The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2021, 383–390, 2021
https://doi.org/10.5194/isprs-archives-XLIII-B2-2021-383-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2021, 383–390, 2021
https://doi.org/10.5194/isprs-archives-XLIII-B2-2021-383-2021

  28 Jun 2021

28 Jun 2021

AMBIGUITY CONCEPT IN STEREO MATCHING PIPELINE

E. Sarrazin1, M. Cournet1, L. Dumas2, V. Defonte2, Q. Fardet2, Y. Steux2, N. Jimenez Diaz2, E. Dubois1, D. Youssefi1, and F. Buffe1 E. Sarrazin et al.
  • 1Centre National d’Etudes Spatiales (CNES), 18 avenue E. Belin, Toulouse, France
  • 2CS, 6 rue Brindejonc des Moulinais, Toulouse, France

Keywords: Ambiguity, Confidence, Stereo Matching, Disparity Map Denoising, Semi Global Matching Optimization

Abstract. In a 3D reconstruction pipeline, stereo matching step aims at computing a disparity map representing the depth between image pair. The evaluation of the disparity map can be done through the estimation of a confidence metric. In this article, we propose a new confidence metric, named ambiguity integral metric, to assess the quality of the produced disparity map. This metric is derived from the concept of ambiguity, which characterizes the property of the cost curve profile. It aims to quantify the difficulty in identifying the correct disparity to select. The quality of ambiguity integral metric is evaluated through the ROC curve methodology and compared with other confidence measures. In regards to other measures, the ambiguity integral measure shows a good potential. We also integrate this measure through various steps of the stereo matching pipeline in order to improve the performance estimation of the disparity map. First, we include ambiguity integral measure during the Semi Global Matching optimization step. The objective is to weight, by ambiguity integral measure, the influence of points in the SGM regularization to reduce the impact of ambiguous points. Secondly, we use ambiguity as an input of a disparity refinement deep learning architecture in order to easily locate noisy area and preserve details.