Clustering Point Process Based Network Topology Structure Constrained Urban Road Extraction From Remote Sensing Images

Abstract

To extract complicated road network from remote sensing images on urban scenes, this article presents a clustering point process (CPP) based network topology structure constrained road extraction algorithm. Firstly, the CPP is constructed to model the feature points, such as endpoints, bends, and crossroads in a road system. Based on that, an initial network topology structure is constructed by connecting the points with lines. Then, according to the network structure characteristic and the spectral characteristic of road, a network topology structure constraining model and a spectral measurement constraining model are constructed, respectively. By combining the models above, a road extraction model is built under the framework of Bayes' theorem. Finally, to simulate from the road extraction model and extract an optimal road network, a solution strategy, reversible jump Markov Chain Monte Carlo (RJMCMC) simulation algorithm with related transfer operations, is designed according to the CPP and network topology structure. Several high-resolution remote sensing images on urban scenes are tested. According to a buffer evaluation method, and compared with the comparing algorithms, accuracy and extraction rate of results from the proposed algorithm are increased by 10.86% and 8.75% on average, respectively. It is proved that the proposed algorithm can extract the complicated road network effectively. Index Terms-Clustering point process (CPP), feature points, network topology structure, reversible jump Markov chain Monte Carlo (RJMCMC), urban road extraction.

Finding the Time-Period-Based Most Frequent Path from Trajectory–Topology

“…For example, ref. [18] presents a clustering point process (CPP)-based network topology structure. The feature points, such as endpoints, bends, and crossroads in a road system, are connected by lines to characterize the network structure.…”

Utilization of Improved Annotations From Object-Based Image Analysis as Training Data for DeepLab V3+ Model: A Focus on Road Extraction in Very High-Resolution Orthophotos

“…For instance, Jiguang Dai devised a multiscale line segment orientation histogram (MLSOH) to accentuate road curvature [11], [12]. You Wu employed the Clustering Point Process (CPP) algorithm [13], while Jinming Zhan utilized graph theory to connect edges and nodes for road extraction. [14].…”