Publications

MAVNet: An Effective Semantic Segmentation Micro-Network for MAV-Based Tasks

Published in IEEE Robotics and Automation Letters ( Volume: 4 , Issue: 4 , Oct. 2019 ) , 2019

Real-time semantic image segmentation on platforms subject to size, weight, and power constraints is a key area of interest for air surveillance and inspection.

Recommended citation: T. Nguyen et al., "MAVNet: An Effective Semantic Segmentation Micro-Network for MAV-Based Tasks," in IEEE Robotics and Automation Letters, vol. 4, no. 4, pp. 3908-3915, Oct. 2019. doi: 10.1109/LRA.2019.2928734 https://ieeexplore.ieee.org/document/8764006

The Open Vision Computer: An Integrated Sensing and Compute System for Mobile Robots

Published in 2019 International Conference on Robotics and Automation (ICRA), 2019

In this paper we describe the Open Vision Computer (OVC) which was designed to support high speed, vision guided autonomous drone flight.

Recommended citation: M. Quigley et al., "The Open Vision Computer: An Integrated Sensing and Compute System for Mobile Robots," 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, 2019, pp. 1834-1840. doi: 10.1109/ICRA.2019.8794472 https://ieeexplore.ieee.org/abstract/document/8794472

Real Time Dense Depth Estimation by Fusing Stereo with Sparse Depth Measurements

Published in 2019 International Conference on Robotics and Automation (ICRA), 2019

We present an approach to depth estimation that fuses information from a stereo pair with sparse range measurements derived from a LIDAR sensor or a range camera.

Recommended citation: S. S. Shivakumar, K. Mohta, B. Pfrommer, V. Kumar and C. J. Taylor, "Real Time Dense Depth Estimation by Fusing Stereo with Sparse Depth Measurements," 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, 2019, pp. 6482-6488. doi: 10.1109/ICRA.2019.8794023 https://ieeexplore.ieee.org/abstract/document/8794023

Monocular Camera Based Fruit Counting and Mapping with Semantic Data Association

Published in IEEE Robotics and Automation Letters (27 February 2019) , 2019

We present a cheap, lightweight, and fast fruit counting pipeline. Our pipeline relies only on a monocular camera..

Recommended citation: Liu, Xu. (2019). "Monocular Camera Based Fruit Counting and Mapping with Semantic Data Association" Journal 1. 1(3). https://ieeexplore.ieee.org/document/8653965/

Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model

Published in IEEE Robotics and Automation Letters (Volume: 3, Issue: 3, July 2018) , 2018

In this study, we propose an unsupervised learning algorithm that trains a Deep Convolutional Neural Network to estimate planar homographies.

Recommended citation: Ngyuen, Ty. (2018). "Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model" Journal 1. 1(3). https://ieeexplore.ieee.org/document/8302515/

Stereo 3D Tracking of Infants in Natural Play Conditions

Published in 2017 International Conference on Rehabilitation Robotics (ICORR), 2017

This paper describes the design and implementation of a multiple view stereoscopic 3D vision system and a supporting infant tracker pipeline..

Recommended citation: Shivakumar, S.S. (2017). "Stereo 3D Tracking of Infants in Natural Play Conditions." 2017 International Conference on Rehabilitation Robotics. 1(1). https://ieeexplore.ieee.org/document/8009353/

Counting Apples and Oranges with Deep Learning: A Data-Driven Approach

Published in IEEE Robotics and Automation Letters (Volume: 2, Issue: 2, April 2017), 2017

This paper describes a fruit counting pipeline based on deep learning that accurately counts fruit in unstructured environments

Recommended citation: Chen, S.W. (2017). "Counting Apples and Oranges with Deep Learning: A Data-Driven Approach" Journal 1. 1(2). https://ieeexplore.ieee.org/abstract/document/7814145/

Shreyas S. Shivakumar