John Femiani

Road Network Extraction and Intersection Detection From Aerial Images by Tracking Road Footprints

In this paper, a new two-step approach (detecting and pruning) for automatic extraction of road networks from aerial images is presented. The road detection step is based on shape classification of a local homogeneous region around a pixel. The local homogeneous region is enclosed by a polygon, called the footprint of the pixel. This step involves detecting road footprints, tracking roads, and growing a road tree. We use a spoke wheel operator to obtain the road footprint. We propose an automatic road seeding method based on rectangular approximations to road footprints and a toe-finding algorithm to classify footprints for growing a road tree. The road tree pruning step makes use of a Bayes decision model based on the area-to-perimeter ratio (the A/P ratio) of the footprint to prune the paths that leak into the surroundings. We introduce a lognormal distribution to characterize the conditional probability of A/P ratios of the footprints in the road tree and present an automatic method to estimate the parameters that are related to the Bayes decision model. Results are presented for various aerial images. Evaluation of the extracted road networks using representative aerial images shows that the completeness of our road tracker ranges from 84% to 94%, correctness is above 81%, and quality is from 82% to 92%.

Curve matching for open 2D curves

We present a curve matching framework for planar open curves under similarity transform based on a new scale invariant signature. The signature is derived from the concept of integral of unsigned curvatures. If one input curve as a whole can be aligned with some part in the second curve then the algorithm will find the requisite starting and end positions and will estimate the similarity transform in O(Nlog(N)) time. We extend our frame work to a more general case where some part of the first input curve can be aligned with some part of the second input curve. This is a more difficult problem that we solve in O(N^3) time. The contributions of the paper are the new signature as well as faster algorithms for matching open 2D curves. We present examples from diverse application set to show that our algorithm can work across several domains.

Evaluating the effectiveness of flipped classrooms for teaching CS1

An alternative to the traditional classroom structure that has seen increased use in higher education is the flipped classroom. Flipping the classroom switches when assignments (e.g. homework) and knowledge transfer (e.g. lecture) occur. Flipped classrooms are getting popular in secondary and post-secondary teaching institutions as evidenced by the marked increase in the study, use, and application of the flipped pedagogy as it applies to learning and retention. The majority of the courses that have undergone this change use applied learning strategies and include a significant “learning-by-doing” component. The research in this area is skewed towards such courses and in general there are many considerations that educators ought to account for if they were to move to this form of teaching. Introductory courses in computer programming can appear to have all the elements needed to move to a flipped environment; however, initial observations from our research identify possible pitfalls with the assumption. In this work in progress the authors discuss early results and observations of implementing a flipped classroom to teach an introductory programming course (CS1) to engineering, engineering technology, and software engineering undergraduates.

Ecological divergence and medial cuneiform morphology in gorillas

Gorillas are more closely related to each other than to any other extant primate and are all terrestrial knuckle-walkers, but taxa differ along a gradient of dietary strategies and the frequency of arboreality in their behavioral repertoire. In this study, we test the hypothesis that medial cuneiform morphology falls on a morphocline in gorillas that tracks function related to hallucial abduction ability and relative frequency of arboreality. This morphocline predicts that western gorillas, being the most arboreal, should display a medial cuneiform anatomy that reflects the greatest hallucial abduction ability, followed by grauer gorillas, and then by mountain gorillas. Using a three-dimensional methodology to measure angles between articular surfaces, relative articular and nonarticular areas, and the curvatures of the hallucial articular surface, the functional predictions are partially confirmed in separating western gorillas from both eastern gorillas. Western gorillas are characterized by a more medially oriented, proportionately larger, and more mediolaterally curved hallucial facet than are eastern gorillas. These characteristics follow the predictions for a more prehensile hallux in western gorillas relative to a more stable, plantigrade hallux in eastern gorillas. The characteristics that distinguish eastern gorilla taxa from one another appear unrelated to hallucial abduction ability or frequency of arboreality. In total, this reexamination of medial cuneiform morphology suggests differentiation between eastern and western gorillas due to a longstanding ecological divergence and more recent and possibly non-adaptive differences between eastern taxa.

Robust rooftop extraction from visible band images using higher order CRF

In this paper, we propose a robust framework for building extraction in visible band images. We first get an initial classification of the pixels based on an unsupervised presegmentation. Then, we develop a novel conditional random field (CRF) formulation to achieve accurate rooftops extraction, which incorporates pixel-level information and segment-level information for the identification of rooftops. Comparing with the commonly used CRF model, a higher order potential defined on segment is added in our model, by exploiting region consistency and shape feature at segment level. Our experiments show that the proposed higher order CRF model outperforms the state-of-the-art methods both at pixel and object levels on rooftops with complex structures and sizes in challenging environments.

Shadow-Based Rooftop Segmentation in Visible Band Images

This paper presents a method to extract rooftops from aerial images with only visible red, green, and blue bands of data. In particular, it does not require near-infrared data, lidar, or multiple viewpoints. The proposed method uses shadows in the image in order to detect buildings and to determine a set of constraints on which parts can or cannot be rooftops. We then use the grabcut algorithm to identify complete rooftop regions and a method to make corrections that simulate a user performing interactive image segmentation in order to improve the precision of our results. The precision, recall, and F-score of the proposed approach show significant improvement over two very recently published papers. On our test dataset, we observe an average F-score of 89% compared to scores of 68% and 33%.

Fourier Shape Descriptors of Pixel Footprints for Road Extraction from Satellite Images

In this paper, an automatic road tracking method is presented for detecting roads from satellite images. This method is based on shape classification of a local homogeneous region around a pixel. The local homogeneous region is enclosed by a polygon, called the pixel footprint. We introduce a spoke wheel operator to obtain the pixel footprint and propose a Fourier-based approach to classify footprints for automatic seeding and growing of the road tracker. We experimentally demonstrate that our proposed road tracker can extract the centerlines of roads with sharp turns and intersections effectively, and has relatively small amount of leakage.

Interval HSV: Extracting ink annotations

The HSV color space is an intuitive way to reason about color, but the nonlinear relationship to RGB coordinates complicates histogram analysis of colors in HSV. We present novel Interval-HSV formulas to identify a range in HSV for each RGB interval. We show the usefulness by introducing a parameter-free and completely automatic technique to extract both colored and black ink annotations from faded backgrounds such as digitized aerial photographs, maps, or printed-text documents. We discuss the characteristics of ink mixing in the HSV color space and discover a single feature, the upper limit of the saturation-interval, to extract ink even when it is achromatic. We form robust Interval-HV histograms in order to identify the number and colors of inks in the image.

A Hybrid Method for Multi-sensor Remote Sensing Image Registration Based on Salience Region

In order to align the remote sensing images, we propose a novel hybrid method that combines image segmentation and salient region detection, which is inspired by human vision system. First of all, we present a novel superpixel-based method for dividing the image into sub-areas. Second, we propose a novel method based on color and image textures for detecting salient regions composed by superpixels. Then, we extract a new feature based on difference of Gaussian and local binary pattern from the salient regions. Finally, the sensed image is transformed by thin-plate spline. The proposed algorithm was tested on 30 pairs of remote sensing images and compared to other three state of the art methods. Experimental results show our approach is fast and robust, while still being efficient, which is better than other three methods.

Least eccentric ellipses for geometric Hermite interpolation

We present a rational Bezier solution to the geometric Hermite interpolation problem. Given two points and respective unit tangent vectors, we provide an interpolant that can reproduce a circle if possible. When the tangents permit an ellipse, we produce one that deviates least from a circle. We cast the problem as a theorem and provide its proof, and a method for determining the weights of the control points of a rational curve. Our approach targets ellipses, but we also present a cubic interpolant that can find curves with inflection points and space curves when an ellipse cannot satisfy the tangent constraints.