Skip to main content
main-content

Tipp

Weitere Artikel dieser Ausgabe durch Wischen aufrufen

Erschienen in: Neural Processing Letters 3/2019

30.06.2018

A Comparison: Different DCNN Models for Intelligent Object Detection in Remote Sensing Images

verfasst von: Peng Ding, Ye Zhang, Ping Jia, Xu-ling Chang

Erschienen in: Neural Processing Letters | Ausgabe 3/2019

Einloggen, um Zugang zu erhalten
share
TEILEN

Abstract

In recent years, deep learning especially deep convolutional neural networks (DCNN) has made great progress. Many researchers take advantage of different DCNN models to do object detection in remote sensing. Different DCNN models have different advantages and disadvantages. But in the field of remote sensing, many scholars usually do comparison between DCNN models and traditional machine learning. In this paper, we compare different state-of-the-art DCNN models mainly over two publicly available remote sensing datasets—airplane dataset and car dataset. Such comparison can provide guidance for related researchers. Besides,we provide suggestions for fine-tuning different DCNN models. Moreover, for DCNN models including fully connected layers, we provide a method to save storage space.
Literatur
1.
Zurück zum Zitat Hong C, Yu J, Wan J, Tao D, Wang M (2015) multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659–5670 MathSciNetCrossRefMATH Hong C, Yu J, Wan J, Tao D, Wang M (2015) multimodal deep autoencoder for human pose recovery. IEEE Trans Image Process 24(12):5659–5670 MathSciNetCrossRefMATH
2.
Zurück zum Zitat Hong C, Yu J, Chen X (2013) Image-based 3D human pose recovery with locality sensitive sparse retrieval. In: Systems, man and cybernetics, pp 2103–2108 Hong C, Yu J, Chen X (2013) Image-based 3D human pose recovery with locality sensitive sparse retrieval. In: Systems, man and cybernetics, pp 2103–2108
5.
Zurück zum Zitat Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324 CrossRef Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324 CrossRef
6.
Zurück zum Zitat Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958 MathSciNetMATH Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958 MathSciNetMATH
7.
Zurück zum Zitat Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: AISTATS, pp 315–323 Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: AISTATS, pp 315–323
8.
Zurück zum Zitat Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich (2015) A Going deeper with convolutions. In: Computer vision and pattern recognition, pp 1–9 Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich (2015) A Going deeper with convolutions. In: Computer vision and pattern recognition, pp 1–9
9.
Zurück zum Zitat He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. In: Computer vision and pattern recognition, pp 770–778 He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. In: Computer vision and pattern recognition, pp 770–778
10.
Zurück zum Zitat Zisserman KSAA (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR) Zisserman KSAA (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR)
12.
Zurück zum Zitat Zhang QJ, Xu JL, Xu L, Guo HF (2016) Deep convolutional neural networks for forest fire detection. In: Kim YH (ed) Proceedings of the 2016 international forum on management, education and information technology application, vol 47. Advances in social science education and humanities research, pp 568–575. Atlantis Press, Paris Zhang QJ, Xu JL, Xu L, Guo HF (2016) Deep convolutional neural networks for forest fire detection. In: Kim YH (ed) Proceedings of the 2016 international forum on management, education and information technology application, vol 47. Advances in social science education and humanities research, pp 568–575. Atlantis Press, Paris
13.
Zurück zum Zitat Hafemann LG, Oliveira LS, Cavalin PR (2014) Forest species recognition using deep convolutional neural networks. In: International conference on pattern recognition, pp 1103–1107 Hafemann LG, Oliveira LS, Cavalin PR (2014) Forest species recognition using deep convolutional neural networks. In: International conference on pattern recognition, pp 1103–1107
14.
Zurück zum Zitat Castelluccio M, Poggi G, Sansone C, Verdoliva L (2015) Land use classification in remote sensing images by convolutional neural networks. In: Computer science Castelluccio M, Poggi G, Sansone C, Verdoliva L (2015) Land use classification in remote sensing images by convolutional neural networks. In: Computer science
15.
Zurück zum Zitat Lecun Y, Kavukcuoglu K, Farabet C (2010) Convolutional networks and applications in vision. In: International symposium on circuits and systems, pp 253–256 Lecun Y, Kavukcuoglu K, Farabet C (2010) Convolutional networks and applications in vision. In: International symposium on circuits and systems, pp 253–256
16.
Zurück zum Zitat Scherer D, Muller A, Behnke S (2010) Evaluation of pooling operations in convolutional architectures for object recognition. In: International conference on artificial neural networks Scherer D, Muller A, Behnke S (2010) Evaluation of pooling operations in convolutional architectures for object recognition. In: International conference on artificial neural networks
18.
20.
Zurück zum Zitat Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv:​1602.​07360 Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv:​1602.​07360
21.
Zurück zum Zitat Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: ACM multimedia, pp 675–678 Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: ACM multimedia, pp 675–678
22.
Zurück zum Zitat Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: Lechevallier Y, Saporta G (eds) Proceedings of COMPSTAT’2010: 19th International Conference on computational statistics, Paris France, August 22–27, 2010 Keynote, invited and contributed papers, pp 177–186. Physica-Verlag HD, Heidelberg. https://​doi.​org/​10.​1007/​978-3-7908-2604-3_​16 Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: Lechevallier Y, Saporta G (eds) Proceedings of COMPSTAT’2010: 19th International Conference on computational statistics, Paris France, August 22–27, 2010 Keynote, invited and contributed papers, pp 177–186. Physica-Verlag HD, Heidelberg. https://​doi.​org/​10.​1007/​978-3-7908-2604-3_​16
Metadaten
Titel
A Comparison: Different DCNN Models for Intelligent Object Detection in Remote Sensing Images
verfasst von
Peng Ding
Ye Zhang
Ping Jia
Xu-ling Chang
Publikationsdatum
30.06.2018
Verlag
Springer US
Erschienen in
Neural Processing Letters / Ausgabe 3/2019
Print ISSN: 1370-4621
Elektronische ISSN: 1573-773X
DOI
https://doi.org/10.1007/s11063-018-9878-5

Weitere Artikel der Ausgabe 3/2019

Neural Processing Letters 3/2019 Zur Ausgabe