Probabilistic data association methods in visual tracking of groups

Gennari, G.; Hager, Gregory D.

doi:10.1109/cvpr.2004.1315257

Cited by 42 publications

(41 citation statements)

References 4 publications

(2 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Usually, people detectors (or pedestrian detectors) focus on detecting every person, that is supposed to be fully visible. However, people often walk in groups, that are composed of a number of people that are fully visible, and just side by side, or cause little occlusion [12,13,14]. A crowd is, on the other hand, a group in which people are so close that the occlusion level is sensibly high, and a few people (or even none) are fully visible [11].…”

Section: Crowd and Groupsmentioning

confidence: 99%

Texture-Based Crowd Detection and Localisation

Ghidoni¹,

Cielniak

Menegatti³

2013

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

This paper presents a crowd detection system based on texture analysis. The state-of-the-art techniques based on co-occurrence matrix have been revisited and a novel set of features proposed. These features provide a richer description of the co-occurrence matrix, and can be exploited to obtain stronger classification results, especially when smaller portions of the image are considered. This is extremely useful for crowd localisation: acquired images are divided into smaller regions in order to perform a classification on each one. A thorough evaluation of the proposed system on a real world data set is also presented: this validates the improvements in reliability of the crowd detection and localisation.

show abstract

Section: Crowd and Groupsmentioning

confidence: 99%

Texture-Based Crowd Detection and Localisation

Ghidoni¹,

Cielniak

Menegatti³

2013

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

show abstract

“…In the recent surveillance approaches, tracking applications are undoubtedly the workhorses, focusing on each person in the scene, capturing its trajectory, helping in analyzing its motion, gestures, etc.. Recently, the focus has been moved beyond the mere multi-object tracking, considering the groups as interesting entities [27,47,16,69,53,42,44,22,40]. Capturing groups of people helps in defining a visual context where a particular person may be better recognized [73], it enriches the expressivity of a surveillance profiling, and is indeed necessary when the number of people in the scene is too high for employing the simultaneus tracking of multiple persons.…”

Section: Surveillance and Monitoringmentioning

confidence: 99%

Socially intelligent surveillance and monitoring: Analysing social dimensions of physical space

Cristani

Murino

Vinciarelli

2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops

View full text Add to dashboard Cite

In general terms, surveillance and monitoring technologies aim at understanding what people do in a given environment, whether this means to ensure the safety of workers on the factory floor, to detect crimes occurring in indoor or outdoor settings, or to monitor the flow of large crowds through public spaces. However, surveillance and monitoring technologies rarely consider that they analyze human behavior, a phenomenon subject to principles and laws rigorous enough to produce stable and predictable patterns corresponding to social, affective, and psychological phenomena. On the other hand, these phenomena are the subject of other computing domains, in particular Social Signal Processing and Affective Computing, that typically neglect scenarios relevant to surveillance and monitoring technologies, especially when it comes to social and affective dimensions of space in human activities. The goal of this paper is to show that the investigation of the overlapping area between surveillance and monitoring on one side, and Social Signal Processing and Affective Computing on the other side can bring significant progress in both domains and open a number of interesting research perspectives.

show abstract

“…Gennari et al [23] proposed an algorithm for tracking groups based on a modified version of the probabilistic data association estimator. Their method tracks people as groups by merging image regions that are similar at the pixel level, taking into account spatial location, cardinality, and velocity.…”

Section: Data Associationmentioning

confidence: 99%

Occlusion-Robust Human Tracking with Integrated Multi-View Depth Imagery

Fukushi

Kumazawa

2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Kenichiro FUKUSHI†a) and Itsuo KUMAZAWA † †b) , Members SUMMARYIn this paper, we present a computer vision-based human tracking system with multiple stereo cameras. Many widely used methods, such as KLT-tracker, update the trackers "frame-to-frame," so that features extracted from one frame are utilized to update their current state. In contrast, we propose a novel optimization technique for the "multi-frame" approach that computes resultant trajectories directly from video sequences, in order to achieve high-level robustness against severe occlusion, which is known to be a challenging problem in computer vision. We developed a heuristic optimization technique to estimate human trajectories, instead of using dynamic programming (DP) or an iterative approach, which makes our method sufficiently computationally efficient to operate in realtime. Six video sequences where one to six people walk in a narrow laboratory space are processed using our system. The results confirm that our system is capable of tracking cluttered scenes in which severe occlusion occurs and people are frequently in close proximity to each other. Moreover, minimal information is required for tracking, instead of full camera images, which is communicated over the network. Hence, commonly used network devices are sufficient for constructing our tracking system. key words: human tracking, multi-view, multi-frame, stereo vision, depth camera, occlusion robust IntroductionComputer vision-based human tracking has received increasing attention recently. Applications include ambient intelligence, human-computer interaction, human behavior analysis and security. Computer vision (CV) allows tracking systems that operate without such sensors as RFID, GPS, or smart phones. However, a problem known as "occlusion" in CV-based tracking exists, which occurs when a person being tracked goes behind other people or objects. Full occlusion disables any cues for tracking, and partial occlusion changes the appearance of the person, causing tracking difficulties.Earlier work has identified several promising strategies. First, multi-view tracking approaches are employed to reduce the blind areas caused by occlusion. Tracking or feature extraction is conducted for each camera, and then the final tracking result is produced by fusing the evidence from all of the views. The problem is how to match regions observed from different viewpoints. Researchers proposed

show abstract

Probabilistic data association methods in visual tracking of groups

Abstract: Abstract

Cited by 42 publications

References 4 publications

Texture-Based Crowd Detection and Localisation

Texture-Based Crowd Detection and Localisation

Socially intelligent surveillance and monitoring: Analysing social dimensions of physical space

Occlusion-Robust Human Tracking with Integrated Multi-View Depth Imagery

Contact Info

Product

Resources

About