Detection and Classification of Multiple Objects using an RGB-D Sensor and Linear Spatial Pyramid Matching

Michalis Dimitriou, Tsampikos Kounalakis, Nikolaos Vidakis, Georgios Triantafyllidis

Research output: Contribution to journalJournal articleResearchpeer-review

5 Citations (Scopus)
650 Downloads (Pure)

Abstract

This paper presents a complete system for multiple object detection and classification in a 3D scene using an RGB-D sensor such as the Microsoft Kinect sensor. Successful multiple object detection and classification are crucial features in many 3D computer vision applications. The main goal is making machines see and understand objects like humans do. To this goal, the new RGB-D sensors can be utilized since they provide real-time depth map which can be used along with the RGB images for our tasks. In our system we employ effective depth map
processing techniques, along with edge detection, connected components detection and filtering approaches, in order to design a complete image processing algorithm for efficient object detection of multiple individual
objects in a single scene, even in complex scenes with many objects. Besides, we apply the Linear Spatial Pyramid Matching (LSPM) [1] method proposed by Jianchao Yang et al for the efficient classification of the detected objects. Experimental results are presented for both detection and classification, showing the efficiency of the proposed design.
Original languageEnglish
JournalElectronic Letters on Computer Vision and Image Analysis
Volume12
Issue number2
Pages (from-to)78-87
Number of pages10
ISSN1577-5097
Publication statusPublished - 2013

Fingerprint

Sensors
Edge detection
Computer vision
Image processing
Object detection

Keywords

  • Depth Map
  • Object Detection
  • Microsoft Kinect
  • Image Segmentation
  • Feature Extraction
  • Classification
  • Linear Spatial Pyramid Matching

Cite this

@article{2ca4703ce9fd402aa7bdd8bfde27e61d,
title = "Detection and Classification of Multiple Objects using an RGB-D Sensor and Linear Spatial Pyramid Matching",
abstract = "This paper presents a complete system for multiple object detection and classification in a 3D scene using an RGB-D sensor such as the Microsoft Kinect sensor. Successful multiple object detection and classification are crucial features in many 3D computer vision applications. The main goal is making machines see and understand objects like humans do. To this goal, the new RGB-D sensors can be utilized since they provide real-time depth map which can be used along with the RGB images for our tasks. In our system we employ effective depth mapprocessing techniques, along with edge detection, connected components detection and filtering approaches, in order to design a complete image processing algorithm for efficient object detection of multiple individualobjects in a single scene, even in complex scenes with many objects. Besides, we apply the Linear Spatial Pyramid Matching (LSPM) [1] method proposed by Jianchao Yang et al for the efficient classification of the detected objects. Experimental results are presented for both detection and classification, showing the efficiency of the proposed design.",
keywords = "Depth Map, Object Detection, Microsoft Kinect, Image Segmentation, Feature Extraction, Classification, Linear Spatial Pyramid Matching",
author = "Michalis Dimitriou and Tsampikos Kounalakis and Nikolaos Vidakis and Georgios Triantafyllidis",
year = "2013",
language = "English",
volume = "12",
pages = "78--87",
journal = "Electronic Letters on Computer Vision and Image Analysis",
issn = "1577-5097",
publisher = "Universitat Autonoma de Barcelona Centre de Visio per Computador",
number = "2",

}

Detection and Classification of Multiple Objects using an RGB-D Sensor and Linear Spatial Pyramid Matching. / Dimitriou, Michalis; Kounalakis, Tsampikos; Vidakis, Nikolaos; Triantafyllidis, Georgios.

In: Electronic Letters on Computer Vision and Image Analysis, Vol. 12, No. 2, 2013, p. 78-87.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Detection and Classification of Multiple Objects using an RGB-D Sensor and Linear Spatial Pyramid Matching

AU - Dimitriou, Michalis

AU - Kounalakis, Tsampikos

AU - Vidakis, Nikolaos

AU - Triantafyllidis, Georgios

PY - 2013

Y1 - 2013

N2 - This paper presents a complete system for multiple object detection and classification in a 3D scene using an RGB-D sensor such as the Microsoft Kinect sensor. Successful multiple object detection and classification are crucial features in many 3D computer vision applications. The main goal is making machines see and understand objects like humans do. To this goal, the new RGB-D sensors can be utilized since they provide real-time depth map which can be used along with the RGB images for our tasks. In our system we employ effective depth mapprocessing techniques, along with edge detection, connected components detection and filtering approaches, in order to design a complete image processing algorithm for efficient object detection of multiple individualobjects in a single scene, even in complex scenes with many objects. Besides, we apply the Linear Spatial Pyramid Matching (LSPM) [1] method proposed by Jianchao Yang et al for the efficient classification of the detected objects. Experimental results are presented for both detection and classification, showing the efficiency of the proposed design.

AB - This paper presents a complete system for multiple object detection and classification in a 3D scene using an RGB-D sensor such as the Microsoft Kinect sensor. Successful multiple object detection and classification are crucial features in many 3D computer vision applications. The main goal is making machines see and understand objects like humans do. To this goal, the new RGB-D sensors can be utilized since they provide real-time depth map which can be used along with the RGB images for our tasks. In our system we employ effective depth mapprocessing techniques, along with edge detection, connected components detection and filtering approaches, in order to design a complete image processing algorithm for efficient object detection of multiple individualobjects in a single scene, even in complex scenes with many objects. Besides, we apply the Linear Spatial Pyramid Matching (LSPM) [1] method proposed by Jianchao Yang et al for the efficient classification of the detected objects. Experimental results are presented for both detection and classification, showing the efficiency of the proposed design.

KW - Depth Map

KW - Object Detection

KW - Microsoft Kinect

KW - Image Segmentation

KW - Feature Extraction

KW - Classification

KW - Linear Spatial Pyramid Matching

M3 - Journal article

VL - 12

SP - 78

EP - 87

JO - Electronic Letters on Computer Vision and Image Analysis

JF - Electronic Letters on Computer Vision and Image Analysis

SN - 1577-5097

IS - 2

ER -