1 code implementation • 21 Mar 2024 • Bowen Jiang, Zhijun Zhuang, Shreyas S. Shivakumar, Dan Roth, Camillo J. Taylor
This work explores the zero-shot capabilities of foundation models in Visual Question Answering (VQA) tasks.
no code implementations • 14 Apr 2023 • ZiYun Wang, Fernando Cladera Ojeda, Anthony Bisulco, Daewon Lee, Camillo J. Taylor, Kostas Daniilidis, M. Ani Hsieh, Daniel D. Lee, Volkan Isler
Event-based sensors have recently drawn increasing interest in robotic perception due to their lower latency, higher dynamic range, and lower bandwidth requirements compared to standard CMOS-based imagers.
1 code implementation • 13 Mar 2023 • Bowen Jiang, Camillo J. Taylor
This paper presents a finding that leveraging the hierarchical structures among labels for relationships and objects can substantially improve the performance of scene graph generation systems.
2 code implementations • 14 Sep 2021 • Xu Liu, Guilherme V. Nardari, Fernando Cladera Ojeda, Yuezhan Tao, Alex Zhou, Thomas Donnelly, Chao Qu, Steven W. Chen, Roseli A. F. Romero, Camillo J. Taylor, Vijay Kumar
Semantic maps represent the environment using a set of semantically meaningful objects.
no code implementations • ICCV 2021 • Chao Qu, Wenxin Liu, Camillo J. Taylor
By adopting a Bayesian treatment, our Bayesian Deep Basis Fitting (BDBF) approach is able to 1) predict high-quality uncertainty estimates and 2) enable depth completion with few or no sparse measurements.
no code implementations • 22 Sep 2020 • Ty Nguyen, Ian D. Miller, Avi Cohen, Dinesh Thakur, Shashank Prasad, Camillo J. Taylor, Pratik Chaudrahi, Vijay Kumar
Scalable training data generation is a critical problem in deep learning.
no code implementations • 21 Dec 2019 • Chao Qu, Ty Nguyen, Camillo J. Taylor
In this paper we consider the task of image-guided depth completion where our system must infer the depth at every pixel of an input image based on the image content and a sparse set of depth measurements.
1 code implementation • 20 Sep 2019 • Shreyas S. Shivakumar, Neil Rodrigues, Alex Zhou, Ian D. Miller, Vijay Kumar, Camillo J. Taylor
In this work we propose long wave infrared (LWIR) imagery as a viable supporting modality for semantic segmentation using learning-based techniques.
Ranked #13 on Thermal Image Segmentation on PST900
1 code implementation • 3 Apr 2019 • Ty Nguyen, Shreyas S. Shivakumar, Ian D. Miller, James Keller, Elijah S. Lee, Alex Zhou, Tolga Ozaslan, Giuseppe Loianno, Joseph H. Harwood, Jennifer Wozencraft, Camillo J. Taylor, Vijay Kumar
Real-time semantic image segmentation on platforms subject to size, weight and power (SWaP) constraints is a key area of interest for air surveillance and inspection.
no code implementations • 15 Mar 2019 • Yilun Zhang, Ty Nguyen, Ian D. Miller, Shreyas S. Shivakumar, Steven Chen, Camillo J. Taylor, Vijay Kumar
Depth estimation is an important capability for autonomous vehicles to understand and reconstruct 3D environments as well as avoid obstacles during the execution.
1 code implementation • 2 Feb 2019 • Shreyas S. Shivakumar, Ty Nguyen, Ian D. Miller, Steven W. Chen, Vijay Kumar, Camillo J. Taylor
In this paper we propose a convolutional neural network that is designed to upsample a series of sparse range measurements based on the contextual cues gleaned from a high resolution intensity image.
no code implementations • 19 Nov 2018 • Armon Shariati, Bernd Pfrommer, Camillo J. Taylor
This paper describes an approach to automatically extracting floor plans from the kinds of incomplete measurements that could be acquired by an autonomous mobile robot.
no code implementations • 4 Nov 2018 • Xu Liu, Steven W. Chen, Chenhao Liu, Shreyas S. Shivakumar, Jnaneshwar Das, Camillo J. Taylor, James Underwood, Vijay Kumar
We present a cheap, lightweight, and fast fruit counting pipeline that uses a single monocular camera.
Robotics
1 code implementation • 20 Sep 2018 • Shreyas S. Shivakumar, Kartik Mohta, Bernd Pfrommer, Vijay Kumar, Camillo J. Taylor
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.
no code implementations • 18 Sep 2018 • Ty Nguyen, Tolga Ozaslan, Ian D. Miller, James Keller, Giuseppe Loianno, Camillo J. Taylor, Daniel D. Lee, Vijay Kumar, Joseph H. Harwood, Jennifer Wozencraft
Periodical inspection and maintenance of critical infrastructure such as dams, penstocks, and locks are of significant importance to prevent catastrophic failures.
no code implementations • 11 Sep 2018 • Armon Shariati, Bernd Pfrommer, Camillo J. Taylor
In this paper, we will demonstrate how Manhattan structure can be exploited to transform the Simultaneous Localization and Mapping (SLAM) problem, which is typically solved by a nonlinear optimization over feature positions, into a model selection problem solved by a convex optimization over higher order layout structures, namely walls, floors, and ceilings.
no code implementations • 1 Apr 2018 • Xu Liu, Steven W. Chen, Shreyas Aditya, Nivedha Sivakumar, Sandeep Dcunha, Chao Qu, Camillo J. Taylor, Jnaneshwar Das, Vijay Kumar
We present a novel fruit counting pipeline that combines deep segmentation, frame to frame tracking, and 3D localization to accurately count visible fruits across a sequence of images.
11 code implementations • 30 Nov 2017 • Ke Sun, Kartik Mohta, Bernd Pfrommer, Michael Watterson, Sikang Liu, Yash Mulgaonkar, Camillo J. Taylor, Vijay Kumar
However, we still encounter challenges in terms of improving the computational efficiency and robustness of the underlying algorithms for applications in autonomous flight with micro aerial vehicles in which it is difficult to use high quality sensors and pow- erful processors because of constraints on size and weight.
Robotics
3 code implementations • 12 Sep 2017 • Ty Nguyen, Steven W. Chen, Shreyas S. Shivakumar, Camillo J. Taylor, Vijay Kumar
Homography estimation between multiple aerial images can provide relative pose estimation for collaborative autonomous exploration and monitoring.
Ranked #4 on Homography Estimation on S-COCO
no code implementations • CVPR 2015 • Ryan Kennedy, Camillo J. Taylor
This paper presents a novel approach to solving optical flow problems using a discrete, tree-structured MRF derived from a hierarchical segmentation of the image.
no code implementations • 26 Sep 2013 • Ryan Kennedy, Laura Balzano, Stephen J. Wright, Camillo J. Taylor
We present a family of online algorithms for real-time factorization-based structure from motion, leveraging a relationship between incremental singular value decomposition and recently proposed methods for online matrix completion.
no code implementations • CVPR 2013 • Camillo J. Taylor
In this paper we explore approaches to accelerating segmentation and edge detection algorithms based on the gPb framework.