This software finds feature point correspondences in sequences of images. It is designed for feature matching in aerial imagery. Feature matching is a fundamental step in a number of important image processing operations: calibrating the cameras in a camera array, stabilizing images in aerial movies, geo-registration of images, and generating high-fidelity surface maps from aerial movies.
The method uses a Shi-Tomasi corner detector and normalized cross-correlation. This process is likely to result in the production of some mismatches. The feature set is cleaned up using the assumption that there is a large planar patch visible in both images. At high altitude, this assumption is often reasonable. A mathematical transformation, called an homography, is developed that allows us to predict the position in image 2 of any point on the plane in image 1. Any feature pair that is inconsistent with the homography is thrown out. The output of the process is a set of feature pairs, and the homography.
The algorithms in this innovation are well known, but the new implementation improves the process in several ways. It runs in real-time at 2 Hz on 64-megapixel imagery. The new Shi-Tomasi corner detector tries to produce the requested number of features by automatically adjusting the minimum distance between found features. The homography-finding code now uses an implementation of the RANSAC algorithm that adjusts the number of iter-
ations automatically to achieve a pre-set probability of missing a set of inliers. The new interface allows the caller to pass in a set of predetermined points in one of the images. This allows the ability to track the same set of points through multiple frames.
This work was done by Daniel S. Clouse, Yang Cheng, Adnan I. Ansar, David C. Trotz, and Curtis W. Padgett of Caltech for NASA’s Jet Propulsion Laboratory. For more information, download the Technical Support Package (free white paper) at www.techbriefs.com/tsp under the Software category.
The software used in this innovation is available for commercial licensing. Please contact Daniel Broderick of the California Institute of Technology at
This Brief includes a Technical Support Package (TSP).
Real-Time Feature Tracking Using Homography
(reference NPO-46916) is currently available for download from the TSP library.
Don't have an account?
Overview
The document is a Technical Support Package from NASA's Jet Propulsion Laboratory (JPL) detailing "Real-Time Feature Tracking Using Homography," identified by the reference NPO-46916. It serves as a comprehensive guide for utilizing advanced techniques in feature tracking between images, which is crucial for various aerospace applications and has broader technological implications.
The primary focus of the document is on a command-line tool called feature_track, which is designed to find feature correspondences between two images. The tool can handle images of different sizes and employs a Shi-Tomasi corner detector to automatically identify features in the first image if predetermined features are not provided. The matching process utilizes normalized cross-correlation to find corresponding features in the second image.
Key features of the tool include options for specifying input images, predetermined feature files, and an initial estimate of the homography transform. The homography is essential for reducing the search area for features in the second image and improving matching accuracy. The output includes a robust homography that is consistent with the largest subset of feature pairs, which is saved in a file named htrans.txt. This file contains the elements of the 3x3 homography matrix and the dimensions of the first image.
The document also outlines various algorithm tuning options, such as pyramid levels, minimum and maximum features, correlation thresholds, and search radii, allowing users to customize the feature tracking process according to their specific needs. Additionally, it provides options for outputting correlation images, feature images, and interest images, enhancing the usability of the tool for analysis and debugging.
Furthermore, the document emphasizes the importance of consistent feature output with the final homography, which is crucial for ensuring the reliability of the feature tracking results. It also includes debugging options and instructions for setting option values through a configuration file.
Overall, this Technical Support Package not only provides detailed instructions on using the feature tracking tool but also highlights its potential applications in aerospace technology and beyond. It serves as a valuable resource for researchers and engineers looking to implement real-time feature tracking in their projects. For further assistance, the document provides contact information for the Innovative Technology Assets Management team at JPL.
