Automatic Unconstrained Online Configuration of a Master-Slave Camera System

Münch, David; Grosselfinger, Ann-Kristin; Hübner, Wolfgang; Arens, Michael

doi:10.1007/978-3-642-39402-7_1

Cited by 2 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While we use 3D motion capture data in this initial work to prove the applicability of the action recognition method, the next step will be the integration of 3D pose estimation methods such as 26 or 27 to get a closed framework from monocular images to recognized actions. Computational efficiency will enable us to integrate the action recognition framework into a distributed surveillance camera network 28 to provides semantic information -the recognized actions -for existing comprehensive high-level situation analysis.…”

Section: Discussionmentioning

confidence: 99%

Generalized Hough transform based time invariant action recognition with 3D pose information

2014

Self Cite

View full text Add to dashboard Cite

Human action recognition has emerged as an important field in the computer vision community due to its large number of applications such as automatic video surveillance, content based video-search and human robot interaction. In order to cope with the challenges that this large variety of applications present, recent research has focused more on developing classifiers able to detect several actions in more natural and unconstrained video sequences. The invariance discrimination tradeoff in action recognition has been addressed by utilizing a Generalized Hough Transform. As a basis for action representation we transform 3D poses into a robust feature space, referred to as pose descriptors. For each action class a one-dimensional temporal voting space is constructed. Votes are generated from associating pose descriptors with their position in time relative to the end of an action sequence. Training data consists of manually segmented action sequences. In the detection phase valid human 3D poses are assumed as input, e.g. originating from 3D sensors or monocular pose reconstruction methods. The human 3D poses are normalized to gain view-independence and transformed into (i) relative limb-angle space to ensure independence of non-adjacent joints or (ii) geometric features. In (i) an action descriptor consists of the relative angles between limbs and their temporal derivatives. In (ii) the action descriptor consists of different geometric features. In order to circumvent the problem of time-warping we propose to use a codebook of prototypical 3D poses which is generated from sample sequences of 3D motion capture data. This idea is in accordance with the concept of equivalence classes in action space. Results of the codebook method are presented using the Kinect sensor and the CMU Motion Capture Database

show abstract

Section: Discussionmentioning

confidence: 99%