Abstract
This paper presents a new solution for SAR image target recognition by designing a light level convolutional neural network (CNN), and raises an unsupervised detection method by taking the advantages of convolutional features. Firstly, we train a shallow convolutional network by using Moving and Stationary Target Recognition (MSTAR) dataset to classify SAR targets. Then, we extract the outputs of the convolutional layers, and locate the position of the target in the image by the max sampling and clustering. Tested on the MSTAR data set, our method gets satisfied accuracy in classify task, and realizes unsupervised target detection effectively.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.