Vehicle detection in high resolution satellite images with joint-layer deep convolutional neural networks

Vehicle detection can provide volumes of useful data for city planning and transport management. It has always been a challenging task because of various complicated backgrounds and the relatively small sizes of targets, especially in high resolution satellite images. A novel model called joint-layer deep convolutional neural networks (JLDCNNs), which joins features in the higher layers and the lower layers of deep convolutional neural networks (DCNNs), is proposed in this paper. JLDCNNs aim to cover different scales and detect vehicles from complex satellite images rapidly by overcoming the insufficient feature extraction of traditional DCNNs. The model is evaluated and compared with traditional DCNNs and other methods on our challenging dataset which includes 20 high resolution satellite images (including over 2400 vehicles) collected from Google Earth. JLDCNNs significantly improve the precision rate by 16% and the recall rate by 6% compared with traditional DCNNs, let alone outperform other traditional methods.

[1]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Xian Sun,et al.  Automatic Detection of Geospatial Objects Using Taxonomic Semantics , 2010, IEEE Geoscience and Remote Sensing Letters.

[3]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Gellért Máttyus,et al.  Fast Multiclass Vehicle Detection on Aerial Images , 2015, IEEE Geoscience and Remote Sensing Letters.

[6]  John C. Platt,et al.  A Convolutional Neural Network Hand Tracker , 1994, NIPS.

[7]  Lawrence D. Jackel,et al.  Reading handwritten digits: a ZIP code recognition system , 1992, Computer.

[8]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Shiming Xiang,et al.  Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks , 2014, IEEE Geoscience and Remote Sensing Letters.

[10]  Ramakant Nevatia,et al.  Car detection in low resolution aerial images , 2003, Image Vis. Comput..

[11]  Horst Bischof,et al.  On-line Boosting for Car Detection from Aerial Images , 2007, 2007 IEEE International Conference on Research, Innovation and Vision for the Future.

[12]  R. Vaillant,et al.  Original approach for the localisation of objects in images , 1994 .

[13]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[14]  Yann LeCun,et al.  Pedestrian Detection with Unsupervised Multi-stage Feature Learning , 2012, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Christophe Garcia,et al.  Convolutional face finder: a neural architecture for fast and robust face detection , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Ramakant Nevatia,et al.  Car detection in low resolution aerial image , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[17]  Horst Bischof,et al.  On-line boosting-based car detection from aerial images , 2008 .

[18]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[19]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.