IS&T | Library

A New Hybrid Stereo Disparity Estimation Algorithm with Guided Image Filtering-Based Cost Aggregation

168 8

stereo matching
guided image filtering
cost aggregation
segmentation
stereo disparity
image processing
stereo vision

Hanieh Shabanian, Madhusudhanan Balasubramanian

Pages 59-1 - 59-7, January 2021, © Society for Imaging Science and Technology 2021

DOI

10.2352/ISSN.2470-1173.2021.2.SDA-059

Volume 33

Issue 2

Stereo matching algorithms are useful for estimating a dense depth characteristic of a scene by finding corresponding points from stereo images of the scene. Several factors such as occlusion, noise, and illumination inconsistencies in the scene affect the disparity estimates and make this process challenging. Algorithms developed to overcome these challenges can be broadly categorized as learning-based and non-learning based disparity estimation algorithms. The learning-based approaches are more accurate but computationally expensive. In contrary, non-learning based algorithms are widely used and are computationally efficient algorithms. In this paper, we propose a new stereo matching algorithm using guided image filtering (GIF)-based cost aggregation. The main contribution of our approach is a cost calculation framework which is a hybrid of cross-correlation between stereo-image pairs and scene segmentation (HCS). The performance of our HCS technique was compared with state-ofthe- art techniques using version 3 of the benchmark Middlebury dataset. Our results confirm the effective performance of the HCS technique.

Digital Library: EI

Published Online: January 2021

Volume Data Segmentation Using Visual Selection

30 6

visualization
medical image processing
segmentation
visual-selection method
volume rendering
layered manufacturing

Shyh-Kuang Ueng, Hsin-Cheng Huang

Pages 331-1 - 331-7, January 2021, © Society for Imaging Science and Technology 2021

DOI

10.2352/ISSN.2470-1173.2021.1.VDA-331

Volume 33

Issue 1

Segmentation is usually performed in the spatial domain and is likely hindered by similar intensity, intensity inhomogeneity, and partial volume effect. In this article, a visual-selection method is proposed to carry out segmentation in the intensity space such that the aforementioned difficulties are alleviated and better results can be produced. The proposed procedure utilizes volume rendering to explore the input data and builds a transfer function, encoding the intensity distribution of the target. Then, by using this transfer function and image processing techniques, a region of interest (ROI) is constructed in the intensity field. At the following stage, a texture-based region growing computation is conducted to extract the target from the ROI. Experiments show that the proposed method produces high quality results for a phantom which is composed of plates with similar intensities and textures. It also out-performs a traditional segmentation system in separating organs and tissues from a torso CT-scan data set.

Digital Library: EI

Published Online: January 2021

An active contour model for medical image segmentation using a quaternion framework

36 3

segmentation
anisotropic gradient
medical images
quaternion
active contour

V. Voronin, M. Zhdanova, E. Semenishchev, A. Zelensky, S. Agaian

Pages 62-1 - 62-6, January 2020, © Society for Imaging Science and Technology 2020

DOI

10.2352/ISSN.2470-1173.2020.10.IPAS-062

Volume 32

Issue 10

This paper presents a new method for segmenting medical images is based on Hamiltonian quaternions and the associative algebra, method of the active contour model and LPA-ICI (local polynomial approximation - the intersection of confidence intervals) anisotropic gradient. Since for segmentation tasks, the image is usually converted to grayscale, this leads to the loss of important information about color, saturation, and other important information associated color. To solve this problem, we use the quaternion framework to represent a color image to consider all three channels simultaneously when segmenting the RGB image. As a method of noise reduction, adaptive filtering based on local polynomial estimates using the ICI rule is used. The presented new approach allows obtaining clearer and more detailed boundaries of objects of interest. The experiments performed on real medical images (Z-line detection) show that our segmentation method of more efficient compared with the current state-of-art methods.

Digital Library: EI

Published Online: January 2020

Estimating Vehicle Fuel Economy from Overhead Camera Imagery and Application for Traffic Control

55 10

computer vision
segmentation
clean energy
reinforcement learning

Thomas Karnowski, Ryan Tokola, Sean Oesch, Matthew Eicholtz, Jeff Price, Tim Gee

DOI

10.2352/ISSN.2470-1173.2020.6.IRIACV-070

Volume 32

Issue 6

In this work, we explore the ability to estimate vehicle fuel consumption using imagery from overhead fisheye lens cameras deployed as traffic sensors. We utilize this information to simulate vision-based control of a traffic intersection, with a goal of improving fuel economy with minimal impact to mobility. We introduce the ORNL Overhead Vehicle Data set (OOVD), consisting of a data set of paired, labeled vehicle images from a ground-based camera and an overhead fisheye lens traffic camera. The data set includes segmentation masks based on Gaussian mixture models for vehicle detection. We show the data set utility through three applications: estimation of fuel consumption based on segmentation bounding boxes, vehicle discrimination for vehicles with large bounding boxes, and fine-grained classification on a limited number of vehicle makes and models using a pre-trained set of convolutional neural network models. We compare these results with estimates based on a large open-source data set of web-scraped imagery. Finally, we show the utility of the approach using reinforcement learning in a traffic simulator using the open source Simulation of Urban Mobility (SUMO) package. Our results demonstrate the feasibility of the approach for controlling traffic lights for better fuel efficiency based solely on visual vehicle estimates from commercial, fisheye lens cameras.

Digital Library: EI

Published Online: January 2020

3D Medical Image Segmentation in Virtual Reality

39 1

virtual reality
head-mounted display
segmentation
medical imaging
volume rendering

Shea B Yonker, Oleksandr O Korshak, Timothy Hedstrom, Alexander Wu, Siddharth Atre, Jürgen P Schulze

DOI

10.2352/ISSN.2470-1173.2019.2.ERVR-188

Volume 31

Issue 2