COMBINED USE OF MULTIMODAL SIMILARITY MEASURES FOR VISUAL TO RADAR IMAGE REGISTRATION

Abstract : This paper deals with the problem of measuring similarity between visual and radar remote sensing images. It is proposed to combine the benefits of a finite set of representative Similarity Measures (SM) to obtain a combined SM with improved performance in terms of usual assessment criteria (ROC, AUC and LR+). This combined SM relies on a binary linear support vector machines (SVM) classifier trained using real visual-to-radar image pairs RS images. The best combination of SMs among those considered in the finite set is found to be SIFT-OCT, MIND and logLR SMs. It reaches a value of AUC criterion about 0.05 higher than that obtained by the best individual SM. This obtained gain is mainly attributed to the complementary properties of structural (SIFT-OCT, MIND) and area-based (logLR) SMs.
Document type :
Conference papers
Complete list of metadatas

https://hal-univ-rennes1.archives-ouvertes.fr/hal-02018924
Contributor : Laurent Jonchère <>
Submitted on : Thursday, February 14, 2019 - 11:26:13 AM
Last modification on : Thursday, February 21, 2019 - 3:41:28 PM

Identifiers

  • HAL Id : hal-02018924, version 1

Citation

M. L. Uss, B. Vozel, V. V. Lukin, K. Chehdi. COMBINED USE OF MULTIMODAL SIMILARITY MEASURES FOR VISUAL TO RADAR IMAGE REGISTRATION. 38th IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Jul 2018, Valencia, Spain. ⟨hal-02018924⟩

Share

Metrics

Record views

26