CaltechAUTHORS
  A Caltech Library Service

Monocular Perception of Biological Motion - Clutter and Partial Occlusion

Song, Yang and Goncalves, Luis and Perona, Pietro (2000) Monocular Perception of Biological Motion - Clutter and Partial Occlusion. In: Computer Vision — ECCV 2000. Lecture Notes in Computer Science. Vol.II. No.1843. Springer , Berlin, Heidelberg, pp. 719-733. ISBN 9783540676867. https://resolver.caltech.edu/CaltechAUTHORS:20190328-145236091

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190328-145236091

Abstract

The problem of detecting and labeling a moving human body viewed monocularly in a cluttered scene is considered. The task is to decide whether or not one or more people are in the scene (detection), to count them, and to label their visible body parts (labeling). It is assumed that a motion-tracking front end is supplied: a number of moving features, some belonging to the body and some to the background are tracked for two frames and their position and velocity is supplied (Johansson display). It is not guaranteed that all the body parts are visible, nor that the only motion present is the one of the body. The algorithm is based on our previous work [12]; we learn a probabilistic model of the position and motion of body features, and calculate maximum-likelihood labels efficiently using dynamic programming on a triangulated approximation of the probabilistic model. We extend those results by allowing an arbitrary number of body parts to be undetected (e.g. because of occlusion) and by allowing an arbitrary number of noise features to be present. We train and test on walking and dancing sequences for a total of approximately 10^4 frames. The algorithm is demonstrated to be accurate and efficient.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1007/3-540-45053-x_46DOIArticle
https://rdcu.be/b32XmPublisherFree ReadCube access
ORCID:
AuthorORCID
Perona, Pietro0000-0002-7583-5809
Additional Information:© Springer-Verlag Berlin Heidelberg 2000. Funded by the NSF Engineering Research Center for Neuromorphic Systems Engineering (CNSE) at Caltech (NSF9402726), and by an NSF National Young Investigator Award to PP (NSF9457618).
Funders:
Funding AgencyGrant Number
Center for Neuromorphic Systems Engineering, CaltechUNSPECIFIED
NSFEEC-9402726
NSFIIS-9457618
Subject Keywords:Body Part; False Alarm Rate; Conditional Independence; Signal Point; Biological Motion
Series Name:Lecture Notes in Computer Science
Issue or Number:1843
Record Number:CaltechAUTHORS:20190328-145236091
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190328-145236091
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94258
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:28 Mar 2019 22:56
Last Modified:08 May 2020 21:21

Repository Staff Only: item control page