Efficient Upper Body Pose Estimation from a Single Image or a Sequence

Siddiqui, Matheen; Medioni, Gérard

doi:10.1007/978-3-540-75703-0_6

Cited by 6 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other approaches detect the pose of a person by iteratively assembling a person from low-level features, from part detections, or from locally optimal candidate configurations (Fleck et al 1996;Micilotta et al 2005;Siddiqui and Medioni 2007); or by learning a direct mapping from the image to the 3D pose (Agarwal and Triggs 2006).…”

Section: Related Work and Motivationmentioning

confidence: 99%

Upper Body Detection and Tracking in Extended Signing Sequences

et al. 2011

View full text Add to dashboard Cite

The goal of this work is to detect and track the articulated pose of a human in signing videos of more than one hour in length. In particular we wish to accurately localise hands and arms, despite fast motion and a cluttered and changing background.We cast the problem as inference in a generative model of the image, and propose a complete model which accounts for self-occlusion of the arms. Under this model, limb detection is expensive due to the very large number of possible configurations each part can assume. We make the following contributions to reduce this cost: (i) efficient sampling from a pictorial structure proposal distribution to obtain reasonable configurations; (ii) identifying a large number of frames where configurations can be correctly inferred, and exploiting temporal tracking elsewhere.Results are reported for signing footage with challenging image conditions and for different signers. We show that the method is able to identify the true arm and hand locations with high reliability. The results exceed the state-ofthe-art for the length and stability of continuous limb tracking.

show abstract

Section: Related Work and Motivationmentioning

confidence: 99%

Upper Body Detection and Tracking in Extended Signing Sequences

et al. 2011

View full text Add to dashboard Cite

show abstract

“…Of concern in this approach is the construction of candidate poses robustly and at interactive rates. Our system makes use of a search strategy, detailed in [49], that can find locally optimal candidates efficiently and exhaustively. Continuity of motion as well as inspection of regions of significant changed are used to achieve high frame rates.…”

Section: Upper-body Estimationmentioning

confidence: 99%

Vision-based short range interaction between a personal service robot and a user

Siddiqui

Liao

Medioni

2009

Intel Serv Robotics

Self Cite

View full text Add to dashboard Cite

Interaction between a personal service robot and a human user is contingent on being aware of the posture and facial expression of users in the home environment. In this work, we propose algorithms to robustly and efficiently track the head, facial gestures, and the upper body movements of a user. The face processing module consists of 3D head pose estimation, modeling nonrigid facial deformations, and expression recognition. Thus, it can detect and track the face, and classify expressions under various poses, which is the key for human-robot interaction. For body pose tracking, we develop an efficient algorithm based on bottom-up techniques to search in a tree-structured 2D articulated body model, and identify multiple pose candidates to represent the state of current body configuration. We validate these face and body modules in varying experiments with different datasets, and the experimental results are reported. The implementation of both modules can run in real-time, which meets the requirement for real-world human-robot interaction task. These two modules have been ported onto a real robot platform by the Electronics and Telecommunications Research Institute.

show abstract

“…In [11] articulated poses are estimated directly using a large database of exemplars and an appropriate hashing function. Other relevant approaches model a human as a collection of separate but elastically connected limb sections, each associated with its own detector [2][12] [13] [14]. In [2] this collection of limbs is arranged in a tree structure.…”

Section: Related Workmentioning

confidence: 99%