Indiana University-Purdue University Indianapolis (IUPUI) / An RGBZ synthetic dataset consisting of five object classes in a variety of virtual environments and orientations was combined with a small sample of real-world image data and used to train the Mask R-CNN (MR-CNN) architecture in a variety of configurations. When the MR-CNN architecture was initialized with MS COCO weights and the heads were trained with a mix of synthetic data and real world data, F1 scores improved in four of the five classes: The average maximum F1-score of all classes and all epochs for the networks trained with synthetic data is F1∗ = 0.91, compared to F1 = 0.89 for the networks trained exclusively with real data, and the standard deviation of the maximum mean F1-score for synthetically trained networks is σ∗ = 0.015, compared to σ_F1 = 0.020 for the networks trained exclusively with real F1 data. Various backgrounds in synthetic data were shown to have negligible impact on F1 scores, opening the door to abstract backgrounds and minimizing the need for intensive synthetic data fabrication. When the MR-CNN architecture was initialized with MS COCO weights and depth data was included in the training data, the net- work was shown to rely heavily on the initial convolutional input to feed features into the network, the image depth channel was shown to influence mask generation, and the image color channels were shown to influence object classification. A set of latent variables for a subset of the synthetic datatset was generated with a Variational Autoencoder then analyzed using Principle Component Analysis and Uniform Manifold Projection and Approximation (UMAP). The UMAP analysis showed no meaningful distinction between real-world and synthetic data, and a small bias towards clustering based on image background.

In this master thesis, object's detection in image and tracking these objects in temporal area will be presented. First, theoretical background of the image's preprocessing, image filtration, the foreground extraction, and many others various image's features will be described. Next, design and implementation of detector will be processed. This part of my master thesis containes mainly information about detection of objects on belt conveyer Finally,results, conclusion and many supplementary data such as a photography camera's location will be shown.

This master's thesis is engaged in machine vision, methods of image processing and analysis. The reason is to create application to determine relative positions of Trilobot robots in the laboratory.

<p>Imaging and computer vision systems deployed in real-world environments face the challenge of accommodating a wide range of lighting conditions. However, the cost, the demand for high resolution, and the miniaturization of imaging devices impose physical constraints on sensor design, limiting both the dynamic range and effective aperture size of each pixel. Consequently, conventional CMOS sensors fail to deliver satisfactory capture in high dynamic range scenes or under photon-limited conditions, thereby impacting the performance of downstream vision tasks. In this thesis, we address two key problems: 1) exploring the utilization of spatial multiplexing, specifically spatially varying exposure tiling, to extend sensor dynamic range and optimize scene capture, and 2) developing techniques to enhance the robustness of object detection systems under photon-limited conditions.</p> <p><br></p> <p>In addition to challenges imposed by natural environments, real-world vision systems are susceptible to adversarial attacks in the form of artificially added digital content. Therefore, this thesis presents a comprehensive pipeline for constructing a robust and scalable system to counter such attacks.</p>

No description available.

This degree project proposes the design and the implementation of a novel systemfor deep analysis on large-scale datasets of hand poses. The system consists of a set ofmodules for automatic redundancy removal, classification, statistical analysis andvisualization of large-scale datasets based on their content characteristics. In thisproject, work is performed on the specific use case of images of hand movements infront of smartphone cameras. The characteristics of the images are investigated, andthe images are pre-processed to reduce repetitive content and noise in the data. Twodifferent design paradigms for content analysis and image classification areemployed, a computer vision pipeline and a deep learning pipeline. The computervision pipeline incorporates several stages of image processing including imagesegmentation, hand detection as well as feature extraction followed by a classificationstage. The deep learning pipeline utilizes a convolutional neural network forclassification. For industrial applications with high diversity on data content, deeplearning is suggested for image classification and computer vision is recommendedfor feature analysis. Finally, statistical analysis is performed to visually extractrequired information about hand features and diversity of the classified data. Themain contribution of this work lies in the customization of computer vision and deeplearning tools for the design and the implementation of a hybrid system for deep dataanalysis. / Detta examensprojekt föreslår design och implementering av ett nytt system för djup analys av storskaliga datamängder av handställningar. Systemet består av en uppsättning moduler för automatisk borttagning av redundans, klassificering, statistisk analys och visualisering av storskaliga dataset baserade på deras egenskaper. I det här projektet utförs arbete på det specifika användningsområdet för bilder av handrörelser framför smarttelefonkameror. Egenskaperna hos bilderna undersöks, och bilderna förbehandlas för att minska repetitivt innehåll och ljud i data. Två olika designparadigmer för innehållsanalys och bildklassificering används, en datorvisionspipeline och en djuplärningsrörledning. Datasynsrörledningen innehåller flera steg i bildbehandling, inklusive bildsegmentering, handdetektering samt funktionen extraktion följt av ett klassificeringssteg. Den djupa inlärningsrörledningen använder ett fällningsnätverk för klassificering. För industriella applikationer med stor mångfald på datainnehåll föreslås djupinlärning för bildklassificering och vision rekommenderas för funktionsanalys. Slutligen utförs statistisk analys för att visuellt extrahera nödvändig information om handfunktioner och mångfald av klassificerade data. Huvuddelen av detta arbete ligger i anpassningen av datasyn och djupa inlärningsverktyg för design och implementering av ett hybridsystem för djup dataanalys.

Thermals are regions of rising hot air formed on the ground through the warming of the surface by the sun. Thermals are commonly used by birds and glider pilots to extend flight duration, increase cross-country distance, and conserve energy. This kind of powerless flight using natural sources of lift is called soaring. Once a thermal is encountered, the pilot flies in circles to keep within the thermal, so gaining altitude before flying off to the next thermal and towards the destination. A single thermal can net a pilot thousands of feet of elevation gain, however estimating thermal locations is not an easy task. Pilots look for different indicators: color variation on the ground because the difference in the amount of heat absorbed by the ground varies based on the color/composition, birds circling in an area gaining lift, and certain types of cloud formations (cumulus clouds). The above methods are not always reliable enough and pilots study the weather for thermals by estimating solar heating of the ground using cloud cover and time of year and the lapse rate and dew point of the troposphere. In this paper, we present a Machine Learning based solution for assisting in forecasting thermals. We created a custom dataset using flight data recorded and uploaded to public databases by soaring pilots. We determine where and when the pilot encountered thermals to pull weather and satellite images corresponding to the location and time of the flight. Using this dataset we train an algorithm to automatically predict the location of thermals given as input the current weather conditions and terrain information obtained from Google Earth Engine and thermal regions encountered as truth labels. We were able to converge very well on the training and validation set, proving our method with around a 0.98 F1 score. These results indicate success in creating a custom dataset and a powerful neural network with the necessity of bolstering our custom dataset.

The increasing size and complexity of datasets have accelerated the development of machine learning models and exposed the need for more scalable solutions. This thesis explores challenges associated with large-scale machine learning under data privacy constraints. With the growth of machine learning models, traditional privacy methods such as data anonymization are becoming insufficient. Thus, we delve into alternative approaches, such as differential privacy. Our research addresses the following core areas in the context of scalable privacy-preserving machine learning: First, we examine the implications of data dimensionality on privacy for the application of medical image analysis. We extend the classification algorithm Private Aggregation of Teacher Ensembles (PATE) to deal with high-dimensional labels, and demonstrate that dimensionality reduction can be used to improve privacy. Second, we consider the impact of hyperparameter selection on privacy. Here, we propose a novel adaptive technique for hyperparameter selection in differentially gradient-based optimization. Third, we investigate sampling-based solutions to scale differentially private machine learning to dataset with a large number of records. We study the privacy-enhancing properties of importance sampling, highlighting that it can outperform uniform sub-sampling not only in terms of sample efficiency but also in terms of privacy. The three techniques developed in this thesis improve the scalability of machine learning while ensuring robust privacy protection, and aim to offer solutions for the effective and safe application of machine learning in large datasets. / Den ständigt ökande storleken och komplexiteten hos datamängder har accelererat utvecklingen av maskininlärningsmodeller och gjort behovet av mer skalbara lösningar alltmer uppenbart. Den här avhandlingen utforskar tre utmaningar förknippade med storskalig maskininlärning under dataskyddskrav. För stora och komplexa maskininlärningsmodeller blir traditionella metoder för integritet, såsom datananonymisering, otillräckliga. Vi undersöker därför alternativa tillvägagångssätt, såsom differentiell integritet. Vår forskning behandlar följande utmaningar inom skalbar och integitetsmedveten maskininlärning: För det första undersöker vi hur hög data-dimensionalitet påverkar integriteten för medicinsk bildanalys. Vi utvidgar klassificeringsalgoritmen Private Aggregation of Teacher Ensembles (PATE) för att hantera högdimensionella etiketter och visar att dimensionsreducering kan användas för att förbättra integriteten. För det andra studerar vi hur valet av hyperparametrar påverkar integriteten. Här föreslår vi en ny adaptiv teknik för val av hyperparametrar i gradient-baserad optimering med garantier på differentiell integritet. För det tredje granskar vi urvalsbaserade lösningar för att skala differentiellt privat maskininlärning till stora datamängder. Vi studerar de integritetsförstärkande egenskaperna hos importance sampling och visar att det kan överträffa ett likformigt urval av sampel, inte bara när det gäller effektivitet utan även för integritet. De tre teknikerna som utvecklats i denna avhandling förbättrar skalbarheten för integritetsskyddad maskininlärning och syftar till att erbjuda lösningar för effektiv och säker tillämpning av maskininlärning på stora datamängder. / <p>QC 20231101</p>

The use of uncrewed aerial vehicle to map the environment increased significantly in the last decade enabling a finer assessment of the land cover. However, creating accurate maps of the environment is still a complex and costly task. Deep learning (DL) is a new generation of artificial neural network research that, combined with remote sensing techniques, allows a refined understanding of our environment and can help to solve challenging land cover mapping issues. This research focuses on the vegetation segmentation of kettle holes. Kettle holes are small, pond-like, depressional wetlands. Quantifying the vegetation present in this environment is essential to assess the biodiversity and the health of the ecosystem. A machine learning workflow has been developed, integrating a superpixel segmentation algorithm to build a robust dataset, which is followed by a set of DL architectures to classify 10 plant classes present in kettle holes. The best architecture for this task was Xception, which achieved an average F1-score of 85% in the segmentation of the species. The application of solely 318 samples per class enabled a successful mapping in the complex wetland environment, indicating an important direction for future health assessments in such landscapes.

3D environment reconstruction has received great interest in recent years in areas such as city planning, virtual tourism and flood hazard warning. With the rapid development of computer technologies, it has become possible and necessary to develop new methodologies and techniques for real time simulation for virtual environments applications. This thesis proposes a novel dynamic simulation scheme for flood hazard warning. The work consists of three main parts: digital terrain modelling; 3D environmental reconstruction and system development; flood simulation models. The digital terrain model is constructed using real world measurement data of GIS, in terms of digital elevation data and satellite image data. An NTSP algorithm is proposed for very large data assessing, terrain modelling and visualisation. A pyramidal data arrangement structure is used for dealing with the requirements of terrain details with different resolutions. The 3D environmental reconstruction system is made up of environmental image segmentation for object identification, a new shape match method and an intelligent reconstruction system. The active contours-based multi-resolution vector-valued framework and the multi-seed region growing method are both used for extracting necessary objects from images. The shape match method is used with a template in the spatial domain for a 3D detailed small scale urban environment reconstruction. The intelligent reconstruction system is designed to recreate the whole model based on specific features of objects for large scale environment reconstruction. This study then proposes a new flood simulation scheme which is an important application of the 3D environmental reconstruction system. Two new flooding models have been developed. The first one is flood spreading model which is useful for large scale flood simulation. It consists of flooding image spatial segmentation, a water level calculation process, a standard gradient descent method for energy minimization, a flood region search and a merge process. The finite volume hydrodynamic model is built from shallow water equations which is useful for urban area flood simulation. The proposed 3D urban environment reconstruction system was tested on our simulation platform. The experiment results indicate that this method is capable of dealing with complicated and high resolution region reconstruction which is useful for many applications. When testing the 3D flood simulation system, the simulation results are very close to the real flood situation, and this method has faster speed and greater accuracy of simulating the inundation area in comparison to the conventional flood simulation models