On the classification of passenger cars in airborne SAR images using simulated training data and a convolutional neural network

Horst Hammer; Klaus Hoffmann; Karsten Schulz

doi:10.1117/12.2324719

Translator Disclaimer

9 October 2018 On the classification of passenger cars in airborne SAR images using simulated training data and a convolutional neural network

Horst Hammer, Klaus Hoffmann, Karsten Schulz

Author Affiliations +

Proceedings Volume 10789, Image and Signal Processing for Remote Sensing XXIV; 107890P (2018) https://doi.org/10.1117/12.2324719
Event: SPIE Remote Sensing, 2018, Berlin, Germany

Abstract

SAR sensors play an important role in different fields of remote sensing. One of these is Automatic Target Recognition (ATR). In this paper, a new dataset for ATR is introduced, consisting of five classes of passenger cars imaged by SmartRadar of Hensoldt Sensors GmbH. The basic characteristics of the dataset and some details of the measurement campaign are provided. The second part of the paper deals with the creation of a sufficiently large database of training samples to train a Convolutional Neural Network (CNN) to classify these cars. Since training data are not as readily available as in the EO case, training data are simulated using the CohRaS SAR simulator of Fraunhofer IOSB, which is also briefly described. The basic setup of the CNN used for the classification task is outlined and some issues arising in the classification of the training data are discussed. The paper also contains some very preliminary classification results using the CNN and the simulated training data, and a discussion of these results.

Citation Download Citation

Horst Hammer, Klaus Hoffmann, and Karsten Schulz "On the classification of passenger cars in airborne SAR images using simulated training data and a convolutional neural network", Proc. SPIE 10789, Image and Signal Processing for Remote Sensing XXIV, 107890P (9 October 2018); https://doi.org/10.1117/12.2324719

ACCESS THE FULL ARTICLE