People Tracking Research Articles

Activity spaces of homeless men and women measured by GPS tracking data: A comparative analysis of Prague and Pilsen

The aim of this article is to investigate the factors that influence the size of activity spaces of homeless men and women in cities. Vulnerable population groups such as the homeless face the risk of mobility challenges that can exacerbate their social exclusion even more through mobility-driven spatial exclusion. The extent of an individual's activity space is a key precondition for the daily coping strategies and life opportunities of homeless people. This study is the first to combine GPS tracking of homeless people based on a week-long GPS measurement with mobility interviews. The article tests five hypotheses as to the influence of city size, age, gender, housing situation and education on the size of activity space. Data obtained for a large city (Prague) and for a small city (Pilsen) are analysed using three geospatial measurements of activity spaces. In line with mixed-method approaches, the results are further triangulated through mobility interviews. By mapping the objective activity spaces, we were able to evaluate the role of individual and contextual factors in shaping homeless life and discuss the theoretical and practical implications of activity space measurement for social policy and urban planning.

People tracking in multi-camera systems: a review

Ubiquitousness of multiple cameras in surveillance systems is very beneficial for studying peoples behavior. The multiple views of the observed scene permit the management of dynamic occlusions and failures that may affect any sensor. The multi-camera tracking of objects is considered as the basic step in the design of intelligent surveillance applications. This thematic had been addressed in several researches. Various methods had been proposed to achieve an accurate tracking in the most challenging conditions as occlusions and lighting variations. These methods are addressed in two main research lines: the centralized and the distributed tracking approaches. In this paper, we propose an overview of the multi-camera tracking of objects which summarizes and classifies the most used existing methods.

Tracking two pleasures

Can people track several pleasures? In everyday life, pleasing stimuli rarely appear in isolation. Yet, experiments on aesthetic pleasure usually present only one image at a time. Here, we ask whether people can reliably report the pleasure of either of two images seen in a single glimpse. Participants (N = 13 in the original; +25 in the preregistered replication) viewed 36 Open Affective Standardized Image Set (OASIS) images that span the entire range of pleasure and beauty. On each trial, the observer saw two images, side by side, for 200 ms. An arrow cue pointed, randomly, left, right, or bidirectionally. Left or right indicated which image (the target) to rate while ignoring the other (the distractor); bidirectional requested rating the combined pleasure of both images. In half the blocks, the cue came before the images (precuing). Otherwise, it came after (postcuing). Precuing allowed the observer to ignore the distractor, while postcuing demanded tracking both images. Finally, we obtained single-pleasure ratings for each image shown alone. Our replication confirms the original study. People have unbiased access to their felt pleasure from each image and the average of both. Furthermore, the variance of the observer’s report is similar whether reporting the pleasure of one image or the average pleasure of two. The undiminished variance for reports of the average pleasure of two images indicates either that the underlying pleasure variances are highly correlated, or, more likely, that the variance arises in the common reporting process. In brief, observers can faithfully track at least two visual pleasures.

Tracking and people counting using Particle Filter Method

In recent years, technology has developed quite rapidly, especially in the field of object tracking. Moreover, if the object under study is a person and the number of people a lot. The purpose of this research is to apply Particle Filter method for tracking and counting people in certain area. Tracking people will be rather difficult if there are some obstacles, one of which is occlusion. The stages of tracking and people counting scheme in this study include pre-processing, segmentation using Gaussian Mixture Model (GMM), tracking using particle filter, and counting based on centroid. The Particle Filter method uses the estimated motion included in the model used. The test results show that the tracking and people counting can be done well with an average accuracy of 89.33% and 77.33% respectively from six videos test data. In the process of tracking people, the results are good if there is partial occlusion and no occlusion

Going Out: A Sociology of Public Outings

In this article we propose a framework for description and analysis of public life by treating “outings” as a unit of sociological analysis. Studying outings requires bracketing a concern with bounded places and isolated encounters. Instead, descriptions of outings track people as they organize trips “out,” including their preparations, turning points, and post hoc reflections. We emphasize how people understand and contextualize their time in public by linking situated moments of public life to the outing’s unfolding trajectory and to people’s biographical circumstances. We treat outings in and through public parks as a strategic site to show the utility of studying public outings more generally. A sociology of outings has broad theoretical and methodological implications for how we understand the collective patterning of public life and inequality in everyday encounters.

Abnormal events’ detection in crowded scenes

In this paper, two new methods are developed in order to detect and track unexpected events in scenes. The process of detecting people may face some difficulties due to poor contrast, noise and the small size of the defects. For this purpose,the perfect knowledge of the geometry of these defects is an essential step in assessing the quality of detection. First, we collected statistical models of the element for each individual for time tracking of different people using the technique of Gaussian mixture model (GMM). Then we improved this method to detect and track the crowd(IGMM). Thereafter, we adopted two methods: the differential method of Lucas and Kanade(LK) and the method of optical flow estimation of Horn Schunck(HS) for optical flow representation. Then, we proposed a novel descriptor, named the Distribution of Magnitude of Optical Flow (DMOF) for anomalous events’ detection in the surveillance video. This descriptor represents an algorithm whose aim is to accelerate the action of abnormal events’ detection based on a local adjustment of the velocity field by manipulating the light intensity.

Smartphone-Based Cooperative Indoor Localization with RFID Technology.

In GPS-denied indoor environments, localization and tracking of people can be achieved with a mobile device such as a smartphone by processing the received signal strength (RSS) of RF signals emitted from known location beacons (anchor nodes), combined with Pedestrian Dead Reckoning (PDR) estimates of the user motion. An enhacement of this localization technique is feasible if the users themselves carry additional RF emitters (mobile nodes), and the cooperative position estimates of a group of persons incorporate the RSS measurements exchanged between users. We propose a centralized cooperative particle filter (PF) formulation over the joint state of all users that permits to process RSS measurements from both anchor and mobile emitters, as well as PDR motion estimates and map information (if available) to increase the overall positioning accuracy, particularly in regions with low density of anchor nodes. Smartphones are used as a convenient mobile platform for sensor measurements acquisition, low-level processing, and data transmission to a central unit, where cooperative localization processing takes place. The cooperative method is experimentally demonstrated with four users moving in an area of 1600 , with 7 anchor nodes comprised of active RFID (radio frequency identification) tags, and additional mobile tags carried by each user. Due to the limited coverage provided by the anchor beacons, RSS-based individual localization is inaccurate (6.1 m median error), but this improves to 4.9 m median error with the cooperative PF. Further gains are produced if the PDR information is added to the filter: median error of 3.1 m (individual) and 2.6 m (cooperative); and if map information is also considered, the results are 1.8 m (individual) and 1.6 m (cooperative). Thus, for each version of the particle filter, cooperative localization outperforms individual localization in terms of positioning accuracy.

Constrained multi-target tracking for team sports activities

In sports analysis, player tracking is essential to the extraction of statistics such as speed, distance and direction of motion. Simultaneous tracking of multiple people is still a very challenging computer vision problem to which there is no satisfactory solution. This is especially true for sports activities, for which people often wear similar uniforms, move quickly and erratically, and have close interactions with each other. In this paper, we introduce a multi-target tracking algorithm suitable for team sports activities. We extend an existing algorithm by including an automatic estimation of the occupancy of the observed field and the duration of stable periods without people entering or leaving the field. This information is included as a constraint to the existing offline tracking algorithm in order to construct more reliable trajectories. On data from two challenging sports scenarios—an indoor soccer game captured with thermal cameras and an outdoor soccer training session captured with RGB camera—we show that the tracking performance is improved on all sequences. Compared to the original offline tracking algorithm, we obtain improvements of 3–7% in accuracy. Furthermore, the method outperforms two state-of-the-art trackers.

Benchmark Dataset for Evaluation of Range-Based People Tracker Classifiers in Mobile Robots.

Benchmark dataset which can be used to evaluate the performance of different approaches for detecting and tracking people by using lidar sensors. Information contained at the dataset is specially suitable to be used as training data for neural network-based classifiers

ARTIFICIAL VISION ALGORITHMS AND APPLICATIONS: CASE OF PEOPLE`S IDENTIFICATION AND TRACKING

Ponte Academic JournalApr 2018, Volume 74, Issue 4 ARTIFICIAL VISION ALGORITHMS AND APPLICATIONS: CASE OF PEOPLE`S IDENTIFICATION AND TRACKINGAuthor(s): Cristina Paez Quinde ,Victor Hernandez del Salto, Javier Sanchez Guerrero, Veronica E. Chicaiza R., Mocha-Bonilla Julio A.J. Ponte - Apr 2018 - Volume 74 - Issue 4 doi: 10.21506/j.ponte.2018.4.6 Abstract:Artificial vision is used in several areas, one of them is the fight against terrorism, the insecurity due to crime through efficient systems capable of recognizing strange or different situations of a routine, as well as vehicular traffic scenarios. The study shows how video surveillance in the detection of objects that are find moving is important for the detection of complex situations, aspects that should be considered such as the variation in lighting, shadow, background and disorder that show the video sequences. The detection and consequently the tracking of people and body parts of them is of high importance in the understanding of human tasks, the most used mechanism is the video surveillance different from the traditional in this case it is an automated and intelligent surveillance that allows it to become an active research area to the great demand of systems in large areas of massive concurrence of people such as airports, educational institutions at all levels, train stations, buses and at the same time massive events. In conclusion, the artificial vision is a great support within the surveillance networks, because they are monitored by specific personnel, who oversee large amounts of monitoring that are fed by the cameras, therefore, the use of artificial vision optimizes and at the same time makes the process of detecting daily routines effective. Download full text:Check if you have access through your login credentials or your institution Username Password

Searching and tracking people with cooperative mobile robots

Social robots should be able to search and track people in order to help them. In this paper we present two different techniques for coordinated multi-robot teams for searching and tracking people. A probability map (belief) of a target person location is maintained, and to initialize and update it, two methods were implemented and tested: one based on a reinforcement learning algorithm and the other based on a particle filter. The person is tracked if visible, otherwise an exploration is done by making a balance, for each candidate location, between the belief, the distance, and whether close locations are explored by other robots of the team. The validation of the approach was accomplished throughout an extensive set of simulations using up to five agents and a large amount of dynamic obstacles; furthermore, over three hours of real-life experiments with two robots searching and tracking were recorded and analysed.

Comparing eye movements during position tracking and identity tracking: No evidence for separate systems

There is an ongoing debate as to whether people track multiple moving objects in a serial fashion or with a parallel mechanism. One recent study compared eye movements when observers tracked identical objects (Multiple Object Tracking-MOT task) versus when they tracked the identities of different objects (Multiple Identity Tracking-MIT task). Distinct eye-movement patterns were found and attributed to two separate tracking systems. However, the same results could be caused by differences in the stimuli viewed during tracking. In the present study, object identities in the MIT task were invisible during tracking, so observers performed MOT and MIT tasks with identical stimuli. Observer were able to track either position and identity depending on the task. There was no difference in eye movements between position tracking and identity tracking. This result suggests that, while observers can use different eye-movement strategies in MOT and MIT, it is not necessary.

Online Shopping and Social Media: Friends or Foes?

As social network use continues to increase, an important question for marketers is whether consumers’ online shopping activities are related to their use of social networks and, if so, what the nature of this relationship is. On the one hand, spending time on social networks could facilitate social discovery, meaning that consumers “discover” or “stumble upon” products through their connections with others. Moreover, cumulative social network use could expose consumers to new shopping-related information, possibly with greater marginal value than the incremental time spent on a shopping website. This process may therefore be associated with increased shopping activity. On the other hand, social network use could be a substitute for other online activities, including shopping. To test the relationship between social network use and online shopping, the authors leverage a unique consumer panel data set that tracks people's browsing of shopping and social network websites and their online purchasing activities over one year. The authors find that greater cumulative usage of social networking sites is positively associated with shopping activity. However, they also find a short-term negative relationship, such that immediately after a period of increased usage of social networking sites, online shopping activity appears to be lower.

Inverse Source Data-Processing Strategies for Radio-Frequency Localization in Indoor Environments.

Indoor positioning of mobile devices plays a key role in many aspects of our daily life. These include real-time people tracking and monitoring, activity recognition, emergency detection, navigation, and numerous location based services. Despite many wireless technologies and data-processing algorithms have been developed in recent years, indoor positioning is still a problem subject of intensive research. This paper deals with the active radio-frequency (RF) source localization in indoor scenarios. The localization task is carried out at the physical layer thanks to receiving sensor arrays which are deployed on the border of the surveillance region to record the signal emitted by the source. The localization problem is formulated as an imaging one by taking advantage of the inverse source approach. Different measurement configurations and data-processing/fusion strategies are examined to investigate their effectiveness in terms of localization accuracy under both line-of-sight (LOS) and non-line of sight (NLOS) conditions. Numerical results based on full-wave synthetic data are reported to support the analysis.

Gesture based Human Computer Interaction for Athletic Training

The invention of depth sensors for mobile devices, has led to availability of relatively inexpensive high-resolution depth and visual (RGB) sensing for a wide range of applications. The complementary nature of the depth and visual information opens up new opportunities to solve fundamental problems in object and activity recognition, people tracking, 3D mapping and localization, etc. One of the most interesting challenges that can be tackled by using these sensors is tracking the body movements of athletes and providing natural interaction as a result. In this study depth sensors and gesture recognition tools will be used to analyze the position and angle of an athlete’s body parts thought out an exercise. The goal is to assess the training performance of an athlete and decrease injury risk by giving warnings when the trainer is performing a high risk activity.

Robust Tracking Occluded Human in Group by Perception Sensors Network System

Tracking people even being partially or fully occluded in the group situation is studied using a Perception Sensor Network (PSN) system which is composed of multiple Kinects used to detect human 3D locations, and pan tilt zoom (PTZ) cameras used to identify human faces. A method is proposed to fuse multiple detection of human in the PSN system. After associating detected human with corresponding names, the novel grouping and ungrouping algorithms are proposed. When a group of multiple human staying close together is formed, viewpoint and illumination invariant features of group members including human 3D location, height, color and binary robust invariant scalable keypoint (BRISK), retrieved from region of interest (ROI) of both depth and color images, are then stored and updated into the group database. Based on the distance between a group location at previous frame and each member location in the group at current frame, the PSN system decides whether to keep the members in the group or to ungroup them then reassign the right name among the group database by minimizing multiple criterions. The experimental results demonstrate the outperforming of the proposed method on tracking people in group than conventional methods.

An Empirical Design Space Analysis of Doorway Tracking Systems for Real-World Environments

Doorway tracking systems track people’s room location by instrumenting the doorways rather than instrumenting the rooms themselves—resulting in fewer sensors and less monitoring while still providing location information on occupants. In this article, we explore what is required to make doorway tracking a practical solution. We break a doorway tracking system into multiple independent design components, including both sensor and algorithmic design. Informed by this design, we construct a doorway tracking system and analyze how different combinations of these design components affect tracking accuracy. We perform a six-day in situ study in a ten-room house with two volunteers to analyze how these design components respond to the natural types and frequencies of errors in a real-world setting. To reflect the needs of different application classes, we analyze these design components using three different evaluation metrics: room accuracy, duration accuracy, and transition accuracy. Results indicate that doorway tracking can achieve 99.5% room accuracy on average in controlled settings and 96% room accuracy in in situ settings. This is contrasted against the 76% in situ setting room accuracy of Doorjamb, a doorway tracking system whose design implements only a limited number of components in our proposed doorway tracking system design space. We describe the differences between the data in the in situ and controlled settings, and provide guidelines about how to design a doorway tracking system for a given application’s accuracy requirements.

Tracking People in Highly Dynamic Industrial Environments

To date, the majority of positioning systems have been designed to operate within environments that have long-term stable macro-structure with potential small-scale dynamics. These assumptions allow the existing positioning systems to produce and utilize stable maps. However, in highly dynamic industrial settings these assumptions are no longer valid and the task of tracking people is more challenging due to the rapid large-scale changes in structure. In this paper we propose a novel positioning system for tracking people in highly dynamic industrial environments, such as construction sites. The proposed system leverages the existing CCTV camera infrastructure found in many industrial settings along with radio and inertial sensors within each worker's mobile phone to accurately track multiple people. This multi-target multi-sensor tracking framework also allows our system to use cross-modality training in order to deal with the environment dynamics. In particular, we show how our system uses cross-modality training in order to automatically keep track environmental changes (i.e. new walls) by utilizing occlusion maps. In addition, we show how these maps can be used in conjunction with social forces to accurately predict human motion and increase the tracking accuracy. We have conducted extensive real-world experiments in a construction site showing significant accuracy improvement via cross-modality training and the use of social forces.

Deviation maps for robust and informed indoor positioning services

The ability to position and track people and assets has become increasingly widespread and important in business and personal life. The prevalent means for such tasks is signal-strength-based, prominently WiFi-based, positioning, together with GNSS positioning. The latter, however, is insufficient for the majority of indoor environments in which most of our work and personal lives takes place. Signal-strength-based positioning, though, too, is error-prone in real-life building environments, suffering from large biases induced by the often many and complex attenuating elements in the environment. Additionally, in the prevalent signal-strength-based positioning methods, which rely solely on signal pattern matching, such biases and errors are hard to assess and thus positioning quality and glitches hard to predict. We present an approach for assessing, visualizing, and counter-acting positioning biases and impairments in signal-strength-based positioning. This approach, centered around the notion of deviation maps, aim at improving positioning quality and predictability/reliability and, at the same time, at gaining knowledge and understanding of tracking quality. We seek to understand how the tracking quality is influenced by both positioning installation and building environment, and how the former may be altered to better suit the latter. We discuss results from applying our approach in a real-world large-scale work environment, a major hospital spanning 160,000 square meters, as well as lessons learned from the underlying experimentation-driven and use-centric design process. From these lessons we also derive directions for future work.

Forward scatter radar for remote intelligence of building interiors

Through-wall radar allows for remote intelligence of building interiors including stand-off detection and tracking of persons inside a building. However, reliable radar tracking of people inside a building is not trivial. Conventional, monostatic through-wall radar measures the backscatter of moving people. The backscatter from a human is relatively low compared with the scattering from building features or furniture. The forward scatter radar (FSR) concept is proposed to detect and possibly track moving people in specific areas of a building. The FSR concept exploits the forward scatter (FS) of objects, which is typically larger than their backscatter; for humans a factor of 20 is possible. It is shown that stand-off detection of moving people inside a building can be performed reliably and consistently based on their FS.