Abstract
The categorization of places in indoor environments is an important capability for service robots working and interacting with humans. In this paper we present a method to categorize different areas in indoor environments using a mobile robot equipped with a Kinect camera. Our approach transforms depth and grey scale images taken at each place into histograms of local binary patterns (LBPs) whose dimensionality is further reduced following a uniform criterion. The histograms are then combined into a single feature vector which is categorized using a supervised method. In this work we compare the performance of support vector machines and random forests as supervised classifiers. Finally, we apply our technique to distinguish five different place categories: Corridors, laboratories, offices, kitchens, and study rooms. Experimental results show that we can categorize these places with high accuracy using our approach.
| Original language | English |
|---|---|
| Pages (from-to) | 6695-6711 |
| Number of pages | 17 |
| Journal | Sensors (Switzerland) |
| Volume | 12 |
| Issue number | 5 |
| DOIs | |
| Publication status | Published - May 1 2012 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Analytical Chemistry
- Atomic and Molecular Physics, and Optics
- Biochemistry
- Instrumentation
- Electrical and Electronic Engineering
Cite this
Categorization of indoor places using the Kinect sensor. / Mozos, Oscar Martinez; Mizutani, Hitoshi; Kurazume, Ryo; Hasegawa, Tsutomu.
In: Sensors (Switzerland), Vol. 12, No. 5, 01.05.2012, p. 6695-6711.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Categorization of indoor places using the Kinect sensor
AU - Mozos, Oscar Martinez
AU - Mizutani, Hitoshi
AU - Kurazume, Ryo
AU - Hasegawa, Tsutomu
PY - 2012/5/1
Y1 - 2012/5/1
N2 - The categorization of places in indoor environments is an important capability for service robots working and interacting with humans. In this paper we present a method to categorize different areas in indoor environments using a mobile robot equipped with a Kinect camera. Our approach transforms depth and grey scale images taken at each place into histograms of local binary patterns (LBPs) whose dimensionality is further reduced following a uniform criterion. The histograms are then combined into a single feature vector which is categorized using a supervised method. In this work we compare the performance of support vector machines and random forests as supervised classifiers. Finally, we apply our technique to distinguish five different place categories: Corridors, laboratories, offices, kitchens, and study rooms. Experimental results show that we can categorize these places with high accuracy using our approach.
AB - The categorization of places in indoor environments is an important capability for service robots working and interacting with humans. In this paper we present a method to categorize different areas in indoor environments using a mobile robot equipped with a Kinect camera. Our approach transforms depth and grey scale images taken at each place into histograms of local binary patterns (LBPs) whose dimensionality is further reduced following a uniform criterion. The histograms are then combined into a single feature vector which is categorized using a supervised method. In this work we compare the performance of support vector machines and random forests as supervised classifiers. Finally, we apply our technique to distinguish five different place categories: Corridors, laboratories, offices, kitchens, and study rooms. Experimental results show that we can categorize these places with high accuracy using our approach.
UR - http://www.scopus.com/inward/record.url?scp=84861569601&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84861569601&partnerID=8YFLogxK
U2 - 10.3390/s120506695
DO - 10.3390/s120506695
M3 - Article
VL - 12
SP - 6695
EP - 6711
JO - Sensors
JF - Sensors
SN - 1424-3210
IS - 5
ER -