Ground Truth Evaluation of Stereo Algorithms for Real World Applications
نویسندگان
چکیده
Current stereo algorithms are capable to calculate accurate (as defined, e.g., by needs in vision-based driver assistance) dense disparity maps in real time. They have become the source of three-dimensional data for several indoor and outdoor applications. However, ground truthbased evaluation of such algorithms has been typically limited to data sets generated indoors in laboratories. In this paper we present a new approach to evaluate stereo algorithms using ground-truth over real world data sets. Ground truth is generated using range measurements acquired with a high-end laser range-finder. For evaluating as many points as possible in a given disparity map, we use two evaluation approaches: A direct comparison for those pixels with available range data, and a confidence measure for the remaining pixels.
منابع مشابه
Real-World Stereo-Analysis Evaluation
Evaluation of stereo-analysis algorithms is usually done by analysing the performance of stereo matchers on data sets with available ground truth. The trade-off between precise results, obtained with this sort of evaluation, and the limited amount (in both, quantity and diversity) of data sets, needs to be considered if the algorithms are intended to be used for the analysis of real-world envir...
متن کاملEvaluation of Stereo Matching Systems for Real World Applications Using Structured Light for Ground Truth Estimation
In this paper we present an evaluation method for stereo matching systems and sensors especially for real world indoor applications. We estimate ground truth reference images by illuminating scenes with structured light. The paper starts with the selection of appropriate scenes, goes over ground truth estimation to the finally resulting evaluation of the stereo sensors. Three different stereo v...
متن کاملDynamic Programming Stereo on Real-World Sequences
This paper proposes a way to approximate ground truth for real-world stereo sequences, and applies this for evaluating the performance of different variants of dynamic programming stereo analysis. This illustrates a way of performance evaluation, also allowing to derive sequence analysis diagrams. Obtained results differ from those obtained for the discussed algorithms on smaller, or engineered...
متن کاملRealistic CG Stereo Image Dataset with Ground Truth Disparity Maps
Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, research in some branches of the field has been constrained due to the few number of stereo datasets with ground truth disparity maps available. Having available a large dataset of stereo images with ground truth disparity maps would boos...
متن کاملAn RGBN Benchmark
A variety of algorithms in both computer vision and graphics use datasets of an object or scene captured with fixed camera but varying illumination. Evaluating these algorithms is frequently challenging because of the lack of ground truth on the one hand, and insufficiently realistic and varied synthetic datasets on the other. In this work, we present a synthetic benchmark for applications such...
متن کامل