Next Article in Journal
The Outlining of Agricultural Plots Based on Spatiotemporal Consensus Segmentation
Next Article in Special Issue
Hyperspectral Feature Extraction Using Sparse and Smooth Low-Rank Analysis
Previous Article in Journal
Spatiotemporal Evolution of Postseismic Deformation Following the 2001 Mw7.8 Kokoxili, China, Earthquake from 7 Years of Insar Observations
Previous Article in Special Issue
Hyperspectral and LiDAR Fusion Using Deep Three-Stream Convolutional Neural Networks
Open AccessFeature PaperArticle

MsRi-CCF: Multi-Scale and Rotation-Insensitive Convolutional Channel Features for Geospatial Object Detection

by 1,2,†, 3,4,†, 5, 1,2 and 1,2,*
1
School of Information and Electronics, Beijing Institute of Technology (BIT), Beijing 100081, China
2
Beijing Key Laboratory of Fractional Signals and Systems, School of Information and Electronics, Beijing Institute of Technology (BIT), Beijing 100081, China
3
Remote Sensing Technology Institute (IMF), German Aerospace Center (DLR), 82234 Wessling, Germany
4
Signal Processing in Earth Observation (SiPEO), Technical University of Munich (TUM), 80333 Munich, Germany
5
Machine Learning Group, Exploration Division, Helmholtz Institute Freiberg for Resource Technology, Helmholtz-Zentrum Dresden-Rossendorf, 09599 Freiberg, Germany
*
Author to whom correspondence should be addressed.
These authors contributed equally to this work.
Remote Sens. 2018, 10(12), 1990; https://doi.org/10.3390/rs10121990
Received: 5 November 2018 / Revised: 4 December 2018 / Accepted: 6 December 2018 / Published: 8 December 2018
Geospatial object detection is a fundamental but challenging problem in the remote sensing community. Although deep learning has shown its power in extracting discriminative features, there is still room for improvement in its detection performance, particularly for objects with large ranges of variations in scale and direction. To this end, a novel approach, entitled multi-scale and rotation-insensitive convolutional channel features (MsRi-CCF), is proposed for geospatial object detection by integrating robust low-level feature generation, classifier generation with outlier removal, and detection with a power law. The low-level feature generation step consists of rotation-insensitive and multi-scale convolutional channel features, which were obtained by learning a regularized convolutional neural network (CNN) and integrating multi-scaled convolutional feature maps, followed by the fine-tuning of high-level connections in the CNN, respectively. Then, these generated features were fed into AdaBoost (chosen due to its lower computation and storage costs) with outlier removal to construct an object detection framework that facilitates robust classifier training. In the test phase, we adopted a log-space sampling approach instead of fine-scale sampling by using the fast feature pyramid strategy based on a computable power law. Extensive experimental results demonstrate that compared with several state-of-the-art baselines, the proposed MsRi-CCF approach yields better detection results, with 90.19% precision with the satellite dataset and 81.44% average precision with the NWPU VHR-10 datasets. Importantly, MsRi-CCF incurs no additional computational cost, which is only 0.92 s and 0.7 s per test image on the two datasets. Furthermore, we determined that most previous methods fail to gain an acceptable detection performance, particularly when they face several obstacles, such as deformations in objects (e.g., rotation, illumination, and scaling). Yet, these factors are effectively addressed by MsRi-CCF, yielding a robust geospatial object detection method. View Full-Text
Keywords: AdaBoost; deep learning; object detection; optical remote sensing imagery; outlier removal; multi-scale aggregation; rotation-insensitive AdaBoost; deep learning; object detection; optical remote sensing imagery; outlier removal; multi-scale aggregation; rotation-insensitive
Show Figures

Figure 1

MDPI and ACS Style

Wu, X.; Hong, D.; Ghamisi, P.; Li, W.; Tao, R. MsRi-CCF: Multi-Scale and Rotation-Insensitive Convolutional Channel Features for Geospatial Object Detection. Remote Sens. 2018, 10, 1990.

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

1
Back to TopTop