Next Article in Journal
Geographically Weighted Machine Learning and Downscaling for High-Resolution Spatiotemporal Estimations of Wind Speed
Next Article in Special Issue
Remote Sensing Big Data Classification with High Performance Distributed Deep Learning
Previous Article in Journal
A Novel Effectively Optimized One-Stage Network for Object Detection in Remote Sensing Imagery
Previous Article in Special Issue
Domain Adversarial Neural Networks for Large-Scale Land Cover Classification
Open AccessArticle

Automatic Detection of Track and Fields in China from High-Resolution Satellite Images Using Multi-Scale-Fused Single Shot MultiBox Detector

1
Airborne Remote Sensing Center, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China
2
College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China
3
Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2019, 11(11), 1377; https://doi.org/10.3390/rs11111377
Received: 20 April 2019 / Revised: 28 May 2019 / Accepted: 3 June 2019 / Published: 10 June 2019
(This article belongs to the Special Issue Analysis of Big Data in Remote Sensing)
Object detection is facing various challenges as an important aspect in the field of remote sensing—especially in large scenes due to the increase of satellite image resolution and the complexity of land covers. Because of the diversity of the appearance of track and fields, the complexity of the background and the variety between satellite images, even superior deep learning methods have difficulty extracting accurate characteristics of track and field from large complex scenes, such as the whole of China. Taking track and field as a study case, we propose a stable and accurate method for target detection. Firstly, we add the “deconvolution” and “concat” module to the structure of the original Single Shot MultiBox Detector (SSD), where Visual Geometry Group 16 (VGG16) is served as a basic network, followed by multiple convolution layers. The two modules are used to sample the high-level feature map and connect it with the low-level feature map to form a new network structure multi-scale-fused SSD (abbreviated as MSF_SSD). MSF-SSD can enrich the semantic information of the low-level feature, which is especially effective for small targets in large scenes. In addition, a large number of track and fields are collected as samples for the whole China and a series of parameters are designed to optimize the MSF_SSD network through the deep analysis of sample characteristics. Finally, by using MSF_SSD network, we achieve the rapid and automatic detection of meter-level track and fields in the country for the first time. The proposed MSF_SSD model achieves 97.9% mean average precision (mAP) on validation set which is superior to the 88.4% mAP of the original SSD. Apart from this, the model can achieve an accuracy of 94.3% while keeping the recall rate in a high level (98.8%) in the nationally distributed test set, outperforming the original SSD method. View Full-Text
Keywords: object detection; convolutional neural network; multi-scale-fused SSD; track and field; China; high-resolution satellite images object detection; convolutional neural network; multi-scale-fused SSD; track and field; China; high-resolution satellite images
Show Figures

Graphical abstract

MDPI and ACS Style

Chen, Z.; Lu, K.; Gao, L.; Li, B.; Gao, J.; Yang, X.; Yao, M.; Zhang, B. Automatic Detection of Track and Fields in China from High-Resolution Satellite Images Using Multi-Scale-Fused Single Shot MultiBox Detector. Remote Sens. 2019, 11, 1377.

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