Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences Commons™

Open Access. Powered by Scholars. Published by Universities.®

Computer vision

Discipline
Institution
Publication Year
Publication
Publication Type
File Type

Articles 121 - 150 of 349

Full-Text Articles in Computer Sciences

Towards A Machine Learning-Based Digital Twin For Non-Invasive Human Bio-Signal Fusion, Izaldein Al-Zyoud, Fedwa Laamarti, Xiaocong Ma, Diana Tobón, Abdulmotaleb Elsaddik Dec 2022

Towards A Machine Learning-Based Digital Twin For Non-Invasive Human Bio-Signal Fusion, Izaldein Al-Zyoud, Fedwa Laamarti, Xiaocong Ma, Diana Tobón, Abdulmotaleb Elsaddik

Computer Vision Faculty Publications

Human bio-signal fusion is considered a critical technological solution that needs to be advanced to enable modern and secure digital health and well-being applications in the metaverse. To support such efforts, we propose a new data-driven digital twin (DT) system to fuse three human physiological bio-signals: heart rate (HR), breathing rate (BR), and blood oxygen saturation level (SpO2). To accomplish this goal, we design a computer vision technology based on the non-invasive photoplethysmography (PPG) technique to extract raw time-series bio-signal data from facial video frames. Then, we implement machine learning (ML) technology to model and measure the bio-signals. We accurately …

Go to article

Understanding Human Actions: Cognitive Assessment And Action Segmentation Using Human Object Interaction, Saif Sayed Dec 2022

Understanding Human Actions: Cognitive Assessment And Action Segmentation Using Human Object Interaction, Saif Sayed

Computer Science and Engineering Dissertations - Archive

Automatic understanding of human behavior has several applications in medicine and surveillance. Analysing human actions can enable cognitive assessment of children by measuring their hyperactivity and response inhibition which can give physicians better understanding of their cognitive state. Automatic and non-invasive assessment for cognitive disorders will increase the affordability and reach for these detection methods and can prove life-changing in child’s development. Human activity can also be analysed in common settings such as cooking in kitchen and understanding the information of human object interaction can give priors on the underlying activity they are performing. In the first section, we focus …

Go to article

Transresnet: Integrating The Strengths Of Vits And Cnns For High Resolution Medical Image Segmentation Via Feature Grafting, Muhammad Hamza Sharif, Dmitry Demidov, Asif Hanif, Mohammad Yaqub, Min Xu Nov 2022

Transresnet: Integrating The Strengths Of Vits And Cnns For High Resolution Medical Image Segmentation Via Feature Grafting, Muhammad Hamza Sharif, Dmitry Demidov, Asif Hanif, Mohammad Yaqub, Min Xu

Computer Vision Faculty Publications

High-resolution images are preferable in medical imaging domain as they significantly improve the diagnostic capability of the underlying method. In particular, high resolution helps substantially in improving automatic image segmentation. However, most of the existing deep learning-based techniques for medical image segmentation are optimized for input images having small spatial dimensions and perform poorly on high-resolution images. To address this shortcoming, we propose a parallel-in-branch architecture called TransResNet, which incorporates Transformer and CNN in a parallel manner to extract features from multi-resolution images independently. In TransResNet, we introduce Cross Grafting Module (CGM), which generates the grafted features, enriched in both …

Go to article

A Robust Normalizing Flow Using Bernstein-Type Polynomials, Sameera Ramasinghe, Kasun Fernando, Salman Khan, Nick Barnes Nov 2022

A Robust Normalizing Flow Using Bernstein-Type Polynomials, Sameera Ramasinghe, Kasun Fernando, Salman Khan, Nick Barnes

Computer Vision Faculty Publications

Modeling real-world distributions can often be challenging due to sample data that are subjected to perturbations, e.g., instrumentation errors, or added random noise. Since flow models are typically nonlinear algorithms, they amplify these initial errors, leading to poor generalizations. This paper proposes a framework to construct Normalizing Flows (NFs) which demonstrate higher robustness against such initial errors. To this end, we utilize Bernstein-type polynomials inspired by the optimal stability of the Bernstein basis. Further, compared to the existing NF frameworks, our method provides compelling advantages like theoretical upper bounds for the approximation error, better suitability for compactly supported densities, and …

Go to article

Face Pyramid Vision Transformer, Khawar Islam, Muhammad Zaigham Zaheer, Arif Mahmood Nov 2022

Face Pyramid Vision Transformer, Khawar Islam, Muhammad Zaigham Zaheer, Arif Mahmood

Computer Vision Faculty Publications

A novel Face Pyramid Vision Transformer (FPVT) is proposed to learn a discriminative multi-scale facial representations for face recognition and verification. In FPVT, Face Spatial Reduction Attention (FSRA) and Dimensionality Reduction (FDR) layers are employed to make the feature maps compact, thus reducing the computations. An Improved Patch Embedding (IPE) algorithm is proposed to exploit the benefits of CNNs in ViTs (e.g., shared weights, local context, and receptive fields) to model lower-level edges to higher-level semantic primitives. Within FPVT framework, a Convolutional Feed-Forward Network (CFFN) is proposed that extracts locality information to learn low level facial information. The proposed FPVT …

Go to article

How To Train Vision Transformer On Small-Scale Datasets?, Hanan Gani, Muzammal Naseer, Mohammad Yaqub Nov 2022

How To Train Vision Transformer On Small-Scale Datasets?, Hanan Gani, Muzammal Naseer, Mohammad Yaqub

Computer Vision Faculty Publications

Vision Transformer (ViT), a radically different architecture than convolutional neural networks offers multiple advantages including design simplicity, robustness and state-of-the-art performance on many vision tasks. However, in contrast to convolutional neural networks, Vision Transformer lacks inherent inductive biases. Therefore, successful training of such models is mainly attributed to pre-training on large-scale datasets such as ImageNet with 1.2M or JFT with 300M images. This hinders the direct adaption of Vision Transformer for small-scale datasets. In this work, we show that self-supervised inductive biases can be learned directly from small-scale datasets and serve as an effective weight initialization scheme for fine-tuning. This …

Go to article

Ubnormal: New Benchmark For Supervised Open-Set Video Anomaly Detection, Andra Acsintoae, Andrei Florescu, Mariana-Iuliana Georgescu, Tudor Mare, Paul Sumedrea, Radu Tudor Ionescu, Fahad Shahbaz Khan, Mubarak Shah Sep 2022

Ubnormal: New Benchmark For Supervised Open-Set Video Anomaly Detection, Andra Acsintoae, Andrei Florescu, Mariana-Iuliana Georgescu, Tudor Mare, Paul Sumedrea, Radu Tudor Ionescu, Fahad Shahbaz Khan, Mubarak Shah

Computer Vision Faculty Publications

Detecting abnormal events in video is commonly framed as a one-class classification task, where training videos contain only normal events, while test videos encompass both normal and abnormal events. In this scenario, anomaly detection is an open-set problem. However, some studies assimilate anomaly detection to action recognition. This is a closed-set scenario that fails to test the capability of systems at detecting new anomaly types. To this end, we propose UBnormal, a new supervised open-set benchmark composed of multiple virtual scenes for video anomaly detection. Unlike existing data sets, we introduce abnormal events annotated at the pixel level at training …

Go to article

Maximum Spatial Perturbation Consistency For Unpaired Image-To-Image Translation, Yanwu Xu, Shaoan Xie, Wenhao Wu, Kun Zhang, Mingming Gong, Kayhan Batmanghelich Sep 2022

Maximum Spatial Perturbation Consistency For Unpaired Image-To-Image Translation, Yanwu Xu, Shaoan Xie, Wenhao Wu, Kun Zhang, Mingming Gong, Kayhan Batmanghelich

Machine Learning Faculty Publications

Unpaired image-to-image translation (I2I) is an ill-posed problem, as an infinite number of translation functions can map the source domain distribution to the target distribution. Therefore, much effort has been put into designing suitable constraints, e.g., cycle consistency (CycleGAN), geometry consistency (GCGAN), and contrastive learning-based constraints (CUTGAN), that help better pose the problem. However, these well-known constraints have limitations: (1) they are either too restrictive or too weak for specific I2I tasks; (2) these methods result in content distortion when there is a significant spatial variation between the source and target domains. This paper proposes a universal regularization technique called …

Go to article

How Facial Features Convey Attention In Stationary Environments, Janelle Domantay, Brendan Morris Aug 2022

How Facial Features Convey Attention In Stationary Environments, Janelle Domantay, Brendan Morris

Spectra Undergraduate Research Journal

Awareness detection technologies have been gaining traction in a variety of enterprises; most often used for driver fatigue detection, recent research has shifted towards using computer vision technologies to analyze user attention in environments such as online classrooms. This paper aims to extend previous research on distraction detection by analyzing which visual features contribute most to predicting awareness and fatigue. We utilized the open-source facial analysis toolkit OpenFace in order to analyze visual data of subjects at varying levels of attentiveness. Then, using a Support-Vector Machine (SVM) we created several prediction models for user attention and identified the Histogram of …

Go to article

Avist: A Benchmark For Visual Object Tracking In Adverse Visibility, Mubashir Noman, Wafa Al Ghallabi, Daniya Najiha, Christoph Mayer, Hisham Cholakkal, Salman Khan, Luc Van Gool, Fahad Shahbaz Khan Aug 2022

Avist: A Benchmark For Visual Object Tracking In Adverse Visibility, Mubashir Noman, Wafa Al Ghallabi, Daniya Najiha, Christoph Mayer, Hisham Cholakkal, Salman Khan, Luc Van Gool, Fahad Shahbaz Khan

Computer Vision Faculty Publications

One of the key factors behind the recent success in visual tracking is the availability of dedicated benchmarks. While being greatly benefiting to the tracking research, existing benchmarks do not pose the same difficulty as before with recent trackers achieving higher performance mainly due to (i) the introduction of more sophisticated transformers-based methods and (ii) the lack of diverse scenarios with adverse visibility such as, severe weather conditions, camouflage and imaging effects. We introduce AVisT, a dedicated benchmark for visual tracking in diverse scenarios with adverse visibility. AVisT comprises 120 challenging sequences with 80k annotated frames, spanning 18 diverse scenarios …

Go to article

Automated Identification Of Astronauts On Board The International Space Station: A Case Study In Space Archaeology, Rao Hamza Ali, Amir Kanan Kashefi, Alice C. Gorman, Justin St. P. Walsh, Erik J. Linstead Aug 2022

Automated Identification Of Astronauts On Board The International Space Station: A Case Study In Space Archaeology, Rao Hamza Ali, Amir Kanan Kashefi, Alice C. Gorman, Justin St. P. Walsh, Erik J. Linstead

Art Faculty Articles and Research

We develop and apply a deep learning-based computer vision pipeline to automatically identify crew members in archival photographic imagery taken on-board the International Space Station. Our approach is able to quickly tag thousands of images from public and private photo repositories without human supervision with high degrees of accuracy, including photographs where crew faces are partially obscured. Using the results of our pipeline, we carry out a large-scale network analysis of the crew, using the imagery data to provide novel insights into the social interactions among crew during their missions.

Go to article

3d Vision With Transformers: A Survey, Jean Lahoud, Jiale Cao, Fahad Shahbaz Khan, Hisham Cholakkal, Rao Anwer, Salman Khan, Ming-Hsuan Yang Aug 2022

3d Vision With Transformers: A Survey, Jean Lahoud, Jiale Cao, Fahad Shahbaz Khan, Hisham Cholakkal, Rao Anwer, Salman Khan, Ming-Hsuan Yang

Computer Vision Faculty Publications

The success of the transformer architecture in natural language processing has recently triggered attention in the computer vision field. The transformer has been used as a replacement for the widely used convolution operators, due to its ability to learn long-range dependencies. This replacement was proven to be successful in numerous tasks, in which several state-of-the-art methods rely on transformers for better learning. In computer vision, the 3D field has also witnessed an increase in employing the transformer for 3D convolution neural networks and multi-layer perceptron networks. Although a number of surveys have focused on transformers in vision in general, 3D …

Go to article

Applied Deep Learning: Case Studies In Computer Vision And Natural Language Processing, Md Reshad Ul Hoque Aug 2022

Applied Deep Learning: Case Studies In Computer Vision And Natural Language Processing, Md Reshad Ul Hoque

Electrical & Computer Engineering Theses & Dissertations

Deep learning has proved to be successful for many computer vision and natural language processing applications. In this dissertation, three studies have been conducted to show the efficacy of deep learning models for computer vision and natural language processing. In the first study, an efficient deep learning model was proposed for seagrass scar detection in multispectral images which produced robust, accurate scars mappings. In the second study, an arithmetic deep learning model was developed to fuse multi-spectral images collected at different times with different resolutions to generate high-resolution images for downstream tasks including change detection, object detection, and land cover …

Go to article

Directed Acyclic Graph-Based Neural Networks For Tunable Low-Power Computer Vision, Abhinav Goel, Caleb Tung, Nick Eliopoulos, Xiao Hu, George K. Thiruvathukal, James C. Davis, Yung-Hisang Lu Aug 2022

Directed Acyclic Graph-Based Neural Networks For Tunable Low-Power Computer Vision, Abhinav Goel, Caleb Tung, Nick Eliopoulos, Xiao Hu, George K. Thiruvathukal, James C. Davis, Yung-Hisang Lu

Computer Science: Faculty Publications and Other Works

Processing visual data on mobile devices has many applications, e.g., emergency response and tracking. State-of-the-art computer vision techniques rely on large Deep Neural Networks (DNNs) that are usually too power-hungry to be deployed on resource-constrained edge devices. Many techniques improve DNN efficiency of DNNs by compromising accuracy. However, the accuracy and efficiency of these techniques cannot be adapted for diverse edge applications with different hardware constraints and accuracy requirements. This paper demonstrates that a recent, efficient tree-based DNN architecture, called the hierarchical DNN, can be converted into a Directed Acyclic Graph-based (DAG) architecture to provide tunable accuracy-efficiency tradeoff options. We …

Go to article

Computer Aided Diagnosis System For Breast Cancer Using Deep Learning., Asma Baccouche Aug 2022

Computer Aided Diagnosis System For Breast Cancer Using Deep Learning., Asma Baccouche

Electronic Theses and Dissertations

The recent rise of big data technology surrounding the electronic systems and developed toolkits gave birth to new promises for Artificial Intelligence (AI). With the continuous use of data-centric systems and machines in our lives, such as social media, surveys, emails, reports, etc., there is no doubt that data has gained the center of attention by scientists and motivated them to provide more decision-making and operational support systems across multiple domains. With the recent breakthroughs in artificial intelligence, the use of machine learning and deep learning models have achieved remarkable advances in computer vision, ecommerce, cybersecurity, and healthcare. Particularly, numerous …

Go to article

Robustar: Interactive Toolbox Supporting Precise Data Annotation For Robust Vision Learning, Chonghan Chen, Haohan Wang, Leyang Hu, Yuhao Zhang, Shuguang Lyu, Jingcheng Wu, Xinnuo Li, Linjing Sun, Eric Xing Jul 2022

Robustar: Interactive Toolbox Supporting Precise Data Annotation For Robust Vision Learning, Chonghan Chen, Haohan Wang, Leyang Hu, Yuhao Zhang, Shuguang Lyu, Jingcheng Wu, Xinnuo Li, Linjing Sun, Eric Xing

Machine Learning Faculty Publications

We introduce the initial release of our software Robustar, which aims to improve the robustness of vision classification machine learning models through a data-driven perspective. Building upon the recent understanding that the lack of machine learning model’s robustness is the tendency of the model’s learning of spurious features, we aim to solve this problem from its root at the data perspective by removing the spurious features from the data before training. In particular, we introduce a software that helps the users to better prepare the data for training image classification models by allowing the users to annotate the spurious features …

Go to article

Bridging The Gap Between Object And Image-Level Representations For Open-Vocabulary Detection, Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan, Fahad Shahbaz Khan Jul 2022

Bridging The Gap Between Object And Image-Level Representations For Open-Vocabulary Detection, Hanoona Rasheed, Muhammad Maaz, Muhammad Uzair Khattak, Salman Khan, Fahad Shahbaz Khan

Computer Vision Faculty Publications

Existing open-vocabulary object detectors typically enlarge their vocabulary sizes by leveraging different forms of weak supervision. This helps generalize to novel objects at inference. Two popular forms of weak-supervision used in open-vocabulary detection (OVD) include pretrained CLIP model and image-level supervision. We note that both these modes of supervision are not optimally aligned for the detection task: CLIP is trained with image-text pairs and lacks precise localization of objects while the image-level supervision has been used with heuristics that do not accurately specify local object regions. In this work, we propose to address this problem by performing object-centric alignment of …

Go to article

Irrelevant Pixels Are Everywhere: Find And Exclude Them For More Efficient Computer Vision, Caleb Tung, Abhinav Goel, Xiao Hu, Nick Eliopoulos, Emmanuel Amobi, George K. Thiruvathukal, Vipin Chaudhary, Yung-Hisang Lu Jul 2022

Irrelevant Pixels Are Everywhere: Find And Exclude Them For More Efficient Computer Vision, Caleb Tung, Abhinav Goel, Xiao Hu, Nick Eliopoulos, Emmanuel Amobi, George K. Thiruvathukal, Vipin Chaudhary, Yung-Hisang Lu

Computer Science: Faculty Publications and Other Works

Computer vision is often performed using Convolutional Neural Networks (CNNs). CNNs are compute-intensive and challenging to deploy on power-constrained systems such as mobile and Internet-of-Things (IoT) devices. CNNs are compute-intensive because they indiscriminately compute many features on all pixels of the input image. We observe that, given a computer vision task, images often contain pixels that are irrelevant to the task. For example, if the task is looking for cars, pixels in the sky are not very useful. Therefore, we propose that a CNN be modified to only operate on relevant pixels to save computation and energy. We propose a …

Go to article

Traffic Behavior Recognition From Traffic Videos Under Occlusion Condition: A Kalman Filter Approach, Junfeng Jiao, Huihai Wang Jul 2022

Traffic Behavior Recognition From Traffic Videos Under Occlusion Condition: A Kalman Filter Approach, Junfeng Jiao, Huihai Wang

Research Collection College of Integrative Studies

Real-time traffic data at intersections is significant for development of adaptive traffic light control systems. Sensors such as infrared radiation and GPS are not capable of providing detailed traffic information. Compared with these sensors, surveillance cameras have the potential to provide real scenes for traffic analysis. In this research, a You Only Look Once (YOLO)-based algorithm is employed to detect and track vehicles from traffic videos, and a predefined road mask is used to determine traffic flow and turning events in different roads. A Kalman filter is used to estimate and predict vehicle speed and location under the condition of …

Go to article

Edgenext: Efficiently Amalgamated Cnn-Transformer Architecture For Mobile Vision Applications, Muhammad Maaz, Abdelrahman Shaker, Hisham Cholakkal, Salman Khan, Syed Waqas Zamir, Rao Anwer, Fahad Shahbaz Khan Jun 2022

Edgenext: Efficiently Amalgamated Cnn-Transformer Architecture For Mobile Vision Applications, Muhammad Maaz, Abdelrahman Shaker, Hisham Cholakkal, Salman Khan, Syed Waqas Zamir, Rao Anwer, Fahad Shahbaz Khan

Computer Vision Faculty Publications

In the pursuit of achieving ever-increasing accuracy, large and complex neural networks are usually developed. Such models demand high computational resources and therefore cannot be deployed on edge devices. It is of great interest to build resource-efficient general purpose networks due to their usefulness in several application areas. In this work, we strive to effectively combine the strengths of both CNN and Transformer models and propose a new efficient hybrid architecture EdgeNeXt. Specifically in EdgeNeXt, we introduce split depth-wise transpose attention (SDTA) encoder that splits input tensors into multiple channel groups and utilizes depth-wise convolution along with self-attention across channel …

Go to article

Multiple Object Tracking For Marine Science, Nicholas A. Wachter Jun 2022

Multiple Object Tracking For Marine Science, Nicholas A. Wachter

Computer Science and Software Engineering

As drone and computer vision technology has been improving, many fields of study have been quick to utilize it to improve the accuracy and ease of data collection. The combination of the two technologies is perfect for surveying large areas and identifying features of interest. Marine science utilizes these technologies for activities such as animal tracking and population counting. I am working with the Drones for Marine Science research group at Cal Poly who want to build a fleet of drones that will fly out over the ocean to identify and track various marine animals. My role will be to …

Go to article

Metaformer Is Actually What You Need For Vision, Weihao Yu, Mi Luo, Pan Zhou, Chenyang Si, Yichen Zhou, Xinchao Wang, Jiashi Feng, Shuicheng Yan Jun 2022

Metaformer Is Actually What You Need For Vision, Weihao Yu, Mi Luo, Pan Zhou, Chenyang Si, Yichen Zhou, Xinchao Wang, Jiashi Feng, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in transformers can be replaced by spatial MLPs and the resulted models still perform quite well. Based on this observation, we hypothesize that the general architecture of the transformers, instead of the specific token mixer module, is more essential to the model's performance. To verify this, we deliberately replace the attention module in transformers with an embarrassingly simple spatial pooling operator to conduct only basic token mixing. Surprisingly, we observe …

Go to article

High-Resolution Face Swapping Via Latent Semantics Disentanglement, Yangyang Xu, Bailin Deng, Junle Wang, Yanqing Jing, Jia Pan, Shengfeng He Jun 2022

High-Resolution Face Swapping Via Latent Semantics Disentanglement, Yangyang Xu, Bailin Deng, Junle Wang, Yanqing Jing, Jia Pan, Shengfeng He

Research Collection School Of Computing and Information Systems

We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer from the entangled semantics of the latent space. We explicitly disentangle the latent semantics by utilizing the progressive nature of the generator, deriving structure at-tributes from the shallow layers and appearance attributes from the deeper ones. Identity and pose information within the structure attributes are further separated by introducing a landmark-driven structure transfer latent direction. The disentangled latent code produces rich generative features that incorporate feature blending …

Go to article

Gauging The State-Of-The-Art For Foresight Weight Pruning On Neural Networks, Noah James May 2022

Gauging The State-Of-The-Art For Foresight Weight Pruning On Neural Networks, Noah James

Computer Science and Computer Engineering Undergraduate Honors Theses

The state-of-the-art for pruning neural networks is ambiguous due to poor experimental practices in the field. Newly developed approaches rarely compare to each other, and when they do, their comparisons are lackluster or contain errors. In the interest of stabilizing the field of pruning, this paper initiates a dive into reproducing prominent pruning algorithms across several architectures and datasets. As a first step towards this goal, this paper shows results for foresight weight pruning across 6 baseline pruning strategies, 5 modern pruning strategies, random pruning, and one legacy method (Optimal Brain Damage). All strategies are evaluated on 3 different architectures …

Go to article

Visual Attention Methods In Deep Learning: An In-Depth Survey, Mohammed Hassanin, Anwar Saeed, Ibrahim Radwan, Fahad Shahbaz Khan, Ajmal Mian Apr 2022

Visual Attention Methods In Deep Learning: An In-Depth Survey, Mohammed Hassanin, Anwar Saeed, Ibrahim Radwan, Fahad Shahbaz Khan, Ajmal Mian

Computer Vision Faculty Publications

Inspired by the human cognitive system, attention is a mechanism that imitates the human cognitive awareness about specific information, amplifying critical details to focus more on the essential aspects of data. Deep learning has employed attention to boost performance for many applications. Interestingly, the same attention design can suit processing different data modalities and can easily be incorporated into large networks. Furthermore, multiple complementary attention mechanisms can be incorporated in one network. Hence, attention techniques have become extremely attractive. However, the literature lacks a comprehensive survey specific to attention techniques to guide researchers in employing attention in their deep models. …

Go to article

Intra-Hour Solar Forecasting Using Cloud Dynamics Features Extracted From Ground-Based Infrared Sky Images, Guillermo Terrén-Serrano Apr 2022

Intra-Hour Solar Forecasting Using Cloud Dynamics Features Extracted From Ground-Based Infrared Sky Images, Guillermo Terrén-Serrano

Electrical and Computer Engineering ETDs

Due to the increasing use of photovoltaic systems, power grids are vulnerable to the projection of shadows from moving clouds. An intra-hour solar forecast provides power grids with the capability of automatically controlling the dispatch of energy, reducing the additional cost for a guaranteed, reliable supply of energy (i.e., energy storage). This dissertation introduces a novel sky imager consisting of a long-wave radiometric infrared camera and a visible light camera with a fisheye lens. The imager is mounted on a solar tracker to maintain the Sun in the center of the images throughout the day, reducing the scattering effect produced …

Go to article

Energy-Based Latent Aligner For Incremental Learning, K.J. Joseph, Salman Khan, Fahad Shahbaz Khan, Rao Muhammad Anwer, Vineeth N. Balasubramanian Mar 2022

Energy-Based Latent Aligner For Incremental Learning, K.J. Joseph, Salman Khan, Fahad Shahbaz Khan, Rao Muhammad Anwer, Vineeth N. Balasubramanian

Computer Vision Faculty Publications

Deep learning models tend to forget their earlier knowledge while incrementally learning new tasks. This behavior emerges because the parameter updates optimized for the new tasks may not align well with the updates suitable for older tasks. The resulting latent representation mismatch causes forgetting. In this work, we propose ELI: Energy-based Latent Aligner for Incremental Learning, which first learns an energy manifold for the latent representations such that previous task latents will have low energy and the current task latents have high energy values. This learned manifold is used to counter the representational shift that happens during incremental learning. The …

Go to article

Smoothing Of Convolutional Neural Network Classifications, Glen R. Drumm Mar 2022

Smoothing Of Convolutional Neural Network Classifications, Glen R. Drumm

Theses and Dissertations

Smoothing convolutional neural networks is investigated. When intermittent and random false predictions happen, a technique of average smoothing is applied to smooth out the incorrect predictions. While a simple problem environment shows proof of concept, obstacles remain for applying such a technique to a more operationally complex problem.

Go to article

Using Generative Adversarial Networks To Augment Unmanned Aerial Vehicle Image Classification Training Sets, Benjamin J. Mccloskey Mar 2022

Using Generative Adversarial Networks To Augment Unmanned Aerial Vehicle Image Classification Training Sets, Benjamin J. Mccloskey

Theses and Dissertations

A challenging task in computer vision is finding techniques to improve the object detection and classification capabilities of ML models used for processing images acquired by moving aerial platforms. This research explores if GAN augmented UAV training sets can increase the generalizability of a detection model trained on said data. To answer this question, the YOLOv4-Tiny Object Detection Model was trained with aerial image training sets depicting rural environments. The salient objects within the frames were recreated using various GAN architectures, placed back into the original frames, and the augmented frames appended to the original training sets. GAN augmentation on …

Go to article

Monocular Pose Estimation For Automated Aerial Refueling Via Perspective-N-Point, James C. Lynch Mar 2022

Monocular Pose Estimation For Automated Aerial Refueling Via Perspective-N-Point, James C. Lynch

Theses and Dissertations

Any Automated Aerial Refueling (AAR) solution requires the quick and precise estimation of the relative position and rotation of the two aircraft involved. This is currently accomplished using stereo vision techniques augmented by Iterative Closest Point (ICP), but requires post-processing to account for environmental factors such as boom occlusion. This paper proposes a monocular solution, combining a custom-trained single-shot object detection Convolutional Neural Network (CNN) and Perspective-n-Point (PnP) estimation to calculate a pose estimate with a single image. This solution is capable of pose estimation at contact point (22m) within 7cm of error and a rate of 10Hz, regardless of …

Go to article

First Prev Next Last