19 August 2017 Convolutional networks for vehicle track segmentation
Author Affiliations +
Abstract
Existing methods to detect vehicle tracks in coherent change detection images, a product of combining two synthetic aperture radar images taken at different times of the same scene, rely on simple and fast models to label track pixels. These models, however, are unable to capture natural track features, such as continuity and parallelism. More powerful but computationally expensive models can be used in offline settings. We present an approach that uses dilated convolutional networks consisting of a series of 3×3 convolutions to segment vehicle tracks. The design of our networks considers the fact that remote sensing applications tend to operate in low power and have limited training data. As a result, we aim for small and efficient networks that can be trained end-to-end to learn natural track features entirely from limited training data. We demonstrate that our six-layer network, trained on just 90 images, is computationally efficient and improves the F-score on a standard dataset to 0.992, up from 0.959 obtained by the current state-of-the-art method.
© 2017 Society of Photo-Optical Instrumentation Engineers (SPIE) 1931-3195/2017/$25.00 © 2017 SPIE
Tu-Thach Quach "Convolutional networks for vehicle track segmentation," Journal of Applied Remote Sensing 11(4), 042603 (19 August 2017). https://doi.org/10.1117/1.JRS.11.042603
Received: 5 April 2017; Accepted: 18 July 2017; Published: 19 August 2017
Lens.org Logo
CITATIONS
Cited by 4 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Convolution

Synthetic aperture radar

Remote sensing

Charge-coupled devices

Network architectures

Binary data

Back to Top