SHADOWDETECTION FROM VHR AERIAL IMAGES IN URBAN AREA BY USING 3D CITY MODELS AND A DECISION FUSION APPROACH

In VHR(very high resolution) aerial images, shadows indicating height information are valuable for validating or detecting changes on an existing 3D city model. In the paper, we propose a novel and full automatic approach for shadow detection from VHR images. Instead of automatic thresholding, the supervised machine learning approach is expected with better performance on shadow detection, but it requires to obtain training samples manually. The shadow image reconstructed from an existing 3D city model can provide free training samples with large variety. However, as the 3D model is often not accuracy, incomplete and outdated, a small portion of training samples are mislabeled. The erosion morphology is provided to remove boundary pixels which have high mislabeling possibility from the reconstructed image. Moreover, the quadratic discriminant analysis (QDA) which is resistant to the mislabeling is chosen. Further, two feature domains, RGB and ratio of the hue over the intensity, are analyzed to have complementary effects on better detecting different objects. Finally, a decision fusion approach is proposed to combine the results wisely from preliminary classifications from two feature domains. The fuzzy membership is a confidence measurement and determines the way of making decision, in the meanwhile the memberships are weighted by an entropy measurements to indicate their certainties. The experimental results on two cities in the Netherlands demonstrate that the proposed approach outperforms the two separate classifiers and two stacked-vector fusion approaches.

Download Full-text

Semi-Automatic 3D City Model Generation from Large-Format Aerial Images

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi7090339 ◽

2018 ◽

Vol 7 (9) ◽

pp. 339 ◽

Cited By ~ 8

Author(s):

Mehmet Buyukdemircioglu ◽

Sultan Kocaman ◽

Umit Isikdag

Keyword(s):

Large Scale ◽

3D Visualization ◽

Aerial Images ◽

Model Generation ◽

City Management ◽

Large Format ◽

3D City Models ◽

3D City Model ◽

City Model ◽

City Models

3D city models have become crucial for better city management, and can be used for various purposes such as disaster management, navigation, solar potential computation and planning simulations. 3D city models are not only visual models, and they can also be used for thematic queries and analyzes with the help of semantic data. The models can be produced using different data sources and methods. In this study, vector basemaps and large-format aerial images, which are regularly produced in accordance with the large scale map production regulations in Turkey, have been used to develop a workflow for semi-automatic 3D city model generation. The aim of this study is to propose a procedure for the production of 3D city models from existing aerial photogrammetric datasets without additional data acquisition efforts and/or costly manual editing. To prove the methodology, a 3D city model has been generated with semi-automatic methods at LoD2 (Level of Detail 2) of CityGML (City Geographic Markup Language) using the data of the study area over Cesme Town of Izmir Province, Turkey. The generated model is automatically textured and additional developments have been performed for 3D visualization of the model on the web. The problems encountered throughout the study and approaches to solve them are presented here. Consequently, the approach introduced in this study yields promising results for low-cost 3D city model production with the data at hand.

Download Full-text

Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

10.26434/chemrxiv.5513581.v1 ◽

2017 ◽

Author(s):

Sabrina Jaeger ◽

Simone Fulle ◽

Samo Turk

Keyword(s):

Machine Learning ◽

Language Processing ◽

Supervised Machine Learning ◽

Learning Approach ◽

Learning Approaches ◽

Unsupervised Machine Learning ◽

Feature Representations ◽

Machine Learning Approach ◽

The Individual ◽

Vector Representations

Inspired by natural language processing techniques we here introduce Mol2vec which is an unsupervised machine learning approach to learn vector representations of molecular substructures. Similarly, to the Word2vec models where vectors of closely related words are in close proximity in the vector space, Mol2vec learns vector representations of molecular substructures that are pointing in similar directions for chemically related substructures. Compounds can finally be encoded as vectors by summing up vectors of the individual substructures and, for instance, feed into supervised machine learning approaches to predict compound properties. The underlying substructure vector embeddings are obtained by training an unsupervised machine learning approach on a so-called corpus of compounds that consists of all available chemical matter. The resulting Mol2vec model is pre-trained once, yields dense vector representations and overcomes drawbacks of common compound feature representations such as sparseness and bit collisions. The prediction capabilities are demonstrated on several compound property and bioactivity data sets and compared with results obtained for Morgan fingerprints as reference compound representation. Mol2vec can be easily combined with ProtVec, which employs the same Word2vec concept on protein sequences, resulting in a proteochemometric approach that is alignment independent and can be thus also easily used for proteins with low sequence similarities.

Download Full-text