The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2022, 501–508, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-501-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2022, 501–508, 2022
https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-501-2022
 
30 May 2022
30 May 2022

TRIPLE EPIPOLAR IMAGES GENERATION AND MATCHING IN TRISTEREO IMAGING ON THE SAME ORBIT MODE

Q. Yue and X. Tang Q. Yue and X. Tang
  • Land Satellite Remote Sensing Application Center, MNR, 100048 Beijing, China

Keywords: Triple epipolar images, Object space geometric constraint, SGM, Matching, Occlusion, Efficiency, Precision

Abstract. This paper proposed the method to generate triple epipolar images in tristereo imaging on the same orbit mode. It generated projection tie points based on double projection surface in object space, and designed conversion model from epipolar images to its corresponding original images on the basis of projection tie points and created the RPC of epipolar images. During stereo matching one stereo image pairs are used as the basic pair and proposed the rapid transformation model between the current matching points and the corresponding point on the third image, which accomplished the combination of epipolar stereo matching and object space geometric constraints. After left/right bidirectional matching and occlusion area checking, a third matching was implemented. The cost of occlusion area will use the smallest one among the three and these areas were revamped. SGM was used as the optimization strategy. Experiments in three typical areas using Pleiades and ZY-3 as data recourses show that the loss of precision is negligible in the proposed epipolar image generation method. The proposed matching method combines the best of both object geometric constraint method and isolate epipolar image pair method, and the computational efficiency significantly better than these two methods. Lastly, the precision of the proposed method is significantly better than these two methods in building area and weak texture area.