Indoor Scene recognition for Micro Aerial Vehicles Navigation using Enhanced SIFT-ScSPM Descriptors. (5th July 2019)

• Record Type: Journal Article
• Authors: Anbarasu, B.; Anitha, G.
• Is Part Of: Journal of navigation. Volume 73:Number 1(2020)
• Page Start: 37
• Page End: 55
• Publication Date: 2019-07-05
• Subjects: Micro Aerial Vehicle, -- Indoor navigation, -- Scene recognition, -- Support vector machines; Navigation -- Periodicals; 623.8905
• DOI: 10.1017/S0373463319000420
• Languages: English
• ISSNs: 0373-4633

Abstract

Abstract : In this paper, a new scene recognition visual descriptor called Enhanced Scale Invariant Feature Transform-based Sparse coding Spatial Pyramid Matching (Enhanced SIFT-ScSPM) descriptor is proposed by combining a Bag of Words (BOW)-based visual descriptor (SIFT-ScSPM) and Gist-based descriptors (Enhanced Gist-Enhanced multichannel Gist (Enhanced mGist)). Indoor scene classification is carried out by multi-class linear and non-linear Support Vector Machine (SVM) classifiers. Feature extraction methodology and critical review of several visual descriptors used for indoor scene recognition in terms of experimental perspectives have been discussed in this paper. An empirical study is conducted on the Massachusetts Institute of Technology (MIT) 67 indoor scene classification data set and assessed the classification accuracy of state-of-the-art visual descriptors and the proposed Enhanced mGist, Speeded Up Robust Features-Spatial Pyramid Matching (SURF-SPM) and Enhanced SIFT-ScSPM visual descriptors. Experimental results show that the proposed Enhanced SIFT-ScSPM visual descriptor performs better with higher classification rate, precision, recall and area under the Receiver Operating Characteristic (ROC) curve values with respect to the state-of-the-art and the proposed Enhanced mGist and SURF-SPM visual descriptors.