Convolutional networks for vehicle track segmentation
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
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, 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-by-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, efficient networks that can be trained end-to-end to learn natural track features entirely from limited training data. We demonstrate that our 6-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.
- Research Organization:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)
- Grant/Contract Number:
- AC04-94AL85000
- OSTI ID:
- 1399516
- Report Number(s):
- SAND-2017-7708J; 655673
- Journal Information:
- Jounral of Applied Remote Sensing, Vol. 11, Issue 04; ISSN 1931-3195
- Publisher:
- SPIECopyright Statement
- Country of Publication:
- United States
- Language:
- English
Web of Science
Similar Records
Using Machine Learning to Track Objects Across Cameras
What’s the Difference? The Potential for Convolutional Neural Networks for Transient Detection without Template Subtraction