Research papers of the week - Feburary 6, 2022

Agata Walicka, Norbert Pfeifer

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

Ministerial score = 140.0
Journal Impact Factor (2020) = 3.784(Q2)

In this paper, we propose a method for instance segmentation of individual grains from a terrestrial laser scanning point cloud representing a mountain river bed. The method was designed as a classification followed by segmentation approach. The binary classification into either points representing river bed or grains is performed using the Random Forest algorithm. The point cloud is classified based only on geometrical features calculated for a local, spherical neighborhood. A multi-size neighborhood approach was used together with the feature selection method that is based on correlation analysis. The final classification was performed using a set of features calculated for the neighborhood size of 5 cm, 15 cm, and 20 cm. The achieved classification results have the overall accuracy of 85% to 95%, depending on the test site. The segmentation is performed using the DBSCAN algorithm in order to cluster the point cloud based on Euclidean distances between points. The performed experiments showed that the proposed method enables us to correctly delineate 67% to 88% of grains, depending on the test site. However, the resulting point cloud-based completeness expressed as Jaccard index is similar for each of the test sites and is approximately 88%. Moreover, the proposed method proved that it is robust to the shadowing effect.

DOI:10.1109/JSTARS.2022.3141892

READ THE PAPER UPWr Base