Recognition and Tracking of the Members of a Moving Human Body

Panagiotakis, Costas; Tziritas, Georgios

doi:10.1007/978-3-540-30074-8_10

Cited by 13 publications

(14 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to [15], where several classification methods were tested on mixed conditional random fields for gender classification, we compared several classification approaches, based on eqs. (16), (17), (21), and (22). For the sake of comparison, the key recognition rates for all above experiments are summarized in Table IV.…”

Section: Gait Half-cycle Fusionmentioning

confidence: 99%

Gait Recognition Using HMMs and Dual Discriminative Observations for Sub-Dynamics Analysis

Boulgouris

Huang

2013

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

We propose a new gait recognition method that combines holistic and model-based features. Both types of features are extracted automatically from gait silhouette sequences and their combination takes place by means of a pair of HMMs. In the proposed system, holistic features are initially used for capturing general gait dynamics while, subsequently, model-based features are deployed for capturing more detailed sub-dynamics by refining upon the preceding general dynamics. Furthermore, holistic and model-based features are suitably processed in order to improve the discriminatory capacity of the final system. Experimental results show that the proposed method exhibits performance advantages in comparison to popular existing methods.

show abstract

Section: Gait Half-cycle Fusionmentioning

confidence: 99%

Gait Recognition Using HMMs and Dual Discriminative Observations for Sub-Dynamics Analysis

Boulgouris

Huang

2013

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…In most cases, the head segmentation is correct because the head is the most visible human part and has the simple shape. Here, the head segmentation method based on the head mask in [23] is used. After segmenting the head part and obtaining its height (h), we can estimate the human height (H e ) by using the equation h = 0.13H e .…”

Section: B Part-based Pedestrian Matchingmentioning

confidence: 99%

“…Then, the head segmentation method based on the head mask [23] is used and the head height h is obtained.…”

Section: B Part-based Pedestrian Matchingmentioning

confidence: 99%

Matching of Tracked Pedestrians Across Disjoint Camera Views Using CI-DLBP

Lian

Lai

Suen

et al. 2012

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Abstract-Matching pedestrians across disjoint camera views is a challenging task, since their observations are separated in time and space and their appearances may vary considerably. Recently, some approaches of matching pedestrians have been proposed. However, these approaches either used too complex representations or only considered the color information and discarded the spatial structural information of the pedestrian. In order to describe the spatial structural information in color space, we propose a distance-based local binary pattern (DLBP) descriptor. Besides the spatial structural information, the color itself namely its intensity value is also an important feature in matching pedestrians across disjoint camera views. In order to effectively combine these two kinds of information, we further propose a novel CI − DLBP descriptor, which unifies the color intensity and DLBP by learning the joint distributions (2-D histograms) of the DLBP and color intensity at each channel. In addition, different from the previous approaches in which the pedestrians matching is based on their whole bodies, we develop a part-based pedestrian representation because the color density and spatial structural information between the upper outer garment and the lower garment worn by the pedestrian is usually different. Experimental results on challenging realistic scenarios and VIPeR dataset validate the proposed DLBP operator, the CI − DLBP descriptor, and the part-based pedestrian representation for pedestrian matching across disjoint camera views. Compared with existing methods based on color information, this new CI − DLBP approach performs better.Index Terms-CI − DLBP descriptor, disjoint camera views, distance-based local binary pattern (DLBP) operator, part-based pedestrian representation, pedestrian matching.

show abstract

“…Concerning the 2-D approaches, Wang et al [19] propose a method to recognize and track a walker using 2D human model and both static and dynamic cues of body biometrics. Moreover, many systems use Shape-From-Silhouette methods to detect and track the human in 2D [12] or 3D space [20]. The silhouettes are easy to extract providing valuable information about the position and shape of the person.…”

Section: Related Workmentioning

confidence: 99%

“…In previous work, a novel architecture utterly based on the Transferable Belief Model [5], an interpretation of Shafer's theory of evidence [6,7], was proposed [8][9][10][11] for human action and activity recognition in athletic sports videos. As for the proposed paper, the goal is to recognize high level actions and activities based on low level shape-motion understandable features [11][12][13]. The database used for testing is made of real videos acquired by a moving camera under varying view angles and can concern indoor or outdoor meetings.…”

Section: Introductionmentioning

confidence: 99%

Shape-Based Individual/Group Detection for Sport Videos Categorization

Panagiotakis

Ramasso

Tziritas

et al. 2008

Int. J. Patt. Recogn. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

We present a shape based method for automatic people detection and counting without any assumption or knowledge of camera motion. The proposed method is applied to athletic videos in order to classify them to videos of individual and team sports. Moreover, in the case of team (multi-agent) sport, we propose a shape deformations based method for running/hurdling discrimination (activity recognition). Robust, adaptive and independent from the camera motion, the proposed features are combined within the Transferable Belief Model (TBM) framework providing a two level (frames and shot) video categorization. The TBM allows to take into account imprecision, uncertainty and conflict inherent to the features into the fusion process. We have tested the proposed scheme into a big variety of athletic videos like pole vault, high jump, triple jump, hurdling, running, etc. The experimental results of 97% individual/team sport categorization accuracy, using a dataset of 252 real videos of athletic meetings acquired by moving cameras under varying view angles, indicate the stability and the good performance of the proposed scheme.

show abstract

Recognition and Tracking of the Members of a Moving Human Body

Cited by 13 publications

References 8 publications

Gait Recognition Using HMMs and Dual Discriminative Observations for Sub-Dynamics Analysis

Gait Recognition Using HMMs and Dual Discriminative Observations for Sub-Dynamics Analysis

Matching of Tracked Pedestrians Across Disjoint Camera Views Using CI-DLBP

Shape-Based Individual/Group Detection for Sport Videos Categorization

Contact Info

Product

Resources

About