Visual hull reconstruction for automated primate behavior observation

Nastaran Ghadar, Xikang Zhang, Kang Li, Deniz Erdogmus, Guillaume Thibault, Alireza Bayestehtashk, Izhak Shafran Kris Coleman, Kathleen (Kathy) Grant

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

The study of social animal interactions is used as means for understanding animal behavior and biology. In this work, we describe a computerized method that utilizes 3D visual hull reconstruction to identify and localize rhesus macaques in their social groups. There are three major steps in this study. First, we collect experimental data from four synchronized cameras at different locations and angels in a cage containing five rhesus macaques. Second, by using computer vision algorithms, we detect and identify animals using 2D observations that were provided from the previous step. This provides essential quantitative data for animal behavior research. Finally, by applying visual hull reconstruction algorithm, we automatically build a 3D model for each rhesus macaques on every frame. The results of this work can be used for tracking these animals in their cage, and furthermore it can be used for activity recognition of social interactions of rhesus macaques. The method we developed in this paper, shows promising results that are accurate, yet runs in a timely manner; this makes this algorithm suitable for large datasets and we can use it for future high-level recognition tasks.

Original languageEnglish (US)
Title of host publicationIEEE International Workshop on Machine Learning for Signal Processing, MLSP
DOIs
StatePublished - 2013
Event2013 16th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2013 - Southampton, United Kingdom
Duration: Sep 22 2013Sep 25 2013

Other

Other2013 16th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2013
CountryUnited Kingdom
CitySouthampton
Period9/22/139/25/13

Fingerprint

Animals
Computer vision
Cameras
Primates

Keywords

  • background substraction
  • object detection
  • social animals
  • Visual hull reconstruction

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing

Cite this

Ghadar, N., Zhang, X., Li, K., Erdogmus, D., Thibault, G., Bayestehtashk, A., ... Grant, K. K. (2013). Visual hull reconstruction for automated primate behavior observation. In IEEE International Workshop on Machine Learning for Signal Processing, MLSP [6661922] https://doi.org/10.1109/MLSP.2013.6661922

Visual hull reconstruction for automated primate behavior observation. / Ghadar, Nastaran; Zhang, Xikang; Li, Kang; Erdogmus, Deniz; Thibault, Guillaume; Bayestehtashk, Alireza; Coleman, Izhak Shafran Kris; Grant, Kathleen (Kathy).

IEEE International Workshop on Machine Learning for Signal Processing, MLSP. 2013. 6661922.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ghadar, N, Zhang, X, Li, K, Erdogmus, D, Thibault, G, Bayestehtashk, A, Coleman, ISK & Grant, KK 2013, Visual hull reconstruction for automated primate behavior observation. in IEEE International Workshop on Machine Learning for Signal Processing, MLSP., 6661922, 2013 16th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2013, Southampton, United Kingdom, 9/22/13. https://doi.org/10.1109/MLSP.2013.6661922
Ghadar N, Zhang X, Li K, Erdogmus D, Thibault G, Bayestehtashk A et al. Visual hull reconstruction for automated primate behavior observation. In IEEE International Workshop on Machine Learning for Signal Processing, MLSP. 2013. 6661922 https://doi.org/10.1109/MLSP.2013.6661922
Ghadar, Nastaran ; Zhang, Xikang ; Li, Kang ; Erdogmus, Deniz ; Thibault, Guillaume ; Bayestehtashk, Alireza ; Coleman, Izhak Shafran Kris ; Grant, Kathleen (Kathy). / Visual hull reconstruction for automated primate behavior observation. IEEE International Workshop on Machine Learning for Signal Processing, MLSP. 2013.
@inproceedings{46a2b6042a974aea8eaaa9ab4711e948,
title = "Visual hull reconstruction for automated primate behavior observation",
abstract = "The study of social animal interactions is used as means for understanding animal behavior and biology. In this work, we describe a computerized method that utilizes 3D visual hull reconstruction to identify and localize rhesus macaques in their social groups. There are three major steps in this study. First, we collect experimental data from four synchronized cameras at different locations and angels in a cage containing five rhesus macaques. Second, by using computer vision algorithms, we detect and identify animals using 2D observations that were provided from the previous step. This provides essential quantitative data for animal behavior research. Finally, by applying visual hull reconstruction algorithm, we automatically build a 3D model for each rhesus macaques on every frame. The results of this work can be used for tracking these animals in their cage, and furthermore it can be used for activity recognition of social interactions of rhesus macaques. The method we developed in this paper, shows promising results that are accurate, yet runs in a timely manner; this makes this algorithm suitable for large datasets and we can use it for future high-level recognition tasks.",
keywords = "background substraction, object detection, social animals, Visual hull reconstruction",
author = "Nastaran Ghadar and Xikang Zhang and Kang Li and Deniz Erdogmus and Guillaume Thibault and Alireza Bayestehtashk and Coleman, {Izhak Shafran Kris} and Grant, {Kathleen (Kathy)}",
year = "2013",
doi = "10.1109/MLSP.2013.6661922",
language = "English (US)",
isbn = "9781479911806",
booktitle = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

}

TY - GEN

T1 - Visual hull reconstruction for automated primate behavior observation

AU - Ghadar, Nastaran

AU - Zhang, Xikang

AU - Li, Kang

AU - Erdogmus, Deniz

AU - Thibault, Guillaume

AU - Bayestehtashk, Alireza

AU - Coleman, Izhak Shafran Kris

AU - Grant, Kathleen (Kathy)

PY - 2013

Y1 - 2013

N2 - The study of social animal interactions is used as means for understanding animal behavior and biology. In this work, we describe a computerized method that utilizes 3D visual hull reconstruction to identify and localize rhesus macaques in their social groups. There are three major steps in this study. First, we collect experimental data from four synchronized cameras at different locations and angels in a cage containing five rhesus macaques. Second, by using computer vision algorithms, we detect and identify animals using 2D observations that were provided from the previous step. This provides essential quantitative data for animal behavior research. Finally, by applying visual hull reconstruction algorithm, we automatically build a 3D model for each rhesus macaques on every frame. The results of this work can be used for tracking these animals in their cage, and furthermore it can be used for activity recognition of social interactions of rhesus macaques. The method we developed in this paper, shows promising results that are accurate, yet runs in a timely manner; this makes this algorithm suitable for large datasets and we can use it for future high-level recognition tasks.

AB - The study of social animal interactions is used as means for understanding animal behavior and biology. In this work, we describe a computerized method that utilizes 3D visual hull reconstruction to identify and localize rhesus macaques in their social groups. There are three major steps in this study. First, we collect experimental data from four synchronized cameras at different locations and angels in a cage containing five rhesus macaques. Second, by using computer vision algorithms, we detect and identify animals using 2D observations that were provided from the previous step. This provides essential quantitative data for animal behavior research. Finally, by applying visual hull reconstruction algorithm, we automatically build a 3D model for each rhesus macaques on every frame. The results of this work can be used for tracking these animals in their cage, and furthermore it can be used for activity recognition of social interactions of rhesus macaques. The method we developed in this paper, shows promising results that are accurate, yet runs in a timely manner; this makes this algorithm suitable for large datasets and we can use it for future high-level recognition tasks.

KW - background substraction

KW - object detection

KW - social animals

KW - Visual hull reconstruction

UR - http://www.scopus.com/inward/record.url?scp=84893322357&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893322357&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2013.6661922

DO - 10.1109/MLSP.2013.6661922

M3 - Conference contribution

SN - 9781479911806

BT - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

ER -