Combining high-speed SVM learning with CNN feature encoding for real-time target recognition in high-definition video for ISR missions

Christine Kroll; Monika von der Werth; Holger Leuck; Christoph Stahl; Klaus Schertler

doi:10.1117/12.2262064

Translator Disclaimer

1 May 2017 Combining high-speed SVM learning with CNN feature encoding for real-time target recognition in high-definition video for ISR missions

Christine Kroll, Monika von der Werth, Holger Leuck, Christoph Stahl, Klaus Schertler

Author Affiliations +

Proceedings Volume 10202, Automatic Target Recognition XXVII; 1020208 (2017) https://doi.org/10.1117/12.2262064
Event: SPIE Defense + Security, 2017, Anaheim, California, United States

Abstract

For Intelligence, Surveillance, Reconnaissance (ISR) missions of manned and unmanned air systems typical electrooptical payloads provide high-definition video data which has to be exploited with respect to relevant ground targets in real-time by automatic/assisted target recognition software. Airbus Defence and Space is developing required technologies for real-time sensor exploitation since years and has combined the latest advances of Deep Convolutional Neural Networks (CNN) with a proprietary high-speed Support Vector Machine (SVM) learning method into a powerful object recognition system with impressive results on relevant high-definition video scenes compared to conventional target recognition approaches. This paper describes the principal requirements for real-time target recognition in high-definition video for ISR missions and the Airbus approach of combining an invariant feature extraction using pre-trained CNNs and the high-speed training and classification ability of a novel frequency-domain SVM training method. The frequency-domain approach allows for a highly optimized implementation for General Purpose Computation on a Graphics Processing Unit (GPGPU) and also an efficient training of large training samples. The selected CNN which is pre-trained only once on domain-extrinsic data reveals a highly invariant feature extraction. This allows for a significantly reduced adaptation and training of the target recognition method for new target classes and mission scenarios. A comprehensive training and test dataset was defined and prepared using relevant high-definition airborne video sequences. The assessment concept is explained and performance results are given using the established precision-recall diagrams, average precision and runtime figures on representative test data. A comparison to legacy target recognition approaches shows the impressive performance increase by the proposed CNN+SVM machine-learning approach and the capability of real-time high-definition video exploitation.

Citation Download Citation

Christine Kroll, Monika von der Werth, Holger Leuck, Christoph Stahl, and Klaus Schertler "Combining high-speed SVM learning with CNN feature encoding for real-time target recognition in high-definition video for ISR missions", Proc. SPIE 10202, Automatic Target Recognition XXVII, 1020208 (1 May 2017); https://doi.org/10.1117/12.2262064

ACCESS THE FULL ARTICLE