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 91 - 120 of 349

Full-Text Articles in Computer Sciences

Object Recognition With Deep Neural Networks In Low-End Systems, Lillian Davis Oct 2023

Object Recognition With Deep Neural Networks In Low-End Systems, Lillian Davis

Mahurin Honors College Capstone Experience/Thesis Projects

Object recognition is an important area in computer vision. Object recognition has been advanced significantly by deep learning that unifies feature extraction and classification. In general, deep neural networks, such as Convolution Neural Networks (CNNs), are trained in high-performance systems. Aiming to extend the reach of deep learning to personal computing, I propose a study of deep learning-based object recognition in low-end systems, such as laptops. This research includes how differing layer configurations and hyperparameter values used in CNNs can either create or resolve the issue of overfitting and affect final accuracy levels of object recognition systems. The main contribution …

Go to article

Stprivacy: Spatio-Temporal Privacy-Preserving Action Recognition, Ming Li, Xiangyu Xu, Hehe Fan, Pan Zhou, Jun Liu, Jia-Wei Liu, Jiahe Li, Jussi Keppo, Mike Zheng Shou, Shuicheng Yan Oct 2023

Stprivacy: Spatio-Temporal Privacy-Preserving Action Recognition, Ming Li, Xiangyu Xu, Hehe Fan, Pan Zhou, Jun Liu, Jia-Wei Liu, Jiahe Li, Jussi Keppo, Mike Zheng Shou, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks. First, they may compromise temporal dynamics in input videos, which are critical for accurate action recognition. Second, they are vulnerable to practical attacking scenarios where attackers probe for privacy from an entire video rather than individual frames. To address these issues, we propose a novel framework STPrivacy to perform video-level PPAR. For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i.e., sparsification …

Go to article

Pymaivar: An Open-Source Python Suit For Audio-Image Representation In Human Action Recognition, Muhammad B. Shaikh, Douglas Chai, Syed M. S. Islam, Naveed Akhtar Sep 2023

Pymaivar: An Open-Source Python Suit For Audio-Image Representation In Human Action Recognition, Muhammad B. Shaikh, Douglas Chai, Syed M. S. Islam, Naveed Akhtar

Research outputs 2022 to 2026

We present PyMAiVAR, a versatile toolbox that encompasses the generation of image representations for audio data including Wave plots, Spectral Centroids, Spectral Roll Offs, Mel Frequency Cepstral Coefficients (MFCC), MFCC Feature Scaling, and Chromagrams. This wide-ranging toolkit generates rich audio-image representations, playing a pivotal role in reshaping human action recognition. By fully exploiting audio data's latent potential, PyMAiVAR stands as a significant advancement in the field. The package is implemented in Python and can be used across different operating systems.

Go to article

Ifseg: Image-Free Semantic Segmentation Via Vision-Language Model, Sukmin Yun, Seong Hyeon Park, Paul Hongsuck Seo, Jinwoo Shin Aug 2023

Ifseg: Image-Free Semantic Segmentation Via Vision-Language Model, Sukmin Yun, Seong Hyeon Park, Paul Hongsuck Seo, Jinwoo Shin

Machine Learning Faculty Publications

Vision-language (VL) pre-training has recently gained much attention for its transferability and flexibility in novel concepts (e.g., cross-modality transfer) across various visual tasks. However, VL-driven segmentation has been under-explored, and the existing approaches still have the burden of acquiring additional training images or even segmentation annotations to adapt a VL model to downstream segmentation tasks. In this paper, we introduce a novel image-free segmentation task where the goal is to perform semantic segmentation given only a set of the target semantic categories, but without any task-specific images and annotations. To tackle this challenging task, our proposed method, coined IFSeg, generates …

Go to article

3d-Aware Multi-Class Image-To-Image Translation With Nerfs, Senmao Li, Joost Van De Weijer, Yaxing Wang, Fahad Shahbaz Khan, Meiqin Liu, Jian Yang Aug 2023

3d-Aware Multi-Class Image-To-Image Translation With Nerfs, Senmao Li, Joost Van De Weijer, Yaxing Wang, Fahad Shahbaz Khan, Meiqin Liu, Jian Yang

Computer Vision Faculty Publications

Recent advances in 3D-aware generative models (3D-aware GANs) combined with Neural Radiance Fields (NeRF) have achieved impressive results. However no prior works investigate 3D-aware GANs for 3D consistent multiclass image-to-image (3D-aware 121) translation. Naively using 2D-121 translation methods suffers from unrealistic shape/identity change. To perform 3D-aware multiclass 121 translation, we decouple this learning process into a multiclass 3D-aware GAN step and a 3D-aware 121 translation step. In the first step, we propose two novel techniques: a new conditional architecture and an effective training strategy. In the second step, based on the well-trained multiclass 3D-aware GAN architecture, that preserves view-consistency, we …

Go to article

Discriminative Co-Saliency And Background Mining Transformer For Co-Salient Object Detection, Long Li, Junwei Han, Ni Zhang, Nian Liu, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan Aug 2023

Discriminative Co-Saliency And Background Mining Transformer For Co-Salient Object Detection, Long Li, Junwei Han, Ni Zhang, Nian Liu, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan

Computer Vision Faculty Publications

Most previous co-salient object detection works mainly focus on extracting co-salient cues via mining the consistency relations across images while ignore explicit exploration of background regions. In this paper, we propose a Discriminative co-saliency and background Mining Transformer framework (DMT) based on several economical multi-grained correlation modules to explicitly mine both co-saliency and background information and effectively model their discrimination. Specifically, we first propose a region-to-region correlation module for introducing inter-image relations to pixel-wise segmentation features while maintaining computational efficiency. Then, we use two types of pre-defined tokens to mine co-saliency and background information via our proposed contrast-induced pixel-to-token correlation …

Go to article

Multiclass Confidence And Localization Calibration For Object Detection, Bimsara Pathiraja, Malitha Gunawardhana, Muhammad Haris Khan Aug 2023

Multiclass Confidence And Localization Calibration For Object Detection, Bimsara Pathiraja, Malitha Gunawardhana, Muhammad Haris Khan

Computer Vision Faculty Publications

Albeit achieving high predictive accuracy across many challenging computer vision problems, recent studies suggest that deep neural networks (DNNs) tend to make over-confident predictions, rendering them poorly calibrated. Most of the existing attempts for improving DNN calibration are limited to classification tasks and restricted to calibrating in-domain predictions. Surprisingly, very little to no attempts have been made in studying the calibration of object detection methods, which occupy a pivotal space in vision-based security-sensitive, and safety-critical applications. In this paper, we propose a new train-time technique for calibrating modern object detection methods. It is capable of jointly calibrating multiclass confidence and …

Go to article

Autonomous Shipwreck Detection & Mapping, William Ard Aug 2023

Autonomous Shipwreck Detection & Mapping, William Ard

LSU Master's Theses

This thesis presents the development and testing of Bruce, a low-cost hybrid Remote Operated Vehicle (ROV) / Autonomous Underwater Vehicle (AUV) system for the optical survey of marine archaeological sites, as well as a novel sonar image augmentation strategy for semantic segmentation of shipwrecks. This approach takes side-scan sonar and bathymetry data collected using an EdgeTech 2205 AUV sensor integrated with an Harris Iver3, and generates augmented image data to be used for the semantic segmentation of shipwrecks. It is shown that, due to the feature enhancement capabilities of the proposed shipwreck detection strategy, correctly identified areas have a 15% …

Go to article

Multi-Object Tracking: A Computer Vision Paradigm, Natalie Friede Aug 2023

Multi-Object Tracking: A Computer Vision Paradigm, Natalie Friede

Computer Science and Computer Engineering Undergraduate Honors Theses

This paper delves into advancements and hurdles encountered in multi-object tracking, a critical aspect of computer vision, with a special emphasis on 'referring understanding.' This technique integrates natural language queries into multi-object tracking tasks, thus broadening the scope for practical applications. The innovative referring multi-object tracking (RMOT) approach emerges as a promising solution in this regard. The effectiveness of RMOT was tested using the Refer-KITTI dataset, a dataset specializing in traffic scenes. The evaluation revealed RMOT's ability to handle a diverse range of referent objects, its robust temporal dynamics, and a high level of adaptability. While the paper acknowledges the …

Go to article

Smartbrush: Text And Shape Guided Object Inpainting With Diffusion Model, Shaoan Xie, Zhifei Zhang, Zhe Lin, Tobias Hinz, Kun Zhang Aug 2023

Smartbrush: Text And Shape Guided Object Inpainting With Diffusion Model, Shaoan Xie, Zhifei Zhang, Zhe Lin, Tobias Hinz, Kun Zhang

Machine Learning Faculty Publications

Generic image inpainting aims to complete a corrupted image by borrowing surrounding information, which barely generates novel content. By contrast, multi-modal inpainting provides more flexible and useful controls on the inpainted content, e.g., a text prompt can be used to describe an object with richer attributes, and a mask can be used to constrain the shape of the inpainted object rather than being only considered as a missing area. We propose a new diffusion-based model named SmartBrush for completing a missing region with an object using both text and shape-guidance. While previous work such as DALLE-2 and Stable Diffusion can …

Go to article

Towards Multi-Modal Explainable Video Understanding, Kashu Yamazaki Aug 2023

Towards Multi-Modal Explainable Video Understanding, Kashu Yamazaki

Graduate Theses and Dissertations

This thesis presents a novel approach to video understanding by emulating human perceptual processes and creating an explainable and coherent storytelling representation of video content. Central to this approach is the development of a Visual-Linguistic (VL) feature for an interpretable video representation and the creation of a Transformer-in-Transformer (TinT) decoder for modeling intra- and inter-event coherence in a video. Drawing inspiration from the way humans comprehend scenes by breaking them down into visual and non-visual components, the proposed VL feature models a scene through three distinct modalities. These include: (i) a global visual environment, providing a broad contextual understanding of …

Go to article

Accuracy Vs. Energy: An Assessment Of Bee Object Inference In Videos From On-Hive Video Loggers With Yolov3, Yolov4-Tiny, And Yolov7-Tiny, Vladimir A. Kulyukin, Aleksey V. Kulyukin Jul 2023

Accuracy Vs. Energy: An Assessment Of Bee Object Inference In Videos From On-Hive Video Loggers With Yolov3, Yolov4-Tiny, And Yolov7-Tiny, Vladimir A. Kulyukin, Aleksey V. Kulyukin

Computer Science Faculty and Staff Publications

A continuing trend in precision apiculture is to use computer vision methods to quantify characteristics of bee traffic in managed colonies at the hive's entrance. Since traffic at the hive's entrance is a contributing factor to the hive's productivity and health, we assessed the potential of three open-source convolutional network models, YOLOv3, YOLOv4-tiny, and YOLOv7-tiny, to quantify omnidirectional traffic in videos from on-hive video loggers on regular, unmodified one- and two-super Langstroth hives and compared their accuracies, energy efficacies, and operational energy footprints. We trained and tested the models with a 70/30 split on a dataset of 23,173 flying bees …

Go to article

Fine-Grained Domain Adaptive Crowd Counting Via Point-Derived Segmentation, Yongtuo Liu, Dan Xu, Sucheng Ren, Hanjie Wu, Hongmin Cai, Shengfeng He Jul 2023

Fine-Grained Domain Adaptive Crowd Counting Via Point-Derived Segmentation, Yongtuo Liu, Dan Xu, Sucheng Ren, Hanjie Wu, Hongmin Cai, Shengfeng He

Research Collection School Of Computing and Information Systems

Due to domain shift, a large performance drop is usually observed when a trained crowd counting model is deployed in the wild. While existing domain-adaptive crowd counting methods achieve promising results, they typically regard each crowd image as a whole and reduce domain discrepancies in a holistic manner, thus limiting further improvement of domain adaptation performance. To this end, we propose to untangle domain-invariant crowd and domain-specific background from crowd images and design a fine-grained domain adaption method for crowd counting. Specifically, to disentangle crowd from background, we propose to learn crowd segmentation from point-level crowd counting annotations in a …

Go to article

A Novel Driver Emotion Recognition System Based On Deep Ensemble Classification, Khalid Zaman, Sun Zhaoyun, Babar Shah, Tariq Hussain, Sayyed Mudassar Shah, Farman Ali, Umer Sadiq Khan Jun 2023

A Novel Driver Emotion Recognition System Based On Deep Ensemble Classification, Khalid Zaman, Sun Zhaoyun, Babar Shah, Tariq Hussain, Sayyed Mudassar Shah, Farman Ali, Umer Sadiq Khan

All Works

Driver emotion classification is an important topic that can raise awareness of driving habits because many drivers are overconfident and unaware of their bad driving habits. Drivers will acquire insight into their poor driving behaviors and be better able to avoid future accidents if their behavior is automatically identified. In this paper, we use different models such as convolutional neural networks, recurrent neural networks, and multi-layer perceptron classification models to construct an ensemble convolutional neural network-based enhanced driver facial expression recognition model. First, the faces of the drivers are discovered using the faster region-based convolutional neural network (R-CNN) model, which …

Go to article

Understanding Masked Autoencoders Via Hierarchical Latent Variable Models, Lingjing Kong, Martin Q. Ma, Guangyi Chen, Eric P. Xing, Yuejie Chi, Louis Philippe Morency, Kun Zhang Jun 2023

Understanding Masked Autoencoders Via Hierarchical Latent Variable Models, Lingjing Kong, Martin Q. Ma, Guangyi Chen, Eric P. Xing, Yuejie Chi, Louis Philippe Morency, Kun Zhang

Machine Learning Faculty Publications

Masked autoencoder (MAE), a simple and effective self-supervised learning framework based on the reconstruction of masked image regions, has recently achieved prominent success in a variety of vision tasks. Despite the emergence of intriguing empirical observations on MAE, a theoretically principled understanding is still lacking. In this work, we formally characterize and justify existing empirical in-sights and provide theoretical guarantees of MAE. We formulate the underlying data-generating process as a hierarchical latent variable model, and show that under reasonable assumptions, MAE provably identifies a set of latent variables in the hierarchical model, explaining why MAE can extract high-level information from …

Go to article

Curricular Contrastive Regularization For Physics-Aware Single Image Dehazing, Yu Zheng, Jiahui Zhan, Shengfeng He, Yong Du Jun 2023

Curricular Contrastive Regularization For Physics-Aware Single Image Dehazing, Yu Zheng, Jiahui Zhan, Shengfeng He, Yong Du

Research Collection School Of Computing and Information Systems

Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. However, the contrastive samples are non-consensual, as the negatives are usually represented distantly from the clear (i.e., positive) image, leaving the solution space still under-constricted. Moreover, the interpretability of deep dehazing models is underexplored towards the physics of the hazing process. In this paper, we propose a novel curricular contrastive regularization targeted at a consensual contrastive space as opposed to a non-consensual one. Our negatives, which provide better lower-bound constraints, can be assembled from 1) the hazy …

Go to article

Tree-Based Unidirectional Neural Networks For Low-Power Computer Vision, Abhinav Goel, Caleb Tung, Nick Eliopoulos, Amy Wang, Jamie C. Davis, George K. Thiruvathukal, Yung-Hisang Lu Jun 2023

Tree-Based Unidirectional Neural Networks For Low-Power Computer Vision, Abhinav Goel, Caleb Tung, Nick Eliopoulos, Amy Wang, Jamie C. Davis, George K. Thiruvathukal, Yung-Hisang Lu

Computer Science: Faculty Publications and Other Works

This article describes the novel Tree-based Unidirectional Neural Network (TRUNK) architecture. This architecture improves computer vision efficiency by using a hierarchy of multiple shallow Convolutional Neural Networks (CNNs), instead of a single very deep CNN. We demonstrate this architecture’s versatility in performing different computer vision tasks efficiently on embedded devices. Across various computer vision tasks, the TRUNK architecture consumes 65% less energy and requires 50% less memory than representative low-power CNN architectures, e.g., MobileNet v2, when deployed on the NVIDIA Jetson Nano.

Go to article

Novel Approach For Non-Invasive Prediction Of Body Shape And Habitus, Emma Young Jun 2023

Novel Approach For Non-Invasive Prediction Of Body Shape And Habitus, Emma Young

Electronic Theses and Dissertations

While marker-based motion capture remains the gold standard in measuring human movement, accuracy is influenced by soft-tissue artifacts, particularly for subjects with high body mass index (BMI) where markers are not placed close to the underlying bone. Obesity influences joint loads and motion patterns, and BMI may not be sufficient to capture the distribution of a subject’s weight or to differentiate differences between subjects. Subjects in need of a joint replacement are more likely to have mobility issues or pain, which prevents exercise. Obesity also increases the likelihood of needing a total joint replacement. Accurate movement data for subjects with …

Go to article

Where Is My Spot? Few-Shot Image Generation Via Latent Subspace Optimization, Chenxi Zheng, Bangzhen Liu, Huaidong Zhang, Xuemiao Xu, Shengfeng He Jun 2023

Where Is My Spot? Few-Shot Image Generation Via Latent Subspace Optimization, Chenxi Zheng, Bangzhen Liu, Huaidong Zhang, Xuemiao Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

Image generation relies on massive training data that can hardly produce diverse images of an unseen category according to a few examples. In this paper, we address this dilemma by projecting sparse few-shot samples into a continuous latent space that can potentially generate infinite unseen samples. The rationale behind is that we aim to locate a centroid latent position in a conditional StyleGAN, where the corresponding output image on that centroid can maximize the similarity with the given samples. Although the given samples are unseen for the conditional StyleGAN, we assume the neighboring latent subspace around the centroid belongs to …

Go to article

Deep Learning For Skin Photoaging, Gokul Srinivasan May 2023

Deep Learning For Skin Photoaging, Gokul Srinivasan

Computer Science Senior Theses

Skin photoaging is the premature aging of skin that results from ultraviolet light exposure. It is a major risk factor for the development of skin cancer, among other malignant skin pathologies. Accordingly, understanding its etiology is important for both preventative and reparative clinical action. In this study, skin samples obtained from patients with ranging solar elastosis grades – a proxy for skin photoaging – were sequenced using next-generation sequencing techniques to further understand the genomic, epigenomic, and histological signs and signals of skin photoaging. The results of this study suggest that tissues with severe photoaging exhibit increases in the frequency …

Go to article

Toward Digital Phenotyping: Human Activity Representation For Embodied Cognition Assessment, Mohammad Zakizadehghariehali May 2023

Toward Digital Phenotyping: Human Activity Representation For Embodied Cognition Assessment, Mohammad Zakizadehghariehali

Computer Science and Engineering Dissertations - Archive

Cognition is the mental process of acquiring knowledge and understanding through thought, experience and senses. Based on Embodied Cognition theory, physical activities are an important manifestation of cognitive functions. As a result, they can be employed to both assess and train cognitive skills. In order to assess various cognitive measures, the ATEC system has been proposed. It consists of physical exercises with different variations and difficulty levels, designed to provide assessment of executive and motor functions. This thesis focuses on obtaining human activity representation from recorded videos of ATEC tasks in order to automatically assess embodied cognition performance. Representation learning …

Go to article

Bubbleu: Exploring Augmented Reality Game Design With Uncertain Ai-Based Interaction, Minji Kim, Kyungjin Lee, Rajesh Krishna Balan, Youngki Lee Apr 2023

Bubbleu: Exploring Augmented Reality Game Design With Uncertain Ai-Based Interaction, Minji Kim, Kyungjin Lee, Rajesh Krishna Balan, Youngki Lee

Research Collection School Of Computing and Information Systems

Object detection, while being an attractive interaction method for Augmented Reality (AR), is fundamentally error-prone due to the probabilistic nature of the underlying AI models, resulting in sub-optimal user experiences. In this paper, we explore the effect of three game design concepts, Ambiguity, Transparency, and Controllability, to provide better gameplay experiences in AR games that use error-prone object detection-based interaction modalities. First, we developed a base AR pet breeding game, called Bubbleu that uses object detection as a key interaction method. We then implemented three different variants, each according to the three concepts, to investigate the impact of each design …

Go to article

Using Embedded Systems And Augmented Reality For Automated Aerial Refueling, Nathaniel A. Wilson Mar 2023

Using Embedded Systems And Augmented Reality For Automated Aerial Refueling, Nathaniel A. Wilson

Theses and Dissertations

The goal of automated aerial refueling (AAR) is to extend the range of unmanned aircraft. Control latency prevents a human from remotely controlling the receiving aircraft as it approaches a tanker. To conform with the size, weight, and power constraints of a small unmanned aircraft, an AAR system must execute in real-time on an embedded platform. This thesis explores the timing and computational performance of a NVIDIA Jetson AGX Orin to a state-of-the-art general-purpose computer using existing AAR algorithms. It also constructs an augmented reality framework as an intermediate step for testing vision-based AAR algorithms between virtual testing and expensive …

Go to article

Real-Time Face Mask Detection And Recognition For Video Surveillance Using Deep Learning Approach, Ehsan Nasiri Feb 2023

Real-Time Face Mask Detection And Recognition For Video Surveillance Using Deep Learning Approach, Ehsan Nasiri

Theses and Dissertations

Facial recognition refers to the determination of identity of an individual based on facial features. The application of facial recognition has been widely used for the purpose of security. The outbreak of coronavirus has made people wear masks as a preventive measure. However, this affects the proper identification of individuals resulting in several security threats. In this paper, the issues related to recognition of both masked and unmasked faces are mitigated and an approach for accurate detection of face masks and recognition of both masked and unmasked faces is Introduced. The proposed approach comprises several processes which are carried out …

Go to article

Motif Mining: Finding And Summarizing Remixed Image Content, William Theisen, Daniel Gonzalez Cedre, Zachariah Carmichael, Daniel Moreira, Tim Weninger, Walter Scheirer Feb 2023

Motif Mining: Finding And Summarizing Remixed Image Content, William Theisen, Daniel Gonzalez Cedre, Zachariah Carmichael, Daniel Moreira, Tim Weninger, Walter Scheirer

Computer Science: Faculty Publications and Other Works

On the Internet, images are no longer static; they have become dynamic content. Thanks to the availability of smartphones with cameras and easy-to-use editing software, images can be remixed (i.e., redacted, edited, and re-combined with other content) on-the-fly, allowing a world-wide audience to repeat the process many times. From digital art to memes, the evolution of images through time is now an important topic of study for digital humanists, social scientists, and media forensics specialists. However, because typical data sets in computer vision are composed of static content, there has been limited development of automated algorithms for analyzing remixed content. …

Go to article

Pose- And Attribute-Consistent Person Image Synthesis, Cheng Xu, Zejun Chen, Jiajie Mai, Xuemiao Xu, Shengfeng He Feb 2023

Pose- And Attribute-Consistent Person Image Synthesis, Cheng Xu, Zejun Chen, Jiajie Mai, Xuemiao Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

PersonImageSynthesisaimsattransferringtheappearanceofthesourcepersonimageintoatargetpose. Existingmethods cannot handle largeposevariations and therefore suffer fromtwocritical problems: (1)synthesisdistortionduetotheentanglementofposeandappearanceinformationamongdifferentbody componentsand(2)failureinpreservingoriginalsemantics(e.g.,thesameoutfit).Inthisarticle,weexplicitly addressthesetwoproblemsbyproposingaPose-andAttribute-consistentPersonImageSynthesisNetwork (PAC-GAN).Toreduceposeandappearancematchingambiguity,weproposeacomponent-wisetransferring modelconsistingoftwostages.Theformerstagefocusesonlyonsynthesizingtargetposes,whilethelatter renderstargetappearancesbyexplicitlytransferringtheappearanceinformationfromthesourceimageto thetargetimageinacomponent-wisemanner. Inthisway,source-targetmatchingambiguityiseliminated duetothecomponent-wisedisentanglementofposeandappearancesynthesis.Second,tomaintainattribute consistency,werepresenttheinputimageasanattributevectorandimposeahigh-levelsemanticconstraint usingthisvectortoregularizethetargetsynthesis.ExtensiveexperimentalresultsontheDeepFashiondataset demonstratethesuperiorityofourmethodoverthestateoftheart,especiallyformaintainingposeandattributeconsistenciesunderlargeposevariations.

Go to article

Towards A Framework For Privacy-Preserving Pedestrian Analysis, Anil Kunchala, Mélanie Bouroche, Bianca Schoen-Phelan Jan 2023

Towards A Framework For Privacy-Preserving Pedestrian Analysis, Anil Kunchala, Mélanie Bouroche, Bianca Schoen-Phelan

Conference papers

The design of pedestrian-friendly infrastructures plays a crucial role in creating sustainable transportation in urban environments. Analyzing pedestrian behaviour in response to existing infrastructure is pivotal to planning, maintaining, and creating more pedestrian-friendly facilities. Many approaches have been proposed to extract such behaviour by applying deep learning models to video data. Video data, however, includes an broad spectrum of privacy-sensitive information about individuals, such as their location at a given time or who they are with. Most of the existing models use privacy-invasive methodologies to track, detect, and analyse individual or group pedestrian behaviour patterns. As a step towards privacy-preserving …

Go to article

A Multistage Framework For Detection Of Very Small Objects, Duleep Rathgamage Don, Ramazan Aygun, Mahmut Karakaya Jan 2023

A Multistage Framework For Detection Of Very Small Objects, Duleep Rathgamage Don, Ramazan Aygun, Mahmut Karakaya

Published and Grey Literature from PhD Candidates

Small object detection is one of the most challenging problems in computer vision. Algorithms based on state-of-the-art object detection methods such as R-CNN, SSD, FPN, and YOLO fail to detect objects of very small sizes. In this study, we propose a novel method to detect very small objects, smaller than 8×8 pixels, that appear in a complex background. The proposed method is a multistage framework consisting of an unsupervised algorithm and three separately trained supervised algorithms. The unsupervised algorithm extracts ROIs from a high-resolution image. Then the ROIs are upsampled using SRGAN, and the enhanced ROIs are detected by our …

Go to article

Accelerating Precision Station Keeping For Automated Aircraft, James D. Anderson Jan 2023

Accelerating Precision Station Keeping For Automated Aircraft, James D. Anderson

Browse all Theses and Dissertations

Automated vehicles pose challenges in various research domains, including robotics, machine learning, computer vision, public safety, system certification, and beyond. These vehicles autonomously handle navigation and locomotion, often requiring minimal user interaction, and can operate on land, in water, or in the air. In the context of aircraft, one specific application is Automated Aerial Refueling (AAR). Traditional aerial refueling involves a "tanker" aircraft using a mechanism, such as a rigid boom arm or a flexible hose, to transfer fuel to another aircraft designated as the "receiver". For AAR, the boom arm may be maneuvered automatically, or in certain instances the …

Go to article

Evolution Of Winning Solutions In The 2021 Low-Power Computer Vision Challenge, Xiao Hu, Ziteng Jiao, Ayden Kocher, Zhenyu Wu, Junjie Liu, James C. Davis, George K. Thiruvathukal, Yung-Hsiang Lu Jan 2023

Evolution Of Winning Solutions In The 2021 Low-Power Computer Vision Challenge, Xiao Hu, Ziteng Jiao, Ayden Kocher, Zhenyu Wu, Junjie Liu, James C. Davis, George K. Thiruvathukal, Yung-Hsiang Lu

Computer Science: Faculty Publications and Other Works

Mobile and embedded devices are becoming ubiquitous. Applications such as rescue with autonomous robots and event analysis on traffic cameras rely on devices with limited power supply and computational sources. Thus, the demand for efficient computer vision algorithms increases. Since 2015, we have organized the IEEE Low-Power Computer Vision Challenge to advance the state of the art in low-power computer vision. We describe the competition organizing details including the challenge design, the reference solution, the dataset, the referee system, and the evolution of the solutions from two winning teams. We examine the winning teams’ development patterns and design decisions, focusing …

Go to article

First Prev Next Last