Engineering Commons^™

On Action Quality Assessment, Paritosh Parmar

UNLV Theses, Dissertations, Professional Papers, and Capstones

In this dissertation, we tackle the task of quantifying the quality of actions, i.e., how well an

action was performed using computer vision. Existing methods used human body pose-based features to express the quality contained in an action sample. Human body pose estimation in actions such as sports actions, like diving and gymnastic vault, is particularly challenging, since the athletes undergo convoluted transformations while performing their routines. Moreover, pose-based features do not take into account visual cues such as water splash in diving. Visual cues are taken into account by human judges. In our first work, we show that using …

An Application Of Deep Learning Models To Automate Food Waste Classification, Alejandro Zachary Espinoza

Dissertations and Theses

Food wastage is a problem that affects all demographics and regions of the world. Each year, approximately one-third of food produced for human consumption is thrown away. In an effort to track and reduce food waste in the commercial sector, some companies utilize third party devices which collect data to analyze individual contributions to the global problem. These devices track the type of food wasted (such as vegetables, fruit, boneless chicken, pasta) along with the weight. Some devices also allow the user to leave the food in a kitchen container while it is weighed, so the container weight must also …

Amodal Instance Segmentation And Multi-Object Tracking With Deep Pixel Embedding, Yanfeng Liu

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

This thesis extends upon the representational output of semantic instance segmentation by explicitly including both visible and occluded parts. A fully convolutional network is trained to produce consistent pixel-level embedding across two layers such that, when clustered, the results convey the full spatial extent and depth ordering of each instance. Results demonstrate that the network can accurately estimate complete masks in the presence of occlusion and outperform leading top-down bounding-box approaches.

The model is further extended to produce consistent pixel-level embeddings across two consecutive image frames from a video to simultaneously perform amodal instance segmentation and multi-object tracking. No post-processing …

Height Measurement Of Basil Crops For Smart Irrigation Applications In Greenhouses Using Commercial Sensors, Leila Bahman

Electronic Thesis and Dissertation Repository

Plant height is a key phenotypic attribute that directly represents how well a plant grows. It can also be a useful parameter in computing other important features such as yield and biomass. As the number of greenhouses increase, the traditional method of measuring plant height requires more time and labor, which increases demand for developing a reliable and affordable method to perform automated height measurements of plants. This research is aimed to develop a solution to automatically measure plant height in greenhouses using low cost sensors and computer vision techniques. For this purpose, the performance of various depth sensing technologies …

Emotion Recognition Using Facial Feature Extraction, Demiyan Smirnov

Theses and Dissertations

Computerized emotion recognition systems can be powerful tools to help solve problems in a wide range of fields including education, healthcare, and marketing. Existing systems use digital images or live video to track facial expressions on a person's face and deduce that person's emotional state. The research presented in this thesis explores combinations of several facial feature extraction techniques with different classifier algorithms. Namely, the feature extraction techniques used in this research were Discrete Cosine/Sine Transforms, Fast Walsh-Hadamard Transform, Principle Component Analysis, and a novel method called XPoint. Features were extracted from both global (using the entire facial image) and …

Approximate Pattern Matching Using Hierarchical Graph Construction And Sparse Distributed Representation, Aakanksha Mathuria, Dan Hammerstrom

Electrical and Computer Engineering Faculty Publications and Presentations

With recent developments in deep networks, there have been significant advances in visual object detection and recognition. However, some of these networks are still easily fooled/hacked and have shown “bag of features” failures. Some of this is due to the fact that even deep networks make only marginal use of the complex structure that exists in real-world images, even after training on huge numbers of images. Biology appears to take advantage of such a structure, but how? In our research, we are studying approaches for robust pattern matching using still, 2D Blocks World images based on graphical representations of the …

The Applications Of Grid Cells In Computer Vision, Keaton Kraiger

Undergraduate Research & Mentoring Program

In this study we present a novel method for position and scale invariant object representation based on a biologically-inspired framework. Grid cells are neurons in the entorhinal cortex whose multiple firing locations form a periodic triangular array, tiling the surface of an animal’s environment. We propose a model for simple object representation that maintains position and scale invariance, in which grid maps capture the fundamental structure and features of an object. The model provides a mechanism for identifying feature locations in a Cartesian plane and vectors between object features encoded by grid cells. It is shown that key object features …

Infrared And Electro-Optical Stereo Vision For Automated Aerial Refueling, William E. Dallmann

Theses and Dissertations

Currently, Unmanned Aerial Vehicles are unsafe to refuel in-flight due to the communication latency between the UAVs ground operator and the UAV. Providing UAVs with an in-flight refueling capability would improve their functionality by extending their flight duration and increasing their flight payload. Our solution to this problem is Automated Aerial Refueling (AAR) using stereo vision from stereo electro-optical and infrared cameras on a refueling tanker. To simulate a refueling scenario, we use ground vehicles to simulate a pseudo tanker and pseudo receiver UAV. Imagery of the receiver is collected by the cameras on the tanker and processed by a …

American Sign Language Recognition Using Machine Learning And Computer Vision, Kshitij Bantupalli, Ying Xie

Master of Science in Computer Science Theses

Speech impairment is a disability which affects an individual’s ability to communicate using speech and hearing. People who are affected by this use other media of communication such as sign language. Although sign language is ubiquitous in recent times, there remains a challenge for non-sign language speakers to communicate with sign language speakers or signers. With recent advances in deep learning and computer vision there has been promising progress in the fields of motion and gesture recognition using deep learning and computer vision-based techniques. The focus of this work is to create a vision-based application which offers sign language translation …

Weld Penetration Identification Based On Convolutional Neural Network, Chao Li

Theses and Dissertations--Electrical and Computer Engineering

Weld joint penetration determination is the key factor in welding process control area. Not only has it directly affected the weld joint mechanical properties, like fatigue for example. It also requires much of human intelligence, which either complex modeling or rich of welding experience. Therefore, weld penetration status identification has become the obstacle for intelligent welding system. In this dissertation, an innovative method has been proposed to detect the weld joint penetration status using machine-learning algorithms.

A GTAW welding system is firstly built. Project a dot-structured laser pattern onto the weld pool surface during welding process, the reflected laser pattern …

Multi-Pig Part Detection And Association With A Fully-Convolutional Network, Eric T. Psota, Mateusz Mittek, Lance C. Pérez, Ty Schmidt, Benny Mote

Department of Electrical and Computer Engineering: Faculty Publications

Computer vision systems have the potential to provide automated, non-invasive monitoring of livestock animals, however, the lack of public datasets with well-defined targets and evaluation metrics presents a significant challenge for researchers. Consequently, existing solutions often focus on achieving task-specific objectives using relatively small, private datasets. This work introduces a new dataset and method for instance-level detection of multiple pigs in group-housed environments. The method uses a single fully-convolutional neural network to detect the location and orientation of each animal, where both body part locations and pairwise associations are represented in the image space. Accompanying this method is a new …

Improving Unsupervised Learning With Exemplar Cnns, Eric Arazo, Noel E. O'Connor, Kevin Mcguinness

Session 3: Deep Learning for Computer Vision

Most recent unsupervised learning methods explore alternative objectives, often referred to as self-supervised tasks, to train convolutional neural networks without the supervision of human annotated labels. This paper explores the generation of surrogate classes as a self-supervised alternative to learn discriminative features, and proposes a clustering algorithm to overcome one of the main limitations of this kind of approach. Our clustering technique improves the initial implementation and achieves 76.4% accuracy in the STL-10 test set, surpassing the current state-ofthe- art for the STL-10 unsupervised benchmark. We also explore several issues with the unlabeled set from STL-10 that should be considered …

Depth Enhancement And Surface Reconstruction With Rgb/D Sequence, Xinxin Zuo

Theses and Dissertations--Computer Science

Surface reconstruction and 3D modeling is a challenging task, which has been explored for decades by the computer vision, computer graphics, and machine learning communities. It is fundamental to many applications such as robot navigation, animation and scene understanding, industrial control and medical diagnosis. In this dissertation, I take advantage of the consumer depth sensors for surface reconstruction. Considering its limited performance on capturing detailed surface geometry, a depth enhancement approach is proposed in the first place to recovery small and rich geometric details with captured depth and color sequence. In addition to enhancing its spatial resolution, I present a …

Applied Deep Learning In Orthopaedics, William Stewart Burton Ii

Electronic Theses and Dissertations

The reemergence of deep learning in recent years has led to its successful application in a wide variety of fields. As a subfield of machine learning, deep learning offers an array of powerful algorithms for data-driven applications. Orthopaedics stands to benefit from the potential of deep learning for advancements in the field. This thesis investigated applications of deep learning for the field of orthopaedics through the development of three distinct projects.

First, algorithms were developed for the automatic segmentation of the structures in the knee from MRI. The resulting algorithms can be used to accurately segment full MRI scans in …

Elimination Of Useless Images From Raw Camera-Trap Data, Ulaş Tekeli̇, Yalin Baştanlar

Turkish Journal of Electrical Engineering and Computer Sciences

Camera-traps are motion triggered cameras that are used to observe animals in nature. The number of images collected from camera-traps has increased significantly with the widening use of camera-traps thanks to advances in digital technology. A great workload is required for wild-life researchers to group and label these images. We propose a system to decrease the amount of time spent by the researchers by eliminating useless images from raw camera-trap data. These images are too bright, too dark, blurred, or they contain no animals. To eliminate bright, dark, and blurred images we employ techniques based on image histograms and fast …

Recognition Of Incomplete Objects Based On Synthesis Of Views Using A Geometric Based Local-Global Graphs, Michael Christopher Robbeloth

Browse all Theses and Dissertations

The recognition of single objects is an old research field with many techniques and robust results. The probabilistic recognition of incomplete objects, however, remains an active field with challenging issues associated to shadows, illumination and other visual characteristics. With object incompleteness, we mean missing parts of a known object and not low-resolution images of that object. The employment of various single machine-learning methodologies for accurate classification of the incomplete objects did not provide a robust answer to the challenging problem. In this dissertation, we present a suite of high-level, model-based computer vision techniques encompassing both geometric and machine learning approaches …