Next Article in Journal
Spatio-Temporal Mapping of Multi-Satellite Observed Column Atmospheric CO2 Using Precision-Weighted Kriging Method
Previous Article in Journal
Advancing High-Throughput Phenotyping of Wheat in Early Selection Cycles
Previous Article in Special Issue
Convolutional Neural Network for Remote-Sensing Scene Classification: Transfer Learning Analysis
Open AccessArticle

A Method for Vehicle Detection in High-Resolution Satellite Images that Uses a Region-Based Object Detector and Unsupervised Domain Adaptation

1
Independent Researcher
2
Center for Spatial Information Science (CSIS), University of Tokyo, 5-1-5 Kashiwanoha, Kashiwa-shi, Chiba 2790000, Japan
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(3), 575; https://doi.org/10.3390/rs12030575
Received: 31 December 2019 / Revised: 28 January 2020 / Accepted: 5 February 2020 / Published: 9 February 2020
(This article belongs to the Special Issue Deep Transfer Learning for Remote Sensing)
Recently, object detectors based on deep learning have become widely used for vehicle detection and contributed to drastic improvement in performance measures. However, deep learning requires much training data, and detection performance notably degrades when the target area of vehicle detection (the target domain) is different from the training data (the source domain). To address this problem, we propose an unsupervised domain adaptation (DA) method that does not require labeled training data, and thus can maintain detection performance in the target domain at a low cost. We applied Correlation alignment (CORAL) DA and adversarial DA to our region-based vehicle detector and improved the detection accuracy by over 10% in the target domain. We further improved adversarial DA by utilizing the reconstruction loss to facilitate learning semantic features. Our proposed method achieved slightly better performance than the accuracy achieved with the labeled training data of the target domain. We demonstrated that our improved DA method could achieve almost the same level of accuracy at a lower cost than non-DA methods with a sufficient amount of labeled training data of the target domain. View Full-Text
Keywords: vehicle detection; domain adaptation; satellite images; single shot multibox detector (SSD); adversarial training; CORAL; reconstruction loss vehicle detection; domain adaptation; satellite images; single shot multibox detector (SSD); adversarial training; CORAL; reconstruction loss
Show Figures

Graphical abstract

MDPI and ACS Style

Koga, Y.; Miyazaki, H.; Shibasaki, R. A Method for Vehicle Detection in High-Resolution Satellite Images that Uses a Region-Based Object Detector and Unsupervised Domain Adaptation. Remote Sens. 2020, 12, 575.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop