Browsing by Subject "3D"

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Advancing 3D Digitization for Libraries, Museums, and Archives
    (Lyrasis, 2018-08-28) Johnson, Jennifer; Miller, Derek; Palmer, Kristi L.
    Digitizing collections has become a standard practice for libraries, museums, and archives. These collections include flat objects, photographs, negatives, microfilm, audio and video materials. Utilizing established workflows and best practices, these collections are easily accessible through content management systems and shareable through standardized metadata and exchange protocols, exemplified by the success of the Digital Public Library of America (DPLA). While the digitization of 2D objects continues, affordable 3D technologies are advancing opportunities for the same institutions to consider including 3D objects in their digital collections. The IUPUI University Library Center for Digital Scholarship is working towards a like basis of standards for scanned 3D artifacts in and incorporating those standards into current digital initiatives.
  • Thumbnail Image
    Item
    Enhancing Precision of Object Detectors: Bridging Classification and Localization Gaps for 2D and 3D Models
    (2024-05) Ravi, Niranjan; El-Sharkawy, Mohamed; Rizkalla, Maher E.; Li, Lingxi; King, Brian S.
    Artificial Intelligence (AI) has revolutionized and accelerated significant advancements in various fields such as healthcare, finance, education, agriculture and the development of autonomous vehicles. We are rapidly approaching Level 5 Autonomy due to recent developments in autonomous technology, including self-driving cars, robot navigation, smart traffic monitoring systems, and dynamic routing. This success has been made possible due to Deep Learning technologies and advanced Computer Vision (CV) algorithms. With the help of perception sensors such as Camera, LiDAR and RADAR, CV algorithms enable a self-driving vehicle to interact with the environment and make intelligent decisions. Object detection lays the foundations for various applications, such as collision and obstacle avoidance, lane detection, pedestrian and vehicular safety, and object tracking. Object detection has two significant components: image classification and object localization. In recent years, enhancing the performance of 2D and 3D object detectors has spiked interest in the research community. This research aims to resolve the drawbacks associated with localization loss estimation of 2D and 3D object detectors by addressing the bounding box regression problem, addressing the class imbalance issue affecting the confidence loss estimation, and finally proposing a dynamic cross-model 3D hybrid object detector with enhanced localization and confidence loss estimation. This research aims to address challenges in object detectors through four key contributions. In the first part, we aim to address the problems associated with the image classification component of 2D object detectors. Class imbalance is a common problem associated with supervised training. Common causes are noisy data, a scene with a tiny object surrounded by background pixels, or a dense scene with too many objects. These scenarios can produce many negative samples compared to positive ones, affecting the network learning and reducing the overall performance. We examined these drawbacks and proposed an Enhanced Hard Negative Mining (EHNM) approach, which utilizes anchor boxes with 20% to 50% overlap and positive and negative samples to boost performance. The efficiency of the proposed EHNM was evaluated using Single Shot Multibox Detector (SSD) architecture on the PASCAL VOC dataset, indicating that the detection accuracy of tiny objects increased by 3.9% and 4% and the overall accuracy improved by 0.9%. To address localization loss, our second approach investigates drawbacks associated with existing bounding box regression problems, such as poor convergence and incorrect regression. We analyzed various cases, such as when objects are inclusive of one another, two objects with the same centres, two objects with the same centres and similar aspect ratios. During our analysis, we observed existing intersections over Union (IoU) loss and its variant’s failure to address them. We proposed two new loss functions, Improved Intersection Over Union (IIoU) and Balanced Intersection Over Union (BIoU), to enhance performance and minimize computational efforts. Two variants of the YOLOv5 model, YOLOv5n6 and YOLOv5s, were utilized to demonstrate the superior performance of IIoU on PASCAL VOC and CGMU datasets. With help of ROS and NVIDIA’s devices, inference speed was observed in real-time. Extensive experiments were performed to evaluate the performance of BIoU on object detectors. The evaluation results indicated MASK_RCNN network trained on the COCO dataset, YOLOv5n6 network trained on SKU-110K and YOLOv5x trained on the custom e-scooter dataset demonstrated 3.70% increase on small objects, 6.20% on 55% overlap and 9.03% on 80% overlap. In the earlier parts, we primarily focused on 2D object detectors. Owing to its success, we extended the scope of our research to 3D object detectors in the later parts. The third portion of our research aims to solve bounding box problems associated with 3D rotated objects. Existing axis-aligned loss functions suffer a performance gap if the objects are rotated. We enhanced the earlier proposed IIoU loss by considering two additional parameters: the objects’ Z-axis and rotation angle. These two parameters aid in localizing the object in 3D space. Evaluation was performed on LiDAR and Fusion methods on 3D KITTI and nuScenes datasets. Once we addressed the drawbacks associated with confidence and localization loss, we further explored ways to increase the performance of cross-model 3D object detectors. We discovered from previous studies that perception sensors are volatile to harsh environmental conditions, sunlight, and blurry motion. In the final portion of our research, we propose a hybrid 3D cross-model detection network (MAEGNN) equipped with MaskedAuto Encoders (MAE) and Graph Neural Networks (GNN) along with earlier proposed IIoU and ENHM. The performance evaluation on MAEGNN on the KITTI validation dataset and KITTI test set yielded a detection accuracy of 69.15%, 63.99%, 58.46% and 40.85%, 37.37% on 3D pedestrians with overlap of 50%. This developed hybrid detector overcomes the challenges of localization error and confidence estimation and outperforms many state-of-art 3D object detectors for autonomous platforms.
  • Thumbnail Image
    Item
    Estimation of Defocus Blur in Virtual Environments Comparing Graph Cuts and Convolutional Neural Network
    (2018-12) Chowdhury, Prodipto; Christopher, Lauren; King, Brian; Ben-Miled, Zina
    Depth estimation is one of the most important problems in computer vision. It has attracted a lot of attention because it has applications in many areas, such as robotics, VR and AR, self-driving cars etc. Using the defocus blur of a camera lens is one of the methods of depth estimation. In this thesis, we have researched this technique in virtual environments. Virtual datasets have been created for this purpose. In this research, we have applied graph cuts and convolutional neural network (DfD-net) to estimate depth from defocus blur using a natural (Middlebury) and a virtual (Maya) dataset. Graph Cuts showed similar performance for both natural and virtual datasets in terms of NMAE and NRMSE. However, with regard to SSIM, the performance of graph cuts is 4% better for Middlebury compared to Maya. We have trained the DfD-net using the natural and the virtual dataset and then combining both datasets. The network trained by the virtual dataset performed best for both datasets. The performance of graph-cuts and DfD-net have been compared. Graph-Cuts performance is 7% better than DfD-Net in terms of SSIM for Middlebury images. For Maya images, DfD-Net outperforms Graph-Cuts by 2%. With regard to NRMSE, Graph-Cuts and DfD-net shows similar performance for Maya images. For Middlebury images, Graph-cuts is 1.8% better. The algorithms show no difference in performance in terms of NMAE. The time DfD-net takes to generate depth maps compared to graph cuts is 500 times less for Maya images and 200 times less for Middlebury images.
  • Thumbnail Image
    Item
    Fully Automated 3D Segmentation of MR-Imaged Calf Muscle Compartments: Neighborhood Relationship Enhanced Fully Convolutional Network
    (Elsevier, 2021) Guo, Zhihui; Zhang, Honghai; Chen, Zhi; van der Plas, Ellen; Gutmann, Laurie; Thedens, Daniel; Nopoulos, Peggy; Sonka, Milan; Neurology, School of Medicine
    Automated segmentation of individual calf muscle compartments from 3D magnetic resonance (MR) images is essential for developing quantitative biomarkers for muscular disease progression and its prediction. Achieving clinically acceptable results is a challenging task due to large variations in muscle shape and MR appearance. In this paper, we present a novel fully convolutional network (FCN) that utilizes contextual information in a large neighborhood and embeds edge-aware constraints for individual calf muscle compartment segmentations. An encoder-decoder architecture is used to systematically enlarge convolution receptive field and preserve information at all resolutions. Edge positions derived from the FCN output muscle probability maps are explicitly regularized using kernel-based edge detection in an end-to-end optimization framework. Our method was evaluated on 40 T1-weighted MR images of 10 healthy and 30 diseased subjects by fourfold cross-validation. Mean DICE coefficients of 88.00-91.29% and mean absolute surface positioning errors of 1.04-1.66 mm were achieved for the five 3D muscle compartments.
  • Thumbnail Image
    Item
    Integrated Cytometry With Machine Learning Applied to High-Content Imaging of Human Kidney Tissue for In Situ Cell Classification and Neighborhood Analysis
    (Elsevier, 2023) Winfree, Seth; McNutt, Andrew T.; Khochare, Suraj; Borgard, Tyler J.; Barwinska, Daria; Sabo, Angela R.; Ferkowicz, Michael J.; Williams, James C., Jr.; Lingeman, James E.; Gulbronson, Connor J.; Kelly, Katherine J.; Sutton, Timothy A.; Dagher, Pierre C.; Eadon, Michael T.; Dunn, Kenneth W.; El-Achkar, Tarek M.; Medicine, School of Medicine
    The human kidney is a complex organ with various cell types that are intricately organized to perform key physiological functions and maintain homeostasis. New imaging modalities, such as mesoscale and highly multiplexed fluorescence microscopy, are increasingly being applied to human kidney tissue to create single-cell resolution data sets that are both spatially large and multidimensional. These single-cell resolution high-content imaging data sets have great potential to uncover the complex spatial organization and cellular makeup of the human kidney. Tissue cytometry is a novel approach used for the quantitative analysis of imaging data; however, the scale and complexity of such data sets pose unique challenges for processing and analysis. We have developed the Volumetric Tissue Exploration and Analysis (VTEA) software, a unique tool that integrates image processing, segmentation, and interactive cytometry analysis into a single framework on desktop computers. Supported by an extensible and open-source framework, VTEA's integrated pipeline now includes enhanced analytical tools, such as machine learning, data visualization, and neighborhood analyses, for hyperdimensional large-scale imaging data sets. These novel capabilities enable the analysis of mesoscale 2- and 3-dimensional multiplexed human kidney imaging data sets (such as co-detection by indexing and 3-dimensional confocal multiplexed fluorescence imaging). We demonstrate the utility of this approach in identifying cell subtypes in the kidney on the basis of labels, spatial association, and their microenvironment or neighborhood membership. VTEA provides an integrated and intuitive approach to decipher the cellular and spatial complexity of the human kidney and complements other transcriptomics and epigenetic efforts to define the landscape of kidney cell types.
  • Thumbnail Image
    Item
    Virtual Exploration of Safe Entry Zones in the Brainstem: Comprehensive Definition and Analysis of the Operative Approach
    (Elsevier, 2020) Meybodi, Ali Tayebi; Hendricks, Benjamin K.; Witten, Andrew J.; Hartman, Jerome; Tomlinson, Samuel B.; Cohen-Gadol, Aaron A.; Neurological Surgery, School of Medicine
    Background Detailed and accurate understanding of intrinsic brainstem anatomy and the inter-relationship between its internal tracts and nuclei and external landmarks is of paramount importance for safe and effective brainstem surgery. Using anatomical models can be an important step in sharpening such understanding. Objective To show the applicability of our developed virtual 3D model in depicting the safe entry zones (SEZs) to the brainstem. Methods Accurate 3D virtual models of brainstem elements were created using high-resolution magnetic resonance imaging and computed tomography to depict brainstem SEZs. Results All the described SEZs to different aspects of the brainstem were successfully depicted using our 3D virtual models. Conclusions The virtual models provide an immersive experience of brainstem anatomy, allowing users to understand the intricacies of the microdissection that is necessary to appropriately traverse the brainstem nuclei and tracts toward a particular target. The models provide an unparalleled learning environment for illustrating SEZs into the brainstem that can be used for training and research.