The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Share
Publications Copernicus
Download
Citation
Share
Articles | Volume XLVIII-G-2025
https://doi.org/10.5194/isprs-archives-XLVIII-G-2025-1747-2025
https://doi.org/10.5194/isprs-archives-XLVIII-G-2025-1747-2025
02 Aug 2025
 | 02 Aug 2025

Finding the Optimal Convolutional Kernel Size for Semantic Segmentation of Pole-like Objects in Lidar Point Clouds

Zezheng Zhang, Davood Shojaei, and Kourosh Khoshelham

Keywords: Mobile Laser Scanning, Street Furniture, Road Assets, Semantic Segmentation, Deep Learning

Abstract. Pole-like objects (PLOs) are important street assets in urban environments, yet current deep learning methods often underperform in their segmentation compared to other objects. The main challenge is determining the right kernel size to effectively understand the unique structure of PLOs with an appropriate receptive field. In this study, we improve the segmentation performance of PLOs by optimizing the kernel size in a KPConv-based network. Our experiments show that kernel size of 9 yields an Intersection over Union (IoU) of 95.02% on the Parkville-3D dataset. We also develop a post-processing approach that transforms semantic segmentation outputs into panoptic segmentation results, enabling accurate detection of individual PLO instances. Furthermore, qualitative tests on an independent, unlabelled point cloud dataset from a different urban area demonstrate that our method consistently achieves accurate segmentation.

Share