شناسایی اهداف در تصاویر سنجش‌ازدوری با قدرت تفکیک بالا با استفاده از روش‌های یادگیری عمیق

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشگاه صنعتی نوشیروانی بابل

2 دانشگاه صنعتی خواجه نصیرالدین طوسی

چکیده

شناسایی عوارض موجود در تصاویر، یکی از مسائل اساسی در حوضه‌ تفسیر تصاویر به‌ویژه در تصاویر سنجش‌از‌دوری، به شمار می‌آید. یکی از روش‌های کارآمد و به‌روز در این زمینه، به‌کارگیری شیوه‌های یادگیری عمیق، جهت استخراج و تفسیر است. یک عارضه، مجموعه‌ای از الگوهای منحصربه‌فرد است که با عوارض مجاور خود متفاوت است، این تفاوت معمولاً در یک یا چند ویژگی به‌طور هم‌زمان اتفاق می‌افتد که می‌توان به‌تفاوت در شکل، رنگ و درجه خاکستری اشاره نمود. در این‌ راستا، روش یادگیری عمیق با توانایی تحلیل مفاهیم انتزاعی سطح بالا، می‌تواند انتخاب مناسبی در این زمینه باشد. در روش پیشنهادی، ابتدا یک پایگاه‌داده مطابق با شرایط محیطی و جغرافیایی کشور از برخی از فرودگاه‌های ایران تشکیل‌‌شد. سپس با استفاده از شبکه‌های عصبی کانولوشنی به تولید مدل یادگیرنده بهینه اقدام شد. برای این کار، در قسمت پردازش داده‌های خام در کنار استفاده از روش انتقال آموزشی، بردارهایی جهت دسته‌بندی عوارض موردنظر استخراج و به یک مدل ماشین‌بردار پشتیبان طبقه‌بندی‌کننده، تحویل داده می‌شوند. در ادامه، مقادیر خروجی با مقادیر به‌دست‌آمده از تصویر آزمایشی برای هر عارضه، مقایسه و در یک روند تکرارشونده تحلیل و جهت تطابق ساختاری بررسی می‌شوند. نتایج استخراج‌شده از اعمال مدل پیشنهادی بر روی چند سری داده‌ آزمایشی، ارزیابی و با روش‌های مشابه مقایسه شد که درنهایت با مقادیر 21/98 درصد برای معیار Precision و 1/99 درصد برای معیار F1-Measure، قادر به شناسایی عوارض هدف است

کلیدواژه‌ها


عنوان مقاله [English]

Target detection from high-resolution remote sensing images using deep learning methods

نویسندگان [English]

  • nima farhadi 1
  • Abas Kiani 2
  • Hamid Ebadi 2
1 Babol Noshirvani University of Technology
2 Faculty, K.N.Toosi
چکیده [English]

Object detection is one of the fundamental issues in image interpretation process, especially from remote-sensing imagery. One of the most effective and efficient methods in this field is the use of deep learning algorithm for feature extraction and interpretation. An object is a collection of unique patterns that differ with own adjacent properties. This difference usually occurs in one or more features simultaneously, which can be indicated by the difference in shape, color, and gray values. In this regard, the use of deep learning as an efficient branch of machine learning can be useful in generating high-level concepts through learning in different layers. In this research, a database based on the environmental and geographical conditions from some Iranian airports was created. Additionally, an optimal learner model was developed with a convolutional neural network. For this purpose, in the raw data processing section, besides using the transfer learning method, some vectors were extracted to classify the objects and delivered to an SVM model. The output values were compared with the values obtained from the test image for each object, and they were analyzed in a repeatable process for structural matching. Precision of 98.21% and F1-Measure of 99.1% was achieved, for identification of the target objects

کلیدواژه‌ها [English]

  • Deep Learning
  • Neural Network
  • Remote Sensing imagery
  • Machine Learning
  • Transfer learning
  1. Akçay, H.G. and Aksoy, S., 2008, Automatic detection of geospatial objects using multiple hierarchical segmentations, IEEE Transactions on Geoscience and Remote Sensing 46, 2097-2111.
  2. Chen, X. and Gupta, A., 2017, An Implementation of Faster RCNN with Study for Region Sampling, arXiv preprint arXiv:1702.02138.
  3. Chen, Z., Zhang, T. and Ouyang, C., 2018, End-to-End Airplane Detection Using Transfer Learning in Remote Sensing Images, Remote Sensing 10, 139.
  4. Cheng, M.-M., Zhang, Z., Lin, W.-Y. and Torr, P., 2014, BING: Binarized normed gradients for objectness estimation at 300fps, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3286-3293.
  5. Ciregan, D., Meier, U. and Schmidhuber, J., 2012, Multi-column deep neural networks for image classification, Computer vision and pattern recognition (CVPR), 2012 IEEE conference on. IEEE, pp. 3642-3649.
  6. Deng, L. and Yu, D., 2014, Deep learning: methods and applications, Foundations and Trends® in Signal Processing 7, 197-387.
  7. Diao, W., Sun, X., Zheng, X., Dou, F., Wang, H. and Fu, K., 2016, Efficient saliency-based object detection in remote sensing images using deep belief networks, IEEE Geoscience and Remote Sensing Letters 13, 137-141.
  8. Diehl, P.U., Neil, D., Binas, J., Cook, M., Liu, S.C. and Pfeiffer, M., 2015, Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In Neural Networks (IJCNN), 2015 International Joint Conference on IEEE, pp. 1-8.
  9. Dollar, P., Appel, R., Belongie, S. and Perona, P., 2014, Fast feature pyramids for object detection, IEEE Transactions on Pattern Analysis and Machine Intelligence 36, 1532-1545.
  10.  
  11. Felzenszwalb, P.F., Girshick, R.B., McAllester, D. and Ramanan, D., 2010, Object detection with discriminatively trained part-based models, IEEE transactions on pattern analysis and machine intelligence 32, 1627-1645.
  12. ghorbani, F., Ebadi, H. and Sedaghat, A., 2017, Classification of the high-resolution remote sensing images for land use and land cover application using SIFT algorithm, The 2nd National Conference on Geospatial Information Technology (NCGIT). K.N.Toosi University of Technology, Tehran.
  13. Girshick, R., 2015, Fast R-CNN, Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), IEEE Computer Society, pp. 1440-1448.
  14. Girshick, R., Donahue, J., Darrell, T. and Malik, J., 2014, Rich feature hierarchies for accurate object detection and semantic segmentation, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 580-587.
  15. Han, J., Zhou, P., Zhang, D., Cheng, G., Guo, L., Liu, Z., Bu, S. and Wu, J., 2014, Efficient, simultaneous detection of multi-class geospatial targets based on visual saliency modeling and discriminative learning of sparse coding, ISPRS Journal of Photo-grammetry and Remote Sensing 89, 37-48.
  16. He, Y., Kavukcuoglu, K., Wang, Y., Szlam, A. and Qi, Y., 2014, Unsupervised feature learning by deep sparse coding, In Proceedings of the 2014 SIAM International Conference on Data Mining, pp. 902-910. Society for Industrial and Applied Mathematics.
  17. Krizhevsky, A., Nair, V. and Hinton, G., 2014, The CIFAR-10 dataset.
  18. Krizhevsky, A., Sutskever, I. and Hinton, G.E., 2012, Imagenet classification with deep convolutional neural networks, Advances in neural information processing systems, pp. 1097-1105.
  19. LeCun, Y., Bengio, Y. and Hinton, G., 2015, Deep learning. nature 521, 436-444.
  20. Li, Y., Fu, K., Sun, H., Sun, X., 2018, An Aircraft Detection Framework Based on Reinforcement Learning and Convolutional Neural Networks in Remote Sensing Images, Remote Sensing 10, 243.
  21. Lu, J., Sibai, H. and Fabry, E., 2017, Adversarial Examples that Fool Detectors, arXiv preprint arXiv:1712.02494.
  22. Ok, A.O., Senaras, C. and Yuksel, B., 2013, Automated detection of arbitrarily shaped buildings in complex environments from monocular VHR optical satellite imagery, IEEE Transactions on Geoscience and Remote Sensing 51, 1701-1717.
  23. Radovic, M., Adarkwa, O., Wang, Q., 2017, Object Recognition in Aerial Images Using Convolutional Neural Networks, Journal of Imaging 3, 21.
  24. Redmon, J., Divvala, S., Girshick, R. and Farhadi, A., 2016, You only look once: Unified, real-time object detection, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788.
  25. Ren, S., He, K., Girshick, R. and Sun, J., 2015, Faster r-cnn: Towards real-time object detection with region proposal networks, Advances in neural information processing systems, pp. 91-99.
  26. Sun, H., Sun, X., Wang, H., Li, Y. and Li, X., 2012, Automatic target detection in high-resolution remote sensing images using spatial sparse coding bag-of-words model, IEEE Geoscience and Remote Sensing Letters 9, 109-113.
  27. Vincent, P., Larochelle, H., Bengio, Y. and Manzagol, P.A., 2008, Extracting and composing robust features with denoising autoencoders, In Proceedings of the 25th international conference on Machine learning, pp. 1096-1103
  28. Wang, G., Wang, X., Fan, B., Pan, C., 2017, Feature extraction by rotation-invariant matrix representation for object detection in aerial image, IEEE Geoscience and Remote Sensing Letters 14, 851-855.
  29. Wu, H., Zhang, H., Zhang, J., Xu, F., 2015, Fast aircraft detection in satellite images based on convolutional neural networks, Image Processing (ICIP), 2015 IEEE International Conference on. IEEE, pp. 4210-4214.
  30. Xie, S., Tu, Z., 2015, Holistically-nested edge detection, Proceedings of the IEEE international conference on computer vision, pp. 1395-1403.
  31. XU, N. and HUO, C., 2018, Learning Deep Relationship for Object Detection, IEICE TRANSACTIONS on Information and Systems 101, 273-276.
  32. Xu, T.-B., Cheng, G.-L., Yang, J. and Liu, C.-L., 2016, Fast Aircraft Detection Using End-to-End Fully Convolutional Network, Digital Signal Processing (DSP), 2016 IEEE International Conference on. IEEE, pp.