Object detection based on particle filter and integration of multiple features

Muhammad Attamimi*, Takayuki Nagai, Djoko Purwanto

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

4 Citations (Scopus)

Abstract

This study proposes a method for object detection using a particle filter combining with the integrated multiple features. There are two problems need to be considered in object detection. First, a single feature based object detection is difficult regarding the types of the objects and the environments (or scenes). For example, object detection based on color information will fail in the dark place. The second problem is the object's pose in the scene that is arbitrary in general. Our proposed method comes to tackle such problems to enable the object detection of various types of objects in the various scenes. We have tested proposed method in various scenes, and the results showed that our method was able to perform object detection in such scenes.

Original languageEnglish
Pages (from-to)214-218
Number of pages5
JournalProcedia Computer Science
Volume144
DOIs
Publication statusPublished - 2018
Event3rd International Neural Network Society Conference on Big Data and Deep Learning, INNS BDDL 2018 - Sanur, Bali, Indonesia
Duration: 17 Apr 201819 Apr 2018

Keywords

  • Object detection
  • features integration
  • multiple features
  • particle filter

Fingerprint

Dive into the research topics of 'Object detection based on particle filter and integration of multiple features'. Together they form a unique fingerprint.

Cite this