Using social effects to guide tracking in complex scenes

Target detection and tracking important in many applications including intelligent monitoring system, defense system and terminal guidance system. Aiming to solve the problem of simulated target tracking, this paper proposes an adaptive algorithm which uses the fusion of the spectral and morphological features of multispectral image to realize the target tracking based on the Particle Filter. Firstly, the target area is manually initialized in the multispectral image and the spectral and texture features of the target are extracted. Secondly, we build the adaptive tracking model of multiple features under the framework of Particle Filter. We validate the effectiveness of the proposed approach on the MATLAB platform. The results show that the proposed approach achieves accurate and stable multispectral target tracking in complex scenes by improving the efficiency of particles usage under defective tracking conditions, which is of great theoretical and practical values for the application of multispectral target tracking technology.

In this paper, by analyzing the characteristics of infrared moving targets, a Symmetric Frame Differencing Target Detection algorithm based on local clustering segmentation is proposed. In consideration of the high real-time performance and accuracy of traditional symmetric differencing, this novel algorithm uses local grayscale clustering to accomplish target detection after carrying out symmetric frame differencing to locate the regions of change. In addition, the mean shift tracking algorithm is also improved to solve the problem of missed targets caused by error convergence. As a result, a kernel-based mean shift target tracking algorithm based on detection updates is also proposed. This tracking algorithm makes use of the interaction between detection and tracking to correct the tracking errors in real time and to realize robust target tracking in complex scenes. In addition, the validity, robustness and stability of the proposed algorithms are all verified by experiments on mid-infrared aerial sequences with vehicles as targets.

Particle filter (PF) based object tracking methods have been widely used in computer vision. However, traditional particle filter trackers cannot effectively distinguish the target from the background in complex scenes since they only exploit appearance information of observation to determine the target region. In this paper, we present an adaptive particle filter based on energy field (EPF), which makes good use of moving information of previous frames adaptively to track the target. Besides, we present the mechanism of result rectification to ensure the target region is accurate. Experiment results on several challenging video sequences have verified that the adaptive EPF method is compared very robust and effective with the traditional particle filter in many complicated scenes.KeywordsTrackingparticle filterprobabilistic approximationimage sequence analysisdynamic scenes

In this paper we propose a pixel-wise visual tracking method using a novel tri-model representation. The newly proposed tri-model is composed of three models, which each model learns the target object, the background, and other non-target moving objects online. The proposed method performs tracking by simultaneous estimation of the holistic position of the target object and the pixel-wise labels. By utilizing the information in the background and the foreground models as well as the target model, our method obtains robust results even under background clutters and partial occlusions in complex scenes. Furthermore, our method is able to give pixel-wise results, and uses them in the learning process to prevent drifting. The method is extensively tested against seven representative trackers both quantitatively and qualitatively showing promising results.

Planar object tracking is an important research area of visual target tracking. In order to improve the speed and accuracy of plane object tracking in complex scenes, this paper proposes a coarse-to-fine plane object tracking algorithm based on fully convolutional dense network. First, the estimated bounding box of the target object in the input image is calculated according to the DiMP50 algorithm; then SIFT is used to locate the key points on the image, and the feature descriptors corresponding to the key points are extracted from the feature map generated based on the cascaded thick and thin dense network. The nearest neighbor algorithm matches the feature descriptors to obtain the paired keypoint set; then the roughly positioned bounding box is used as the a priori box to screen the matching keypoints from coarse to fine, and the keypoints in the a priori box are retained, using RANSAC algorithm estimates the optimal homography matrix parameters for the key points; finally, the real value is calculated by the homography matrix to obtain the final prediction frame of the target. Validated on the POT dataset, the results show that the performance of the planar object tracking algorithm proposed in this paper is better than the classical algorithm, and the average tracking accuracy on all image sequences reaches 64.76%.

The widespread application of Unmanned Aerial Vehicles (UAVs) has raised serious public safety and privacy concerns, making UAV perception crucial for anti-UAV tasks. However, existing UAV tracking datasets pre-dominantly feature conspicuous objects and lack diversity in scene complexity and attribute representation, limiting their applicability to real-world scenarios. To overcome these limitations, we present the CST Anti-UAV, a new thermal infrared dataset specifically designed for Single Object Tracking (SOT) in Complex Scenes with Tiny UAVs (CST). It contains 220 video sequences with over 240k high-quality bounding box annotations, highlighting two key properties: a significant number of tinysized UAV targets and the diverse and complex scenes. To the best of our knowledge, CST Anti-UAV is the first dataset to incorporate complete manual frame-level attribute annotations, enabling precise evaluations under varied challenges. To conduct an in-depth performance analysis for CST Anti-UAV, we evaluate 20 existing SOT methods on the proposed dataset. Experimental results demonstrate that tracking tiny UAVs in complex environments remains a challenge, as the state-of-the-art method achieves only 35.92% state accuracy, much lower than the 67.69% observed on the Anti-UAV410 dataset. These findings underscore the limitations of existing benchmarks and the need for further advancements in UAV tracking research. The CST Anti-UAV benchmark is about to be publicly released, which not only fosters the development of more robust SOT methods but also drives innovation in anti-UAV systems.

Multi-cue-based Camshift algorithm is presented for object tracking in complex scenes. Because color-based Camshift algorithm suffers from objects with color clutter in backgrounds, this paper integrates motion cue with color cue to extend its application areas. Moreover, the robust real-time multiresolution algorithm is used to obtain motion information in dynamic background. Experimental work verifies that the proposed multiple cues strategy really improves the tracking performance of the classical Camshift using a single cue.

We present an automatic video object tracking algorithm capable of dealing with multiple simultaneous objects. The tracking is based on interactions between high-level and low-level image analysis results. The high-level result is a partition defining video objects, and the low-level result is a partition formed by homogeneous regions. For each region, a set of characteristic descriptors is produced. These region descriptors, and not regions themselves, are used to track the regions (and thus the objects) along time. Track management issues such as appearance and disappearance of objects, splitting and partial occlusions are resolved through interactions between regions and objects. Defining the tracking based on the parts of objects, identified by region segmentation, has led to a flexible technique that exploits the nature of the video object tracking problem. Experimental results show that the proposed method is able to track multiple rigid and deformable objects in indoor and outdoor scenes.

Digitalization is one of the strategic directions taken in the reform of social services and a prerequisite for improving their quality and accessibility for various target groups in modern society. In recent years, the problems of digitalization occupy a significant place in social research; however, insufficient attention has been paid to the consideration of the digitalization process from the point of view of the social services clients themselves. The purpose of this article is to partially fill this gap. The article presents the results of a study aimed at developing the concept of the 'digital capital' of current and potential customers of social services, which comprised an analysis of their digital literacy, Internet use as well as the technical capabilities and willingness of Russian citizens to receive online social services. Our analysis of the digital capital of consumers of social services draws on data of the Federal Statistics Service and Unified Social Security Information System as well as on the results of a survey on social services conducted among residents of St. Petersburg and Yekaterinburg in 2019. The results of the study suggest the existence of various barriers to the development of the digitalization of social services provision. In addition to infrastructural problems, the existence/absence of digital communication tools and ICT competencies among citizens, primarily socially vulnerable sectors of the population, it is necessary to highlight the socio-psychological barriers: a lack of understanding and distrust among certain social groups – primarily among older age groups – towards digital technologies, i. e. insufficient digital capital. Overcoming the identified barriers can be achieved by investing in the digital capital of consumers of social services.

Conventional missile guidance laws assume that only one target is present. This paper considers how a multiple target scenario, with a state estimator represented by a multi-modal probability distribution, could be handled. A control law, based on a bounded terminal cost, is proposed. A simple simulation is used to demonstrate some of its properties.

When selecting feeding, hiding, or resting areas, animals face multiple decisions with different fitness consequences. To maximize efficiency, individuals can either collect personal information, or use information gathered and transmitted by other individuals (social information). Within group living species, organisms often specialize in either generating social information or using information gathered by other groups members. That is the case of the Spix’s disk-winged bat, Thyroptera tricolor. This species uses contact calls during roost finding. Social groups are composed by a mix of vocal and non-vocal individuals and those vocal roles appear to be consistent over time. Moreover, their vocal behavior can predict roost finding in natural settings, suggesting that vocal individuals are capable of generating social information that can be used by other group members. To date, however, we do not know if when presented with social information (contact calls) during roost finding, vocal individuals will make more or less use of these cues, compared to non-vocal individuals. To answer this question, we broadcast contact calls from a roost inside a flight cage to test whether vocal individuals could find a potential roost faster than non-vocal individuals when they encounter sounds that signal the presence of a roost site. Our results suggest that non-vocal individuals select roost sites based primarily on social information, whereas vocal individuals do not rely heavily on social information when deciding where to roost. This study provides the first link between vocal behavior and the use of social information during the search for roosting resources in bats. Incorporating ideas of social roles, and how individuals decide when and where to move based on the use of social information, may shed some light on these and other outstanding questions about the social lives of bats.

The problem of distributed tracking of multiple targets is tackled by exploiting sensor mobility and the presence of sparsity in the sensor data covariance matrix. Sparse matrix decomposition relying on norm-one/two regularization is integrated with a kinematic framework to identify informative sensors, associate them with the targets, and enable them to follow closely the moving targets. Coordinate descent techniques are employed to determine in a distributed way the target-informative sensors, while the modified barrier method is employed to minimize proper error covariance matrices acquired by extended Kalman filtering. Different from existing approaches which force all sensors to move, here, local updating recursive rules are obtained only for the target-informative sensors that can update their location and follow closely the corresponding targets while staying connected. Simulations advocate that the proposed scheme outperforms alternative tracking schemes while accurately tracks multiple targets by imposing mobility only on the target-informative sensors.

Successive POI recommendation is a newly emerged research direction in recent years, which tries to recommend new POIs that the user has not visited before under the premise of knowing the current POIs of users. Previous work on successive POI recommendation only made limited improvements from using the geographical context and social information and so on. However, these approaches are mostly roughly regarded social influences as neighbor relationships and have not deeply studied social influences. Hence, in this paper, we propose a unified POI recommendation model, which is called the periodic and successive point-of-interest recommendation based on the dual social influence. We subdivide the social influence into two social groups, namely, the direct social group with link relationship and the indirect social group with the common checked-in POIs. A stochastic gradient descent based algorithm is adopted to learn the matrix factorization and the experimental study on two real-world datasets demonstrate the effectiveness of the proposed approach over the existing state-of-the-art ones.

Vehicle detection and tracking from a UAV perspective often encounters omission and misdetection due to the small targets, complex scenes and target occlusion, which finally influences hugely on detection accuracy and target tracking stability. Additionally, the number of parameters of current model is large that makes it is hard to be deployed on mobile devices. Therefore, this paper proposes a YOLO-LMP and NGCTrack-based target detection and tracking algorithm to address these issues. Firstly, the performance of detecting small targets in occluded scenes is enhanced by adding a MODConv to the small-target detection head and increasing its size; In addition, excessive deletion of prediction boxes is prevented by utilizing LSKAttention mechanism to adaptively adjust the target sensing field at the downsampling stage and combining it with the Soft-NMS strategy. Furthermore, the C2f module is replaced by the FPW to reduce the pointless computation and memory utilization of the model. At the target tracking stage, the so-called NGCTrack in our algorithm replaces IOU with GIOU and employs a modified NSA Kalman filter to adjust the state-space aspect ratio for width prediction. Finally, the camera adjustment mechanism was introduced to improve the precision and consistency of tracking. The experimental results show that, compared to YOLOv8, the YOLO-LMP model improves map50 and map50:95 metrics by 10.3 and 12.2%, respectively and the number of parameters is decreased by 47.7%. After combined it with the improved NGCTrack, the number of IDSW reduced by 73.6% compared to the ByteTrack method, while the MOTA and IDF1 increase by 5.2 and 9.8%, respectively.

Although there is a tradition of examining generalized discrimination against multiple targets, recent studies have tended to consider race and homosexuality as separate targets without considering their relationship with each other. Recent studies have also argued for a moral dimension in attitudes to homosexuality, but this has not yet been explicitly modeled as an explanation for patterns of social attitudes. In a questionnaire study of practicing Australian Christians (N= 143), we examined the relationship of religious orientation and ideology (intrinsic, extrinsic, fundamentalism, orthodoxy, and quest) with four attitude targets (Aboriginal Australians, women, homosexual persons, and abortion). Using structural equation modeling (SEM), we develop a two‐factor model, incorporating group and moral orientation factors, which completely mediates the relationships between the religiosity variables and the social attitudes. Religiosity variables exhibit different patterns of correlation with the two factors. The two‐factor model provides a useful framework for further exploration of socially and politically contested attitudes.