Semi-Automatic Objects Recognition in Urban Areas Based on Fuzzy Logic

Abstract

Three dimensional object extraction and recognition (OER) from geographic data has been definitely one of more important topic in photogrammetry for quite a long time. Today, the capability of rapid generating high-density DSM increases the supply of geographic information but the discrete nature of the measuring makes more difficult to recognize correctly and to extract 3D objects from these surface. The proposed methodology wants to semi-automate some geographic objects clustering operations, in order to perform the recognition process. The clustering is a subjective process; the same set of data items often needs to be partitioned differently based on the application. Fuzzy logic gives the possibility to use in a mathematical process the uncertain information typical of human reasoning. The concept at the base of our proposal is to use the information contained in Image Matching or LiDAR DSM, and typically understood by the human operator, in a fuzzy recognition process able to combine the different input in order to perform the classification. So the object recognition approach proposed in our workflow integrates 3D structural descriptive components of objects, extracted from DSM, into a fuzzy reasoning process in order to exploit more fully all available information, which can contribute to the extraction and recognition process and, to handling the object's vagueness. The recognition algorithm has been tested with to different data set and different objectives. An important issue is to apply the typical human process which allows to recognize objects in a range image in a fuzzy reasoning process. The investigations presented here have given a first demonstration of the capability of this approach.

Performance Evaluation of Machine Learning Algorithms for Urban Pattern Recognition from Multi-spectral Satellite Images

“…It can be inferred from the literature that machine learning algorithms (both parametric and non-parametric) have mainly been used as per-pixel classifiers in remote sensing image analysis [4]. For the classification of image segments, many studies so far have used fuzzy set theory-based expert systems [17,18]. Expert systems are considered to have a great potential for image classification when also considering ancillary data [4].…”

Towards a methodology for 3D content models: The reconstruction of ancient vaults for maintenance and structural behaviour in the logic of BIM management

“…Image Segmentation, Spin-Images algorithms techniques, and homogeneous pattern analysis techniques will contribute to feature extraction methodologies, that need to improve semantic and qualitative aspects already applied for 3D city modelling [12]. The 3D vault surface model has been reconstructed using the laser scanner points (Rapidform XO64©); the 3D model reconstruction on the profiles for the Object generation has been obtained with AutoCad 3D functionalities and with Rhino© (case studies carried out by the students), in order to facilitate simplified object generation process and elaboration within Revit BIM data management.…”

Open Access to Historical Atlas: Sources of Information and Services for Landscape Analysis in an SDI Framework

“…Suitable remote sensing image interpretation techniques can give precious information on the water content, wet areas, river beds line detection, secondary channel recognition, morphological modifications: it has been giving the first examples of how remotely sensed digital imagery could have the potential to allow panoptic mapping of river hydro-morphology and human impacts [21], as well as the feasibility for fluvial morphology assessment in the San Francisco river [22]. Furthermore, automatic classification algorithms and feature extraction [23], could be experimented in recognition of ancient riverbed traces. The objective here is to demonstrate the potential of the functionalities of the Atl@s and of the services available: tools for an integrated multi-source data analysis have been provided, enabling remote sensing images and products, distributed on the web by WMSs, to be added as new layers and visualized on basic historic maps.…”