A Detailed Analysis of a New 3D Spatial Feature Vector for Indoor Scene Classification

Swadzba A, Wachsmuth S (2014)
Robotics and Autonomous Systems 62(5): 646-662.

Download
OA
Zeitschriftenaufsatz | Veröffentlicht | Englisch
Abstract / Bemerkung
Enhancing perception of the local environment with semantic information like the room type is an important ability for agents acting in their environment. Such high-level knowledge can reduce the effort needed for, for example, object detection. This paper shows how to extract the room label from a small amount of room percepts taken from a certain view point (like the door frame when entering the room). Such functionality is similar to the human ability to get a scene impression from a quick glance. We propose a new three-dimensional (3D) spatial feature vector that captures the layout of a scene from extracted planar surfaces. The trained models emulate the human brain sensitivity to the 3D geometry of a room. Further, we show that our descriptor complements the information encoded by the Gist feature vector — a first attempt to model the mentioned brain area. The global scene properties are extracted from edge information in 2D depictions of the scene. Both features can be fused, resulting in a system that follows our goal to combine psychological insights on human scene perception with physical properties of environments. This paper provides detailed insights into the nature of our spatial descriptor.
Erscheinungsjahr
Zeitschriftentitel
Robotics and Autonomous Systems
Band
62
Zeitschriftennummer
5
Seite
646-662
ISSN
PUB-ID

Zitieren

Swadzba A, Wachsmuth S. A Detailed Analysis of a New 3D Spatial Feature Vector for Indoor Scene Classification. Robotics and Autonomous Systems. 2014;62(5):646-662.
Swadzba, A., & Wachsmuth, S. (2014). A Detailed Analysis of a New 3D Spatial Feature Vector for Indoor Scene Classification. Robotics and Autonomous Systems, 62(5), 646-662. doi:10.1016/j.robot.2012.10.006
Swadzba, A., and Wachsmuth, S. (2014). A Detailed Analysis of a New 3D Spatial Feature Vector for Indoor Scene Classification. Robotics and Autonomous Systems 62, 646-662.
Swadzba, A., & Wachsmuth, S., 2014. A Detailed Analysis of a New 3D Spatial Feature Vector for Indoor Scene Classification. Robotics and Autonomous Systems, 62(5), p 646-662.
A. Swadzba and S. Wachsmuth, “A Detailed Analysis of a New 3D Spatial Feature Vector for Indoor Scene Classification”, Robotics and Autonomous Systems, vol. 62, 2014, pp. 646-662.
Swadzba, A., Wachsmuth, S.: A Detailed Analysis of a New 3D Spatial Feature Vector for Indoor Scene Classification. Robotics and Autonomous Systems. 62, 646-662 (2014).
Swadzba, Agnes, and Wachsmuth, Sven. “A Detailed Analysis of a New 3D Spatial Feature Vector for Indoor Scene Classification”. Robotics and Autonomous Systems 62.5 (2014): 646-662.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2017-01-31T22:23:27Z