Relevamiento del patrimonio histórico rural mediante fotogrametría (SfM-MVS) en la región pampeana argentina. “Primera Estancia” de Magdalena (Buenos Aires, Argentina)

En el marco del relevamiento del patrimonio histórico rural del partido de Magdalena, se presenta un modelo virtual 3D de una estructura habitacional utilizada como vivienda de los peones de una estancia ganadera generado por Structure from Motion MultiView Stereo (SfM-MVS). Dicha estructura se ubica en la región costera de la provincia de Buenos Aires, zona que cuenta con un importante patrimonio cultural y natural. El flujo de trabajo incluyó la adquisición y procesamiento de fotografías con el objetivo de generar un modelo 3D. Este modelo produce un resultado fotorrealista, sobre el que realizan una serie de visualizaciones y análisis; como el registro de patologías, la obtención de mediciones en gabinete y la generacion de un registro para evaluar el estado de conservación. Se pone en consideración la potencialidad de la técnica frente a la posibilidad de pérdida del patrimonio local. Las fortalezas de esta técnica radican en la reducción del tiempo de la toma de datos, el relevamiento in situ, no destructivo y de bajo costo. Permite obtener reconstrucciones con gran detalle y precisión, útiles para la investigación y la divulgación, lo cual contribuye a la salvaguarda y socialización de los bienes patrimoniales.

Semantically Derived Geometric Constraints for MVS Reconstruction of Textureless Areas

Conventional multi-view stereo (MVS) approaches based on photo-consistency measures are generally robust, yet often fail in calculating valid depth pixel estimates in low textured areas of the scene. In this study, a novel approach is proposed to tackle this challenge by leveraging semantic priors into a PatchMatch-based MVS in order to increase confidence and support depth and normal map estimation. Semantic class labels on image pixels are used to impose class-specific geometric constraints during multiview stereo, optimising the depth estimation on weakly supported, textureless areas, commonly present in urban scenarios of building facades, indoor scenes, or aerial datasets. Detecting dominant shapes, e.g., planes, with RANSAC, an adjusted cost function is introduced that combines and weighs both photometric and semantic scores propagating, thus, more accurate depth estimates. Being adaptive, it fills in apparent information gaps and smoothing local roughness in problematic regions while at the same time preserves important details. Experiments on benchmark and custom datasets demonstrate the effectiveness of the presented approach.

A NEW SATELLITE IMAGERY STEREO PIPELINE DESIGNED FOR SCALABILITY, ROBUSTNESS AND PERFORMANCE

This paper presents a new Multiview Stereo Pipeline (MVS), called CARS, dedicated to satellite imagery. This pipeline is intended for massive Digital Surface Model (DSM) production and has therefore been designed to maximize scalability robustness and performance. Those two properties have driven the design of the workflow as well as the choice of algorithms and parameter trends, making our pipeline unique with respect to existing solutions in literature. This paper intends to serve as a reference paper for the pipeline implementation, and therefore provides a detailed description of algorithms and workflow. It also demonstrates the pipeline robustness and stability in several use cases, and compares its accuracy with the state-of-the-art pipelines on a reference dataset.