Abstract
In this paper, a new Region-based Convolutional Neural Networks (RCNN) method is proposed for target recognition in large scene synthetic aperture radar (SAR) images. To locate and recognize the targets in SAR images, there are three steps in the traditional procedure: detection, discrimination, classification and recognition. Each step is supposed to provide optimal processing results for the next step, but this is difficult to implement in real-life applications because of speckle noise and inefficient connection among these procedures. To solve this problem, the RCNN is applied to large scene SAR target recognition, which can detect the objects while recognizing their classes based on its regression method and the sharing network structure. However, size of the input images to RCNN is limited so that the classification could be accomplished, which leads to a problem that RCNN is not able to handle the large scene SAR images directly. Thus, before the RCNN, a fast sliding method is proposed to segment the scene image into sub-images with suitable size and avoid dividing targets into different sub-images. After the RCNN, candidate regions on different slices are predicted. To locate targets on large scene SAR images from these candidate regions on small slices, the Non-maximum Suppression between Regions (NMSR) is proposed, which could find the most proper candidate region among all the overlapped regions. Experiments on 1476 × 1784 simulated MSTAR images of simple scenes and complex scenes show that the proposed method can recognize all targets with the best accuracy and fastest speed, and outperform the other methods, such as constant false alarm rate (CFAR) detector + support vector machine (SVM), Visual Attention+SVM, and Sliding-RCNN.
Highlights
Spaceborne and airborne synthetic aperture radar (SAR) is able to operate in all-weather all-time conditions to generate high resolution SAR images; SAR has been widely used both in military and civil fields
In order to evaluate the accuracy of candidate regions generated by the region proposal network in our CNN network, an untrained slice of T72 in Moving and Stationary Target Acquisition and Recognition (MSTAR) data set is used as test sample, as Figure 10 shows
Inspired by great success of deep convolutional neural networks, methods of DCNN are applied to SAR image interpretation to extract features automatically, and a method to integrate detection and recognition of large scene SAR images based on non-maximum suppression between regions (NMSR) is proposed in this paper
Summary
Spaceborne and airborne synthetic aperture radar (SAR) is able to operate in all-weather all-time conditions to generate high resolution SAR images; SAR has been widely used both in military and civil fields. In the past few years, most researchers just focused on one part of these three stages, put forward theories such as scene segmentation, target discrimination, feature extraction, classifier design and so on These theories and algorithms just out-perform in specific operating conditions, which makes them not able to be applied universally. A reliable and universal system requires effective connection between detection and recognition, so End-to-End models were proposed [7,8], and apply robust trainable classifiers, such as Adaboost and support vector machine (SVM) [9,10,11] to realize SAR ATR. Liu proposed Single Shot MultiBox Detector (SSD), which was a compromise in accuracy and speed between Faster R-CNN and YOLO [16] Inspired by these advanced methods, many researchers tried to introduce deep learning methods into the field of SAR target detection and recognition to solve problems in End-to-End models.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
