| 1. |
- Campos, Alexandre B., et al.
(författare)
-
Adaptive Target Enhancer : Bridging the Gap between Synthetic and Measured SAR Images for Automatic Target Recognition
- 2023
-
Ingår i: Proceedings of the IEEE Radar Conference. - : Institute of Electrical and Electronics Engineers (IEEE). - 9781665436694
-
Konferensbidrag (refereegranskat)abstract
- Automatic target recognition (ATR) algorithms have been successfully used for vehicle classification in synthetic aperture radar (SAR) images over the past few decades. For this application, however, the scarcity of labeled data is often a limiting factor for supervised approaches. While the advent of computer-simulated images may result in additional data for ATR, there is still a substantial gap between synthetic and measured images. In this paper, we propose the so-called adaptive target enhancer (ATE), a tool designed to automatically delimit and weight the region of an image that contains or is affected by the presence of a target. Results for the publicly released Synthetic and Measured Paired and Labeled Experiment (SAMPLE) dataset show that, by defining regions of interest and suppressing the background, we can increase the classification accuracy from 68% to 84% while only using artificially generated images for training. © 2023 IEEE.
|
|
| 2. |
- Molin, Ricardo D., Jr., et al.
(författare)
-
A CHANGE DETECTION ALGORITHM FOR SAR IMAGES BASED ON LOGISTIC REGRESSION
- 2019
-
Ingår i: 2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019). - : IEEE. - 9781538691540 ; , s. 1514-1517
-
Konferensbidrag (refereegranskat)abstract
- This paper presents an incoherent change detection algorithm (CDA) for synthetic aperture radar (SAR) images based on logistic regression. The input data consists of a set of 24 SAR images acquired in a test site in northern Sweden [1]. Subsets of these images are trained based on pixel amplitude, flight heading and neighboring features such as local mean, standard deviation and skewness. The proposed method intends to explore the advantadges from both pixel- and object-based approaches, while evaluating multiple features in amplitude only SAR images. Preliminary results based on K-fold cross validation have shown that the proposed CDA achieves good performance when compared to the results presented in [1].
|
|
