Conference paper
Automatic object detection using objectness measure
2013 1st International Conference on Communications, Signal Processing, and their Applications (ICCSPA)
1st International Conference on Communications, Signal Processing, and their Applications (ICCSPA) 2013 (Sharjah, United Arab Emirates, 12/02/2013–14/02/2013)
2013
Abstract
Object detection is an important step towards object recognition. A robust object detection system is one that can detect an object of any class. In this paper, we present a fully automatic approach to object detection based on an objectness measure. The proposed automatic object detection approach quantifies the likelihood for an image window to encompass objects in the image. It can discriminate between multiple objects in a scene, with individual windows capturing each detected object. Most importantly, the proposed approach does not require any manual input. We tested this approach on the challenging PASCAL VOC 07 dataset. Experimental results show that our approach provides a more accurate estimation of the required number of windows for an input image. The proposed technique is computationally efficient and takes less than 4 sec. per image.
Details
- Title
- Automatic object detection using objectness measure
- Authors/Creators
- S.A.A. Shah (Author/Creator) - The University of Western AustraliaM. Bennamoun (Author/Creator) - The University of Western AustraliaF. Boussaid (Author/Creator) - The University of Western AustraliaA.A. El-Sallam (Author/Creator) - The University of Western Australia
- Publication Details
- 2013 1st International Conference on Communications, Signal Processing, and their Applications (ICCSPA)
- Conference
- 1st International Conference on Communications, Signal Processing, and their Applications (ICCSPA) 2013 (Sharjah, United Arab Emirates, 12/02/2013–14/02/2013)
- Identifiers
- 991005545190307891
- Murdoch Affiliation
- Murdoch University
- Language
- English
- Resource Type
- Conference paper
Metrics
43 Record Views