Stereo matching: performance study of two global algorithms

Abstract

Techniques such as clinometry, stereoscopy, interferometry, and polarimetry are used for Digital Elevation Model (DEM) generation from Synthetic Aperture Radar (SAR) images. The choice of technique depends on the SAR configuration, the means used for image acquisition, and the relief type. The most popular techniques are interferometry for regions of high coherence and stereoscopy for regions such as steep forested mountain slopes. Stereo matching, which is finds the disparity map or correspondence points between two images acquired from different sensor positions, is a core process in stereoscopy. Additionally, automatic stereo processing, which involves stereo matching, is an important process in other applications including vision-based obstacle avoidance for unmanned air vehicles (UAVs), extraction of weak targets in clutter, and automatic target detection. Due to its high computational complexity, stereo matching has traditionally been, and continues to be, one of the most heavily investigated topics in computer vision. A stereo matching algorithm performs a subset of the following four steps: cost computation, cost (support) aggregation, disparity computation/optimization, and disparity refinement. Based on the method used for cost computation, the algorithms are classified into feature-, phase-, and area-based algorithms; and they are classified as local or global based on how they perform disparity computation/optimization. We present a comparative performance study of two pairs, i.e., four versions, of global stereo matching codes. Each pair uses a different minimization technique: a simulated annealing or graph cut algorithm. And, the codes of a pair differ in terms of the employed global cost function: absolute difference (AD) or a variation of normalized cross correlation (NCC). The performance comparison is in terms of execution time, the global minimum cost achieved, power and energy consumption, and the quality of generated output. The results of this preliminary study provide insights into the suitability and relative merits of these algorithms and cost functions for execution on field-deployable and on-board computer systems with size, weight, and power (SWaP) constraints. The results show that for 12 out of 14 instances the graph cut codes, compared to their simulated annealing counterparts provided a 35-85% improvement in energy consumption and, therefore, are promising candidates for use in fielddeployable and on-board systems.

How do code refactorings affect energy usage?

“…Arunagiri et al performed a comparative study to solve the global stereo matching problem in terms of performance and energy consumption [4]. Their result suggests that stereo matching with the graph cut algorithm is a lot better than stereo matching with simulated annealing for both terms they consider.…”

Investigating the impacts of web servers on web application energy usage

“…Arunagiri et al performed a comparative performance study of several implementations, each with multiple versions, of algorithms to solve the global stereo matching problem [8]. They compared the execution time, global minimum cost achieved, and quality of the general solutions against the amounts of energy consumed.…”

Supporting software evolution through feedback on executing/skipping energy tests for proposed source code changes

“…These studies include impacts of performance tips, code obfuscation, code refactorings, design patterns, web servers, sorting algorithms, advertisements, API usage,() and programming models . In addition, researchers have investigated an application's energy consumption among versions and among separate implementations of the same application, the energy consumption impacts of selecting between different software systems that achieve the same purpose, how developers ask questions about energy usage, and how developers think about energy when they develop their software …”