Presentation | 2008-11-27 A Novel Evidence Accumulation Framework for Robust Multi-Camera Person Detection and Tracking Akio Kosaka, Hidekazu Iwaki, Takashi Miyoshi, Gaurav Srivastava, Johnny Park, Avinash Kak, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose a novel evidence accumulation framework that accurately estimates the positions of humans in a 3D environment using camera networks. The framework consists of a network of distributed agents having different functionalities. The modular structure of the network allows scalability to large surveillance areas and robust operation. The framework does not assume reliable measurements in single cameras (referred to as 'sensing agents' in our framework) or reliable communication between different agents. There is a position uncertainty associated with single camera measurements and it is reduced through an uncertainty reducing transform that performs evidence accumulation using multiple camera measurements. Our framework has the advantage that single camera measurements do not need to be temporally synchronized to perform evidence accumulation. The system has been tested for detecting single or multiple humans in the environment. We conducted experiments to evaluate the localization accuracy of the position estimates obtained from the system by comparing them with the ground truth. We also developed a system capable of tracking and interacting with humans in motion to support human activities. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | camera networks / distributed processing / evidence accumulation / uncertainty reduction |
Paper # | PRMU2008-128,MVE2008-77 |
Date of Issue |
Conference Information | |
Committee | MVE |
---|---|
Conference Date | 2008/11/20(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Media Experience and Virtual Environment (MVE) |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Novel Evidence Accumulation Framework for Robust Multi-Camera Person Detection and Tracking |
Sub Title (in English) | |
Keyword(1) | camera networks |
Keyword(2) | distributed processing |
Keyword(3) | evidence accumulation |
Keyword(4) | uncertainty reduction |
1st Author's Name | Akio Kosaka |
1st Author's Affiliation | Future Creation Laboratory, Olympus Corporation:Robot Vision Laboratory, Purdue University() |
2nd Author's Name | Hidekazu Iwaki |
2nd Author's Affiliation | Future Creation Laboratory, Olympus Corporation |
3rd Author's Name | Takashi Miyoshi |
3rd Author's Affiliation | Future Creation Laboratory, Olympus Corporation |
4th Author's Name | Gaurav Srivastava |
4th Author's Affiliation | Robot Vision Laboratory, Purdue University |
5th Author's Name | Johnny Park |
5th Author's Affiliation | Robot Vision Laboratory, Purdue University |
6th Author's Name | Avinash Kak |
6th Author's Affiliation | Robot Vision Laboratory, Purdue University |
Date | 2008-11-27 |
Paper # | PRMU2008-128,MVE2008-77 |
Volume (vol) | vol.108 |
Number (no) | 328 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |