Tracking People by Detection Using CNN Features

Dina Chahyati; Mohamad Ivan Fanany; Aniati Murni Arymurthy

doi:10.1016/j.procs.2017.12.143

Tracking People by Detection Using CNN Features

Dina Chahyati
, Mohamad Ivan Fanany
, Aniati Murni Arymurthy

Research output: Contribution to journal › Conference article › peer-review

40 Citations (Scopus)

Abstract

Multiple people tracking is an important task for surveillance. Recently, tracking by detection methods had emerged as immediate effect of deep learning remarkable achievements in object detection. In this paper, we use Faster-RCNN for detection and compare two methods for object association. The first method is simple Euclidean distance and the second is more complicated Siamese neural network. The experiment result show that simple Euclidean distance gives promising result as object association method, but it depends heavily on the robustness of detection process on individual frames.

Original language	English
Pages (from-to)	167-172
Number of pages	6
Journal	Procedia Computer Science
Volume	124
DOIs	https://doi.org/10.1016/j.procs.2017.12.143
Publication status	Published - 2017
Event	4th Information Systems International Conference 2017, ISICO 2017 - Bali, Indonesia Duration: 6 Nov 2017 → 8 Nov 2017

Keywords

Convolutional Neural Network
Faster-RCNN
Multiple Object Tracking
Siamese Neural Network

Access to Document

10.1016/j.procs.2017.12.143

Cite this

@article{16e44a6570e54b69a6a1dde136ca7f11,

title = "Tracking People by Detection Using CNN Features",

abstract = "Multiple people tracking is an important task for surveillance. Recently, tracking by detection methods had emerged as immediate effect of deep learning remarkable achievements in object detection. In this paper, we use Faster-RCNN for detection and compare two methods for object association. The first method is simple Euclidean distance and the second is more complicated Siamese neural network. The experiment result show that simple Euclidean distance gives promising result as object association method, but it depends heavily on the robustness of detection process on individual frames.",

keywords = "Convolutional Neural Network, Faster-RCNN, Multiple Object Tracking, Siamese Neural Network",

author = "Dina Chahyati and Fanany, \{Mohamad Ivan\} and Arymurthy, \{Aniati Murni\}",

note = "Publisher Copyright: {\textcopyright} 2018 The Authors.; 4th Information Systems International Conference 2017, ISICO 2017 ; Conference date: 06-11-2017 Through 08-11-2017",

year = "2017",

doi = "10.1016/j.procs.2017.12.143",

language = "English",

volume = "124",

pages = "167--172",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Tracking People by Detection Using CNN Features

AU - Chahyati, Dina

AU - Fanany, Mohamad Ivan

AU - Arymurthy, Aniati Murni

PY - 2017

Y1 - 2017

N2 - Multiple people tracking is an important task for surveillance. Recently, tracking by detection methods had emerged as immediate effect of deep learning remarkable achievements in object detection. In this paper, we use Faster-RCNN for detection and compare two methods for object association. The first method is simple Euclidean distance and the second is more complicated Siamese neural network. The experiment result show that simple Euclidean distance gives promising result as object association method, but it depends heavily on the robustness of detection process on individual frames.

AB - Multiple people tracking is an important task for surveillance. Recently, tracking by detection methods had emerged as immediate effect of deep learning remarkable achievements in object detection. In this paper, we use Faster-RCNN for detection and compare two methods for object association. The first method is simple Euclidean distance and the second is more complicated Siamese neural network. The experiment result show that simple Euclidean distance gives promising result as object association method, but it depends heavily on the robustness of detection process on individual frames.

KW - Convolutional Neural Network

KW - Faster-RCNN

KW - Multiple Object Tracking

KW - Siamese Neural Network

UR - https://www.scopus.com/pages/publications/85041526773

U2 - 10.1016/j.procs.2017.12.143

DO - 10.1016/j.procs.2017.12.143

M3 - Conference article

AN - SCOPUS:85041526773

SN - 1877-0509

VL - 124

SP - 167

EP - 172

JO - Procedia Computer Science

JF - Procedia Computer Science

T2 - 4th Information Systems International Conference 2017, ISICO 2017

Y2 - 6 November 2017 through 8 November 2017

ER -

Tracking People by Detection Using CNN Features

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this