Andrés Serna

TerraMobilita/iQmulus urban point cloud analysis benchmark

The objective of the TerraMobilita/iQmulus 3D urban analysis benchmark is to evaluate the current state of the art in urban scene analysis from mobile laser scanning (MLS) at large scale. A very detailed semantic tree for urban scenes is proposed. We call analysis the capacity of a method to separate the points of the scene into these categories (classification), and to separate the different objects of the same type for object classes (detection). A very large ground truth is produced manually in two steps using advanced editing tools developed especially for this benchmark. Based on this ground truth, the benchmark aims at evaluating the classification, detection and segmentation quality of the submitted results. Graphical abstractDisplay Omitted HighlightsVery rich data: high accuracy, high resolution, many attributes.Massive data: 160 million annotated points thanks to a performant web based annotation tool (and many hours of work).Rich semantics organized in a semantic tree with various levels of generalization.Very objective evaluation metrics.

Attribute Controlled Reconstruction and Adaptive Mathematical Morphology

In this paper we present a reconstruction method controlled by the evolution of attributes. The process begins from a marker, propagated over increasing quasi–flat zones. The evolution of several increasing and non–increasing attributes is studied in order to select the appropriate region. Additionally, the combination of attributes can be used in a straightforward way.

Segmentation of Façades from Urban 3D Point Clouds Using Geometrical and Morphological Attribute-Based Operators

3D building segmentation is an important research issue in the remote sensing community with relevant applications to urban modeling, cloud-to-cloud and cloud-to-model registration, 3D cartography, virtual reality, cultural heritage documentation, among others. In this paper, we propose automatic, parametric and robust approaches to segment facades from 3D point clouds. Processing is carried out using elevation images and 3D decomposition, and the final result can be reprojected onto the 3D point cloud for visualization or evaluation purposes. Our methods are based on geometrical and geodesic constraints. Parameters are related to urban and architectural constraints. Thus, they can be set up to manage facades of any height, length and elongation. We propose two methods based on facade marker extraction and a third method without markers based on the maximal elongation image. This work is developed in the framework of TerraMobilita project. The performance of our methods is proved in our experiments on TerraMobilita databases using 2D and 3D ground truth annotations.

Segmentation of elongated objects using attribute profiles and area stability: Application to melanocyte segmentation in engineered skin

In this paper, a method to segment elongated objects is proposed. It is based on attribute profiles and area stability. Images are represented as component trees using a threshold decomposition. Then, some attributes are computed on each node of the tree. Finally, the attribute profile is analyzed to identify important events useful for segmentation tasks. In this work, a new attribute, combining geodesic elongation and area stability is defined. This methodology is successfully applied to the segmentation of cells in multiphoton fluorescence microscopy images of engineered skin. Quantitative results are provided, demonstrating the performance and robustness of the new attribute. A comparison with MSER is also given.

Segmentation and Classification of 3D Urban Point Clouds: Comparison and Combination of Two Approaches

Segmentation and classification of 3D urban point clouds is a complex task, making it very difficult for any single method to overcome all the diverse challenges offered. This sometimes requires the combination of several techniques to obtain the desired results for different applications. This work presents and compares two different approaches for segmenting and classifying 3D urban point clouds. In the first approach, detection, segmentation and classification of urban objects from 3D point clouds, converted into elevation images, are performed by using mathematical morphology. First, the ground is segmented and objects are detected as discontinuities on the ground. Then, connected objects are segmented using a watershed approach. Finally, objects are classified using SVM (Support Vector Machine) with geometrical and contextual features. The second method employs a super-voxel based approach in which the 3D urban point cloud is first segmented into voxels and then converted into super-voxels. These are then clustered together using an efficient link-chain method to form objects. These segmented objects are then classified using local descriptors and geometrical features into basic object classes. Evaluated on a common dataset (real data), both these methods are thoroughly compared on three different levels: detection, segmentation and classification. After analyses, simple strategies are also presented to combine the two methods, exploiting their complementary strengths and weaknesses, to improve the overall segmentation and classification results.

Paris-rue-Madame Database

This paper describes a publicly available 3D database from the rue Madame, a street in the 6th Parisian district. Data have been acquired by the Mobile Laser Scanning (MLS) system L3D2 and correspond to a 160 m long street section. Annotation has been carried out in a manually assisted way. An initial annotation is obtained using an automatic segmentation algorithm. Then, a manual refinement is done and a label is assigned to each segmented object. Finally, a class is also manually assigned to each object. Available classes include facades, ground, cars, motorcycles, pedestrians, traffic signs, among others. The result is a list of (X, Y, Z, reflectance, label, class) points. Our aim is to offer, to the scientific community, a 3D manually labeled dataset for detection, segmentation and classification benchmarking. With respect to other databases available in the state of the art, this dataset has been exhaustively annotated in order to include all available objects and to allow point-wise comparison.

Ultimate Opening Combined with Area Stability Applied to Urban Scenes

This paper explores the use of ultimate opening in urban analysis context. It demonstrates the efficiency of this approach for street level elevation images, derived from 3D point clouds acquired by terrestrial mobile mapping systems. An area-stability term is introduced in the residual definition, reducing the over-segmentation of the vegetation while preserving small significant regions.