Open Access. Powered by Scholars. Published by Universities.®
- Discipline
Articles 1 - 8 of 8
Full-Text Articles in Computer Engineering
Sequential Frame-Interpolation And Dct-Based Video Compression Framework, Yeganeh Jalalpour, Wu-Chi Feng, Feng Liu
Sequential Frame-Interpolation And Dct-Based Video Compression Framework, Yeganeh Jalalpour, Wu-Chi Feng, Feng Liu
Computer Science Faculty Publications and Presentations
Video data is ubiquitous; capturing, transferring, and storing even compressed video data is challenging because it requires substantial resources. With the large amount of video traffic being transmitted on the internet, any improvement in compressing such data, even small, can drastically impact resource consumption. In this paper, we present a hybrid video compression framework that unites the advantages of both DCT-based and interpolation-based video compression methods in a single framework. We show that our work can deliver the same visual quality or, in some cases, improve visual quality while reducing the bandwidth by 10--20%.
Flight Simulator Modeling Using Recurrent Neural Networks, Nickolas Sabatini, Andreas Natsis
Flight Simulator Modeling Using Recurrent Neural Networks, Nickolas Sabatini, Andreas Natsis
Undergraduate Research & Mentoring Program
Recurrent neural networks (RNNs) are a form of machine learning used to predict future values. This project uses RNNs tor predict future values for a flight simulator. Coded in Python using the Keras library, the model demonstrates training loss and validation loss, referring to the error when training the model.
Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods
Exploring And Expanding The One-Pixel Attack, Umairullah Khan, Walt Woods
Undergraduate Research & Mentoring Program
In machine learning research, adversarial examples are normal inputs to a classifier that have been specifically perturbed to cause the model to misclassify the input. These perturbations rarely affect the human readability of an input, even though the model’s output is drastically different. Recent work has demonstrated that image-classifying deep neural networks (DNNs) can be reliably fooled with the modification of a single pixel in the input image, without knowledge of a DNN’s internal parameters. This “one-pixel attack” utilizes an iterative evolutionary optimizer known as differential evolution (DE) to find the most effective pixel to perturb, via the evaluation of …
Real-Time Object Detection And Tracking On Drones, Tu Le
Real-Time Object Detection And Tracking On Drones, Tu Le
Undergraduate Research & Mentoring Program
Unmanned aerial vehicles, also known as drones, have been more and more widely used in recent decades because of their mobility. They appear in many applications such as farming, search and rescue, entertainment, military, and so on. Such high demands for drones lead to the need of developments in drone technologies. Next generations of commercial and military drones are expected to be aware of surrounding objects while flying autonomously in different terrains and conditions. One of the biggest challenges to drone automation is the ability to detect and track objects of interest in real-time. While there are many robust machine …
Video Frame Interpolation Via Adaptive Separable Convolution, Simon Niklaus, Long Mai, Feng Liu
Video Frame Interpolation Via Adaptive Separable Convolution, Simon Niklaus, Long Mai, Feng Liu
Computer Science Faculty Publications and Presentations
Standard video frame interpolation methods first estimate optical flow between input frames and then synthesize an intermediate frame guided by motion. Recent approaches merge these two steps into a single convolution process by convolving input frames with spatially adaptive kernels that account for motion and re-sampling simultaneously. These methods require large kernels to handle large motion, which limits the number of pixels whose kernels can be estimated at once due to the large memory demand. To address this problem, this paper formulates frame interpolation as local separable convolution over input frames using pairs of 1D kernels. Compared to regular 2D …
Fast On-Line Kernel Density Estimation For Active Object Localization, Anthony D. Rhodes, Max H. Quinn, Melanie Mitchell
Fast On-Line Kernel Density Estimation For Active Object Localization, Anthony D. Rhodes, Max H. Quinn, Melanie Mitchell
Computer Science Faculty Publications and Presentations
A major goal of computer vision is to enable computers to interpret visual situations—abstract concepts (e.g., “a person walking a dog,” “a crowd waiting for a bus,” “a picnic”) whose image instantiations are linked more by their common spatial and semantic structure than by low-level visual similarity. In this paper, we propose a novel method for prior learning and active object localization for this kind of knowledge-driven search in static images. In our system, prior situation knowledge is captured by a set of flexible, kernel-based density estimations— a situation model—that represent the expected spatial structure of the given situation. These …
Bayesian Optimization For Refining Object Proposals, Anthony D. Rhodes, Jordan Witte, Melanie Mitchell, Bruno Jedynak
Bayesian Optimization For Refining Object Proposals, Anthony D. Rhodes, Jordan Witte, Melanie Mitchell, Bruno Jedynak
Computer Science Faculty Publications and Presentations
We develop a general-purpose algorithm using a Bayesian optimization framework for the efficient refinement of object proposals. While recent research has achieved substantial progress for object localization and related objectives in computer vision, current state-of-the-art object localization procedures are nevertheless encumbered by inefficiency and inaccuracy. We present a novel, computationally efficient method for refining inaccurate bounding-box proposals for a target object using Bayesian optimization. Offline, image features from a convolutional neural network are used to train a model to predict an object proposal’s offset distance from a target object. Online, this model is used in a Bayesian active search to …
Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson
Constructive Induction Machines For Data Mining, Marek Perkowski, Stanislaw Grygiel, Qihong Chen, Dave Mattson
Electrical and Computer Engineering Faculty Publications and Presentations
"Learning Hardware" approach involves creating a computational network based on feedback from the environment (for instance, positive and negative examples from the trainer), and realizing this network in an array of Field Programmable Gate Arrays (FPGAs). Computational networks can be built based on incremental supervised learning (Neural Net training) or global construction (Decision Tree design). Here we advocate the approach to Learning Hardware based on Constructive Induction methods of Machine Learning (ML) using multivalued functions. This is contrasted with the Evolvable Hardware (EHW) approach in which learning/evolution is based on the genetic algorithm only.