page last updated (June 2018):
Conference Paper Publications

Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings, By Bao Xin Chen, Raghavender Sahdev, Dekun Wu, Xing Zhao, Manos Papagelis and John K. Tsotsos, In the International Conference on Robotics and Automation (ICRA) Workshop 2018: Representing a Complex World, Brisbane, Australia, May 21-25, 2018.
Click here for project page
Download paper: click here
Click here for project page
Download paper: click here

Indoor Localization in Dynamic Human Environments using Visual Odometry and Global Pose Refinement, By Raghavender Sahdev, Bao Xin Chen and John K. Tsotsos, In the 15th Conference on Computer and Robot Vision Systems (CRV 2018), Toronto, China , May 9-11, 2018.
* Download Paper: click here
* Project page: click here
* Download Paper: click here
* Project page: click here
Integrating Stereo Vision with a CNN Tracker for a Person-Following Robot, By Bao Xin Chen*, Raghavender Sahdev* and John K. Tsotsos, In the 11th International Conference on Computer Vision Systems (ICVS 2017), Shengen, China , July 10-13, 2017 (Oral Presentation).
* denotes equal contribution * Download Paper: click here * Project page click here * Finalist for the Best Conference Paper Award at ICVS 2017. |
|
Person Following Robot Using Selected Online Ada-Boosting with a Stereo Camera, By Bao Xin Chen*, Raghavender Sahdev* and John K. Tsotsos, In the 14th Conference on Computer and Robot Vision, Edmonton, Ablerta, May 16-19, 2017. (Oral Presentation)
Project Page: click here Download paper: click here Presentation slides: click here Poster link: click here * denotes equal contribution *Best Robotics Paper Award at the 14th Conference on Computer and Robot Vision, Edmonton, May 17-19, 2017. |
|
Indoor Place Recognition System for Localization of Mobile Robots, By Raghavender Sahdev and John K. Tsotsos, In the 13th Conference on Computer and Robot Vision, Victoria, British Columbia, June 1-3, 2016. (Oral presentation)
Paper pdf Project Page: click here |
Poster Publications

TimeLapseReg - An ImageJ plugin for drift correction of video sequence in time-lapse microscopy, poster presented at the 2015 ImageJ Users and Developers Conference at the University of Wisconsin-Madison, USA on September 3-4, 2015 by Raghavender Sahdev (1), Tomasz Konopczynski (2), Dimiter Prodanov(3,4) and Daniel Sage(5)
Project page - click here
poster download - click here
slides download - click here
presentation video link - click here
Poster Abstract: The main functionality of the Turboreg plugin allows for aligning or matching two images. The plugin is widely used in Neuroscience for pre-processing of both static and time-lapse imaging data. In this project we develop an ImageJ's plugin to be used by an end-user to correct for the drift in very long sequences of noisy multi-channel fluorescence images. TimeLapseReg uses the well-known TurboReg/StackReg engine method to register frames to a reference image. It computes and applies rigid transformations of the user-selected channel and stores them for subsequent use. The geometrical transformations are further applied to all channels. We present the user with a drift trajectory over the entire image sequence. The user has the option of choosing the reference image and discarding corrupted images. We have applied our software to calcium imaging data for helping neuro-scientists to better infer neuronal network spiking activity
- BITS Pilani Hyderabad Campus, India
- University of Heidelberg, Germany
- INCF Belgian Node
- EHS/NERF, Imec Leuven, Belgium
- Biomedical Imaging Group, Ecole Polytechnique Federale de Lausanne, Switzerland
Project page - click here
poster download - click here
slides download - click here
presentation video link - click here
Poster Abstract: The main functionality of the Turboreg plugin allows for aligning or matching two images. The plugin is widely used in Neuroscience for pre-processing of both static and time-lapse imaging data. In this project we develop an ImageJ's plugin to be used by an end-user to correct for the drift in very long sequences of noisy multi-channel fluorescence images. TimeLapseReg uses the well-known TurboReg/StackReg engine method to register frames to a reference image. It computes and applies rigid transformations of the user-selected channel and stores them for subsequent use. The geometrical transformations are further applied to all channels. We present the user with a drift trajectory over the entire image sequence. The user has the option of choosing the reference image and discarding corrupted images. We have applied our software to calcium imaging data for helping neuro-scientists to better infer neuronal network spiking activity
|
Poster Abstract: This poster focuses on development of a Place Recognition and Categorization system for localization of mobile Robots. The Robot learns the places from experience and then recognizes previously observed topological places in known environments and categorizes previously unseen places in new environments. This system has been practically tested with a novel dataset built by us to validate the theoretical results of the proposed system. A HOUP (Histogram of Oriented Uniform Patterns) descriptor has been developed which is used to represent an image and then appropriate classifiers have been used to perform the classification tasks. It is shown in the work that our developed system not only performs well on the existing datasets but also performs remarkably well on the dataset developed by us. The proposed system has been tested with the 2 robots Virtual Me and Pioneer under different illumination conditions
Masters Thesis
Autonomous Robots in Dynamic Indoor Environments: Localization and Person Following. Raghavender Sahdev. Masters Thesis, York University, Canada, March 2018.
Abstract: Autonomous social robots have many tasks that they need to address such as localization, mapping, navigation, person following, place recognition, etc. In this thesis we focus on two key components required for the navigation of autonomous robots namely, person following behaviour and localization in dynamic human environments. We propose three novel approaches to address these components; two approaches for person following and one for indoor localization. A convolutional neural networks based approach and an Ada-boost based approach are developed for person following. We demonstrate the results by showing the tracking accuracy over time for this behaviour. For the localization task, we propose a novel approach which can act as a wrapper for traditional visual odometry based approaches to improve the localization accuracy in dynamic human environments. We evaluate this approach by showing how the performance varies with increasing number of dynamic agents present in the scene. This thesis provides qualitative and quantitative evaluations for each of the approaches proposed and show that we perform better than the current approaches.
*nominated for Best Masters thesis award
Abstract: Autonomous social robots have many tasks that they need to address such as localization, mapping, navigation, person following, place recognition, etc. In this thesis we focus on two key components required for the navigation of autonomous robots namely, person following behaviour and localization in dynamic human environments. We propose three novel approaches to address these components; two approaches for person following and one for indoor localization. A convolutional neural networks based approach and an Ada-boost based approach are developed for person following. We demonstrate the results by showing the tracking accuracy over time for this behaviour. For the localization task, we propose a novel approach which can act as a wrapper for traditional visual odometry based approaches to improve the localization accuracy in dynamic human environments. We evaluate this approach by showing how the performance varies with increasing number of dynamic agents present in the scene. This thesis provides qualitative and quantitative evaluations for each of the approaches proposed and show that we perform better than the current approaches.
*nominated for Best Masters thesis award
Talks/Demos at conferences
1. I gave a lighting talk presentation at ROSCon 2017 in Vancouver, BC, Canada on September 23, 2017. Click here for video available online (25:20 onwards)
2. I gave an oral presentation on a Person Following robot for my paper at the 14th International Conference on Computer and Robot Vision 2017 at Edmonton, Alberta, May 17-19, 2017.
3. I was the graduate student representing the Department of Electrical Engineering and Computer Science, York University at the the Summer Undergraduate Research Conference on August 11, 2016. I gave a talk about my research. The slides from the talk can be downloaded from here
link to the conference:
4. I gave a presentation about my research work on Place Recognition at the Space Vision and Advanced Robotics Workshop to space researchers/scientists at MDA, Toronto on June 16, 2016
5. I gave an oral presentation on Place Recognition for my paper at 13th International Conference on Computer and Robot Vision 2016 at Victoria, BC, June1-3, 2016.
6. I gave the demo on "Time Lapse Reg - An ImageJ plugin for drift correction of video sequence in time-lapse microscopy", at the Society for Neuroscience 2015 in Chicago at the INCF (International Neuroinformatics Coordinating Facility) Booth #2114 as an Exhibitor on October 20, 2015 - https://incf.org/documents/sfn_2015_demo_schedule
7. I was the Lightning talk presenter on "TimeLapseReg: An Image J plugin for drift correction of video sequences in timelapse microscopy" at the ImageJ Users and Developers Conference 2015 at the University of Wisconsin-Madison on September 3-4, 2015. video link here
2. I gave an oral presentation on a Person Following robot for my paper at the 14th International Conference on Computer and Robot Vision 2017 at Edmonton, Alberta, May 17-19, 2017.
3. I was the graduate student representing the Department of Electrical Engineering and Computer Science, York University at the the Summer Undergraduate Research Conference on August 11, 2016. I gave a talk about my research. The slides from the talk can be downloaded from here
link to the conference:
4. I gave a presentation about my research work on Place Recognition at the Space Vision and Advanced Robotics Workshop to space researchers/scientists at MDA, Toronto on June 16, 2016
5. I gave an oral presentation on Place Recognition for my paper at 13th International Conference on Computer and Robot Vision 2016 at Victoria, BC, June1-3, 2016.
6. I gave the demo on "Time Lapse Reg - An ImageJ plugin for drift correction of video sequence in time-lapse microscopy", at the Society for Neuroscience 2015 in Chicago at the INCF (International Neuroinformatics Coordinating Facility) Booth #2114 as an Exhibitor on October 20, 2015 - https://incf.org/documents/sfn_2015_demo_schedule
7. I was the Lightning talk presenter on "TimeLapseReg: An Image J plugin for drift correction of video sequences in timelapse microscopy" at the ImageJ Users and Developers Conference 2015 at the University of Wisconsin-Madison on September 3-4, 2015. video link here
8. Gave a short presentation on "Place Recognition System for Localization of Mobile Robots" at the Birds of a Feather Session at the NCFRN Field Trials on June 13, 2015.
pdf slides
9. Gave a short presentation on "Concurrent and Social Learning Algorithms in Robot Teams" at the Birds of a Feather Session at the NCFRN Field Trials on June 13, 2015.
pdf slides
pdf slides
9. Gave a short presentation on "Concurrent and Social Learning Algorithms in Robot Teams" at the Birds of a Feather Session at the NCFRN Field Trials on June 13, 2015.
pdf slides
Bachelor's Thesis
Place Recognition System for Localization of Mobile Robots
Supervisors
Dr. John K. Tsotsos, Professor at Center for Vision Research, York University, Canada
Dr. Aruna Malapati Assistant Professor BITS Pilani, Hyderabad Campus, India
bachelor's thesis pdf
* contact me to know more about the thesis
Supervisors
Dr. John K. Tsotsos, Professor at Center for Vision Research, York University, Canada
Dr. Aruna Malapati Assistant Professor BITS Pilani, Hyderabad Campus, India
bachelor's thesis pdf
* contact me to know more about the thesis