Search results

  • CSV Spreadsheet
  • RSS Feed
(1 - 8 of 8)
Weakly Supervised Learning on Image Manifolds
Title
Weakly Supervised Learning on Image Manifolds
Author
Wu, Hui
Date Created
2015
Subjects--Topical
Computer science
Description
Recent work in image manifold learning has shown the prevalence of unsupervised methods that provide compact representation and perceptually meaningful organization of images in certain types of natural image sets. However, in situations where a d...
Visual sonar: Estimating depth using sound waves and neuromorphic cameras
Title
Visual sonar: Estimating depth using sound waves and neuromorphic cameras
Author
Bagepalli, Abhijith
Date Created
2020
Subjects--Topical
Electrical engineering
Description
This thesis proposes a novel method to recover depth of scene objects using an acoustic source and a calibrated neuromorphic camera or event camera sensor. The proposed system is a non-contact, monocular depth estimation method that observes subtl...
Human-Centric Computer Vision for the Artificial Intelligence of Things
Title
Human-Centric Computer Vision for the Artificial Intelligence of Things
Author
Neff, Christopher
Date Created
2023
Subjects--Topical
Artificial intelligence, Computer engineering
Description
This dissertation presents a comprehensive exploration of innovative approaches and systems at the intersection of edge computing, deep learning, and real-time video analytics, with a focus on real-world computer vision for the Artificial Intellig...
Fine-grained Video Classification for Rare Events
Title
Fine-grained Video Classification for Rare Events
Author
Shan, Junjie
Date Created
2018
Subjects--Topical
Computer science, Information technology
Description
Video analysis plays an important role in the field of computer vision and finds its application in many areas. Fine-grained event classification is one of the most challenging problems in video analysis due to subtle difference between classes an...
Dynamic View Selection for Human Motion Analysis in Camera Networks
Title
Dynamic View Selection for Human Motion Analysis in Camera Networks
Author
Spurlock, Scott
Date Created
2015
Subjects--Topical
Computer science
Description
Automated human activity analysis for multi-camera networks requires algorithms that are both accurate and efficient for practical, real-time use. Current approaches face a trade-off between accuracy and speed, with the most accurate methods havin...
Better modeling of matching possibilities and uncertainty for offline visual multiple object tracking
Title
Better modeling of matching possibilities and uncertainty for offline visual multiple object tracking
Author
Rice, Lance
Date Created
2021
Subjects--Topical
Computer science
Description
The task of visually tracking multiple objects remains an active field of algorithm development even after several decades of research in the computer vision community. One reason it remains an active research area is that identifying and maintain...
Anomaly Detection for Manufacturing Applications Using Convolutional Autoencoders
Title
Anomaly Detection for Manufacturing Applications Using Convolutional Autoencoders
Author
Zouar, Nourelislam
Date Created
2021
Subjects--Topical
Computer science
Description
ABSTRACTNOURELISLAM ZOUAR. ANOMALY DETECTION FOR MANUFACTURING APPLICATIONS USING CONVOLUTIONAL AUTOENCODERS. (Under the direction of DR. MIN SHIN) Anomaly Detection in manufacturing environments is increasingly gaining popularity among companies ...
A Beginning-to-End System for Efficiently Gathering Tracking Data on Multiple Targets
Title
A Beginning-to-End System for Efficiently Gathering Tracking Data on Multiple Targets
Author
Rice, Lance
Date Created
2016
Subjects--Topical
Computer science
Description
Multi-object tracking in video has the potential for broad applicability, from analyzing division-of-labor within biological networks such as insects, to surveillance and traffic monitoring. Despite any potential the field of multiple object track...