aware Data Synthesis.

While deep-learning-based tracking methods have achieved substantial progress, they entail large-scale and high-quality annotated data for sufficient training. To eliminate expensive and exhaustive annotation, we study self-supervised (SS) learning for visual tracking. In this work, we develop the crop-transform-paste operation, which is able to synthesize sufficient training data by simulating various appearance variations during tracking, including appearance variations of objects and background interference. Since the target state is known in all synthesized data, existing deep trackers can be trained in routine ways using the synthesized data without human annotation. The proposed target-aware data-synthesis method adapts existing tracking approaches within a SS learning framework without algorithmic changes. Thus, the proposed SS learning mechanism can be seamlessly integrated into existing tracking frameworks to perform training. Extensive experiments show that our method: 1) achieves favorable performance against supervised (Su) learning schemes under the cases with limited annotations; 2) helps deal with various tracking challenges such as object deformation, occlusion (OCC), or background clutter (BC) due to its manipulability; 3) performs favorably against the state-of-the-art unsupervised tracking methods; and 4) boosts the performance of various state-of-the-art Su learning frameworks, including SiamRPN++, DiMP, and TransT.