Abstract: Structure from Motion (SfM) has been proved an efficient algorithm of 3-D point cloud reconstruction derived from optical images. This paper extends it to infrared images taken by thermal cameras. To solve the absence of distinctive features and presence of thermal reflections with low contrast, this paper proposed a new TAC-RANSAC model to eliminate the mismatches using a feature detection algorithm suitable for infrared images. The experiment shows that the proposed method reduced the number of mismatches and obtain an ideal result of reconstruction.
DOI: *As the DOI is a unique identifier, it is already available in the pdf version. **The DOI link will be activated in the first midst of January 2026.
WSEAS Transactions on Signal Processing, ISSN / E-ISSN: 1790-5052 / 2224-3488, Volume 15, 2019, Art. #3
Yingying Kong, Bowen Zhang, Yingying Chen, Henry Leung, Shiyu Xi, "3-D Point Cloud Reconstruction of Infrared Images based on Improved Structure from Motion," WSEAS Transactions on Signal Processing, vol. 15, pp. 14-19, 2019, DOI:
Yingying Kong, Bowen Zhang, Yingying Chen, Henry Leung, Shiyu Xi. 3-D Point Cloud Reconstruction of Infrared Images based on Improved Structure from Motion.
WSEAS Transactions on Signal Processing. 2019;15:14-19.