skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information
  1. Vehicle track identification in synthetic aperture radar images

    Various technologies pertaining to identification of vehicle tracks in synthetic aperture radar coherent change detection image data are described herein. Coherent change detection images are analyzed in a parameter space using Radon transforms. Peaks of the Radon transforms correspond to features of interest, including vehicle tracks, which are identified and classified. New coherent change detection images in which the features of interest and their characteristics are signified are then generated using inverse Radon transforms.
  2. Terrain detection and classification using single polarization SAR

    The various technologies presented herein relate to identifying manmade and/or natural features in a radar image. Two radar images (e.g., single polarization SAR images) can be captured for a common scene. The first image is captured at a first instance and the second image is captured at a second instance, whereby the duration between the captures are of sufficient time such that temporal decorrelation occurs for natural surfaces in the scene, and only manmade surfaces, e.g., a road, produce correlated pixels. A LCCD image comprising the correlated and decorrelated pixels can be generated from the two radar images. A medianmore » image can be generated from a plurality of radar images, whereby any features in the median image can be identified. A superpixel operation can be performed on the LCCD image and the median image, thereby enabling a feature(s) in the LCCD image to be classified.« less
  3. Scalable Track Detection in SAR CCD Images

    Existing methods to detect vehicle tracks in coherent change detection images, a product of combining two synthetic aperture radar images ta ken at different times of the same scene, rely on simple, fast models to label track pixels. These models, however, are often too simple to capture natural track features such as continuity and parallelism. We present a simple convolutional network architecture consisting of a series of 3-by-3 convolutions to detect tracks. The network is trained end-to-end to learn natural track features entirely from data. The network is computationally efficient and improves the F-score on a standard dataset to 0.988,more » up fr om 0.907 obtained by the current state-of-the-art method.« less
  4. MISB EG 1206.1 :

    Abstract not provided.
  5. Road Segmentation using Multipass Single-Pol Synthetic Aperture Radar Imagery.

    Abstract not provided.

Search for:
All Records
Creator / Author
"Chow, James G"

Refine by:
Resource Type
Publication Date
Creator / Author
Research Organization