This paper presents a robust algorithm to reconstruct power-lines using ALS technology. Point cloud data are automatically classified into five target classes before reconstruction. In order to improve upon the defaults of only using the local shape properties of a single power-line span in traditional methods, the distribution properties of power-line group between two neighbor pylons and contextual information of related pylon objects are used to improve the reconstruction results. First, the distribution properties of power-line sets are detected using a similarity detection method. Based on the probability of neighbor points belonging to the same span, a RANSAC rule based algorithm is then introduced to reconstruct power-lines through two important advancements: reliable initial parameters fitting and efficient candidate sample detection. Our experiments indicate that the proposed method is effective for reconstruction of power-lines from complex scenarios.

Object detection and reconstruction from remotely sensed data are active research topic in photogrammetric and remote sensing communities. Power engineering device monitoring by detecting key objects is important for power safety. In this paper, we introduce a novel method for the reconstruction of self-supporting pylons widely used in high voltage power-line systems from airborne LiDAR data. Our work constructs pylons from a library of 3D parametric models, which are represented using polyhedrons based on stochastic geometry. Firstly, laser points of pylons are extracted from the dataset using an automatic classification method. An energy function made up of two terms is then defined: the first term measures the adequacy of the objects with respect to the data, and the second term has the ability to favor or penalize certain configurations based on prior knowledge. Finally, estimation is undertaken by minimizing the energy using simulated annealing. We use a Markov Chain Monte Carlo sampler, leading to an optimal configuration of objects. Two main contributions of this paper are: (1) building a framework for automatic pylon reconstruction; and (2) efficient global optimization. The pylons can be precisely reconstructed through energy optimization. Experiments producing convincing results validated the proposed method using a dataset of complex structure.

Terrestrial laser scanning (TLS) point clouds are increasingly used for monitoring steel grid structures, and accurate instance segmentation is central to their processing. In complex environments, segmenting junction regions is challenging owing to multi-member geometry and incomplete sampling. Existing approaches frequently depend on prior information such as design drawings or Building Information Modeling (BIM), which limits generality and offers few solutions when model priors are unavailable. A hierarchical spherical coordinate segmentation with dual-sphere center refinement method (HSC-DCR) is proposed for geometry-driven junction region instance segmentation. The method uses radial connectivity. A segmentation origin is first located via a grid search driven by directional convergence evaluation, and a spherical coordinate system is then established for initial angular domain clustering. Subsequently, topological correction is guided by multi-dimensional indicators, and instance refinement is achieved through dual-sphere center optimization. The process is geometry-driven and independent of design models. Experiments on a laser-scanned stadium point cloud, covering 22 junction-region types and 521 instances, achieve an F1-score of 0.948 and mIoU of 85.5% under an instance-matched evaluation protocol. The results show that HSC-DCR can reliably obtain node and member instances from TLS point clouds without relying on drawings or BIM, supporting TLS-based monitoring of steel grid structures.

Land cover maps generated from semantic segmentation of high-resolution remotely sensed images have drawn mucon in the photogrammetry and remote sensing research community. Currently, massive fine-resolution remotely sensed (FRRS) images acquired by improving sensing and imaging technologies become available. However, accurate semantic segmentation of such FRRS images is greatly affected by substantial class disparities, the invisibility of key ground objects due to occlusion, and object size variation. Despite the extraordinary potential in deep convolutional neural networks (DCNNs) in image feature learning and representation, extracting sufficient features from FRRS images for accurate semantic segmentation is still challenging. These challenges demand the deep learning models to learn robust features and generate sufficient feature descriptors. Specifically, learning multi-contextual features to guarantee adequate coverage of varied object sizes from the ground scene and harnessing global-local contexts to overcome class disparities challenge even profound networks. Deeper networks significantly lose spatial details due to gradual downsampling processes resulting in poor segmentation results and coarse boundaries. This article presents a stacked deep residual network (SDRNet) for semantic segmentation from FRRS images. The proposed framework utilizes two stacked encoder-decoder networks to harness long-range semantics yet preserve spatial information and dilated residual blocks (DRB) between each encoder and decoder network to capture sufficient global dependencies thus improving segmentation performance. Our experimental results obtained using the ISPRS Vaihingen and Potsdam datasets demonstrate that the SDRNet performs effectively and competitively against current DCNNs in semantic segmentation.