RAGHAVENDER SAHDEV
  • Home
  • About Me
    • Research Interests
    • Teaching Experience
    • Exp. with Languages and Platforms
    • Contact Me
  • Gallery
  • Research
    • On-going Projects
    • Completed Projects
    • Graduate Courses
    • Mini Projects
    • Undergraduate Courses
    • Online Courses Taken
  • Grants & Awards
  • Publications
  • Outreach

Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings

Abstract:

Scene Classification has been addressed with numerous techniques in the computer vision literature. However with the increasing size of datasets in the field, it has become difficult to achieve high accuracy in the context of robotics. We overcome this problem and obtain good results through our approach. In our approach, we propose to address indoor Scene Classification task using a CNN model trained with a reduced pre-processed version of the Places365 dataset and an empirical analysis is done on a real world dataset that we built by capturing image sequences using a GoPro camera. We also report results obtained on a subset of the Places365 dataset using our approach and additionally show a deployment of our approach on a robot operating in a real world environment.

Sample images from our dataset can be seen in the images on this page.
Download paper: click here
​
Publication
"Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings", By Bao Xin Chen, Raghavender Sahdev, Dekan Wu, Xing Zhao, Manos Papagelis, John Tsotsos, In International Conference on Robotics and Automation Workshop (ICRA-W), 2018, Representing a Complex World, Brisbane, Australia, May 21-25, 2018.

*if you use our dataset please cite our work
DATASET DOWNLOADS
Click here to download our DATASET                                                                 
Click here to download the taxonomy of our dataset                                        
Scene Classification Demo Videos
Sample Dataset Images
by Raghavender Sahdev