Tracking People by Detection Using CNN Features

Research output: Contribution to journalConference articlepeer-review

17 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 languageEnglish
Pages (from-to)167-172
Number of pages6
JournalProcedia Computer Science
Volume124
DOIs
Publication statusPublished - 1 Jan 2017
Event4th Information Systems International Conference 2017, ISICO 2017 - Bali, Indonesia
Duration: 6 Nov 20178 Nov 2017

Keywords

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

Fingerprint

Dive into the research topics of 'Tracking People by Detection Using CNN Features'. Together they form a unique fingerprint.

Cite this