Current Search:   Mahalanobis, Abhijit (x)

View All Items

  • CSV Spreadsheet
(1 - 4 of 4)
Optimization Algorithms for Deep Learning Based Medical Image Segmentations
Title
Optimization Algorithms for Deep Learning Based Medical Image Segmentations.
Creator
Mortazi, Aliasghar, Bagci, Ulas, Shah, Mubarak, Mahalanobis, Abhijit, Pensky, Marianna, University of Central Florida
Abstract / Description
Medical image segmentation is one of the fundamental processes to understand and assess the functionality of different organs and tissues as well as quantifying diseases and helping treatmentplanning. With ever increasing number of medical scans, the automated, accurate, and efficient medical image segmentation is as unmet need for improving healthcare. Recently, deep learn-ing has emerged as one the most powerful methods for almost all image analysis tasks such as segmentation, detection,...
Show moreMedical image segmentation is one of the fundamental processes to understand and assess the functionality of different organs and tissues as well as quantifying diseases and helping treatmentplanning. With ever increasing number of medical scans, the automated, accurate, and efficient medical image segmentation is as unmet need for improving healthcare. Recently, deep learn-ing has emerged as one the most powerful methods for almost all image analysis tasks such as segmentation, detection, and classification and so in medical imaging. In this regard, this dissertation introduces new algorithms to perform medical image segmentation for different (a) imaging modalities, (b) number of objects, (c) dimensionality of images, and (d) under varying labelingconditions. First, we study dimensionality problem by introducing a new 2.5D segmentation engine that can be used in single and multi-object settings. We propose new fusion strategies and loss functions for deep neural networks to generate improved delineations. Later, we expand the proposed idea into 3D and 4D medical images and develop a "budget (computational) friendly"architecture search algorithm to make this process self-contained and fully automated without scarifying accuracy. Instead of manual architecture design, which is often based on plug-in and out and expert experience, the new algorithm provides an automated search of successful segmentation architecture within a short period of time. Finally, we study further optimization algorithms on label noise issue and improve overall segmentation problem by incorporating prior information about label noise and object shape information. We conclude the thesis work by studying different network and hyperparameter optimization settings that are fine-tuned for varying conditions for medical images. Applications are chosen from cardiac scans (images) and efficacy of the proposed algorithms are demonstrated on several data sets publicly available, and independently validated by blind evaluations.
Show less
Date Issued
2019
Identifier
CFE0007841, ucf:52825
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0007841
Action Recognition, Temporal Localization and Detection in Trimmed and Untrimmed Video
Title
Action Recognition, Temporal Localization and Detection in Trimmed and Untrimmed Video.
Creator
Hou, Rui, Shah, Mubarak, Mahalanobis, Abhijit, Hua, Kien, Sukthankar, Rahul, University of Central Florida
Abstract / Description
Automatic understanding of videos is one of the most active areas of computer vision research. It has applications in video surveillance, human computer interaction, video sports analysis, virtual and augmented reality, video retrieval etc. In this dissertation, we address four important tasks in video understanding, namely action recognition, temporal action localization, spatial-temporal action detection and video object/action segmentation. This dissertation makes contributions to above...
Show moreAutomatic understanding of videos is one of the most active areas of computer vision research. It has applications in video surveillance, human computer interaction, video sports analysis, virtual and augmented reality, video retrieval etc. In this dissertation, we address four important tasks in video understanding, namely action recognition, temporal action localization, spatial-temporal action detection and video object/action segmentation. This dissertation makes contributions to above tasks by proposing. First, for video action recognition, we propose a category level feature learning method. Our proposed method automatically identifies such pairs of categories using a criterion of mutual pairwise proximity in the (kernelized) feature space, and a category-level similarity matrix where each entry corresponds to the one-vs-one SVM margin for pairs of categories. Second, for temporal action localization, we propose to exploit the temporal structure of actions by modeling an action as a sequence of sub-actions and present a computationally efficient approach. Third, we propose 3D Tube Convolutional Neural Network (TCNN) based pipeline for action detection. The proposed architecture is a unified deep network that is able to recognize and localize action based on 3D convolution features. It generalizes the popular faster R-CNN framework from images to videos. Last, an end-to-end encoder-decoder based 3D convolutional neural network pipeline is proposed, which is able to segment out the foreground objects from the background. Moreover, the action label can be obtained as well by passing the foreground object into an action classifier. Extensive experiments on several video datasets demonstrate the superior performance of the proposed approach for video understanding compared to the state-of-the-art.
Show less
Date Issued
2019
Identifier
CFE0007655, ucf:52502
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0007655
Fast Compressed Automatic Target Recognition for a Compressive Infrared Imager
Title
Fast Compressed Automatic Target Recognition for a Compressive Infrared Imager.
Creator
Millikan, Brian, Foroosh, Hassan, Rahnavard, Nazanin, Muise, Robert, Atia, George, Mahalanobis, Abhijit, Sun, Qiyu, University of Central Florida
Abstract / Description
Many military systems utilize infrared sensors which allow an operator to see targets at night. Several of these are either mid-wave or long-wave high resolution infrared sensors, which are expensive to manufacture. But compressive sensing, which has primarily been demonstrated in medical applications, can be used to minimize the number of measurements needed to represent a high-resolution image. Using these techniques, a relatively low cost mid-wave infrared sensor can be realized which has...
Show moreMany military systems utilize infrared sensors which allow an operator to see targets at night. Several of these are either mid-wave or long-wave high resolution infrared sensors, which are expensive to manufacture. But compressive sensing, which has primarily been demonstrated in medical applications, can be used to minimize the number of measurements needed to represent a high-resolution image. Using these techniques, a relatively low cost mid-wave infrared sensor can be realized which has a high effective resolution. In traditional military infrared sensing applications, like targeting systems, automatic targeting recognition algorithms are employed to locate and identify targets of interest to reduce the burden on the operator. The resolution of the sensor can increase the accuracy and operational range of a targeting system. When using a compressive sensing infrared sensor, traditional decompression techniques can be applied to form a spatial-domain infrared image, but most are iterative and not ideal for real-time environments. A more efficient method is to adapt the target recognition algorithms to operate directly on the compressed samples. In this work, we will present a target recognition algorithm which utilizes a compressed target detection method to identify potential target areas and then a specialized target recognition technique that operates directly on the same compressed samples. We will demonstrate our method on the U.S. Army Night Vision and Electronic Sensors Directorate ATR Algorithm Development Image Database which has been made available by the Sensing Information Analysis Center.
Show less
Date Issued
2018
Identifier
CFE0007408, ucf:52739
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0007408
Vehicle Tracking and Classification via 3D Geometries for Intelligent Transportation Systems
Title
Vehicle Tracking and Classification via 3D Geometries for Intelligent Transportation Systems.
Creator
Mcdowell, William, Mikhael, Wasfy, Jones, W Linwood, Haralambous, Michael, Atia, George, Mahalanobis, Abhijit, Muise, Robert, University of Central Florida
Abstract / Description
In this dissertation, we present generalized techniques which allow for the tracking and classification of vehicles by tracking various Point(s) of Interest (PoI) on a vehicle. Tracking the various PoI allows for the composition of those points into 3D geometries which are unique to a given vehicle type. We demonstrate this technique using passive, simulated image based sensor measurements and three separate inertial track formulations. We demonstrate the capability to classify the 3D...
Show moreIn this dissertation, we present generalized techniques which allow for the tracking and classification of vehicles by tracking various Point(s) of Interest (PoI) on a vehicle. Tracking the various PoI allows for the composition of those points into 3D geometries which are unique to a given vehicle type. We demonstrate this technique using passive, simulated image based sensor measurements and three separate inertial track formulations. We demonstrate the capability to classify the 3D geometries in multiple transform domains (PCA (&) LDA) using Minimum Euclidean Distance, Maximum Likelihood and Artificial Neural Networks. Additionally, we demonstrate the ability to fuse separate classifiers from multiple domains via Bayesian Networks to achieve ensemble classification.
Show less
Date Issued
2015
Identifier
CFE0005976, ucf:50790
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0005976