Man-Made Object Detection in Aerial Images Using Color Statistical Features and Machine Learning

Document Type : علمی - پژوهشی

Authors

Associate Professor, Faculty of IT and Computer Engineering, Azarbaijan Shahid Madani University, Tabriz, Iran

Abstract

Generally, the photos captured by drones and satellites include both natural scenes and man-made objects. Having these two categories classified, we will be able to extract important information from aerial scenes such as the shapes and the alignments of the structures and then, create labeled aerial images accordingly. Obtaining such information is of great interest in, for example, military, urban, and environmental protection applications. However, due to a huge amount of data that is collected in form of images, it seems that manually processing of such data is impossible. Therefore, employing automatic techniques based on artificial intelligence has become more on demand. There are numerous researches on this topic from which detection of buildings, vehicles, roads, and vegetation are of more interest. In this paper, we aim to introduce a method to detect man-made objects in aerial images based on a new set of color statistical features, which can be easily extracted, together with a learning model. Experimental results on a publicly available dataset, Massachusetts dataset, have shown promising results in terms of both accuracy and processing time; the accuracy and the average processing time are 90.07% and 0.96 seconds, respectively.

Keywords


  1. سجادی، س. ی.، پارسیان، س.، ۱۳۹۶، استخراج ساختمان به کمک تلفیق داده‌های ابر طیفی و لیدار به روش یادگیری ماشین، سنجش از دور و GIS ایران جلد دهم، شماره ۲، صص ۱۴-۱.
  2. Barzohar, M., D. B. J. I. T. o. P. A. Cooper and M. Intelligence 1996, Automatic finding of main roads in aerial images by using geometric-stochastic models and estimation, 18(7): 707-721.
  3. Bhagavathy, S., B. S. J. I. T. o. G. Manjunath and R. Sensing, 2006, Modeling and detection of geospatial objects using texture motifs 44(12): 3706-3715.
  4. Bhagavathy, S., S. Newsam and B. Manjunath, 2002, Modeling object classes in aerial images using texture motifs. Pattern Recognition, 2002. Proceedings. 16th International Conference on, IEEE.
  5. Burkov, A., 2019, The Hundred-Page Machine Learning Book, Andriy Burkov.
  6. Burochin, J.-P., B. Vallet, M. Bredif, C. Mallet, T. Brosset, N. J. I. J. o. P. Paparoditis and R. Sensing, 2014, Detecting blind building façades from highly overlapping wide angle aerial imagery, 96: 193-209.
  7. Cai, F., H. Chen and J. J. I. J. I. T. C. S. Ma , 2011, Man-made object detection based on texture clustering and geometric structure feature extracting, 3(2): 9-16.
  8. Cao, G. and X. J. I. J. o. R. S. Yang, 2007, Man‐made object detection in aerial images using multi‐stage level set evolution, 28(8): 1747-1757.
  9. Chang, C.-C., C.-J. J. A. t. o. i. s. Lin and technology, 2011, LIBSVM: A library for support vector machines, 2(3): 27.
  10. Cheng, G. & J. Han, 2016, A survey on object detection in optical remote sensing images, ISPRS Journal of Photogrammetry and Remote Sensing 117: 11-28.
  11. Cheng, G., J. J. I. J. o. P. Han & R. Sensing, 2016, A survey on object detection in optical remote sensing images, 117: 11-28.
  12. Cheriyadat, A. M. J. I. T. o. G. & R. Sensing, 2014, Unsupervised feature learning for aerial scene classification, 52(1): 439-451.
  13. Cunningham, J. P. & Z. J. T. J. o. M. L. R. Ghahramani, 2015, Linear dimensionality reduction: Survey, insights, and generalizations, 16(1): 2859-2900.
  14. Douglas, S. A. & A. E. J. A. T. o. G. Kirkpatrick, 1999, Model and representation: the effect of visual feedback on human performance in a color picker interface, 18(2): 96-127.
  15. Fauqueur, J., N. Kingsbury & R. Anderson, 2005, Semantic discriminant mapping for classification and browsing of remote sensing textures and objects, Image Processing, 2005. ICIP 2005. IEEE International Conference on, IEEE.
  16. Fischer, A., T. H. Kolbe, F. Lang, A. B. Cremers, W. Förstner, L. Plümer, V. J. C. V. Steinhage & I. Understanding, 1998, Extracting buildings from aerial images using hierarchical aggregation in 2D and 3D, 72(2): 185--203.
  17. Gruen, A., H. J. I. J. o. P. Li & R. Sensing, 1995, Road extraction from aerial and satellite images by dynamic programming, 50(4): 11-20.
  18. Hinz, S., 2003, Detection and counting of cars in aerial images, Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on, IEEE.
  19. Hui, J., M. Du, X. Ye, Q. Qin, J. J. I. G. Sui & R. S. Letters, 2018, Effective Building Extraction From High-Resolution Remote Sensing Images With Multitask Driven Deep Neural Network,
  20. Hussnain, Z., S. O. Elberink, G. J. I. A. o. t. P. Vosselman, Remote Sensing and S. I. Sciences, 2016, AUTOMATIC FEATURE DETECTION, DESCRIPTION AND MATCHING FROM MOBILE LASER SCANNING DATA AND AERIAL IMAGERY, 41.
  21. Kohonen, T., J. Hynninen, J. Kangas, J. Laaksonen, S. J. U. o. T. L. o. C. PAK & H. Information Science, Finland, 1995, The self-organizing map program package.
  22. Li, X., S.-C. Chen, M.-L. Shyu & B. J. t. I. C. o. D. M. S. Furht, San Francisco Bay, California, USA, 2002, Image retrieval by color, texture, and spatial information, 1-8.
  23. Li, Z. & L. J. I. T. o. I. P. Itti, 2011, Saliency and gist features for target detection in satellite images, 20(7): 2017-2029.
  24. Lin, C., R. J. C. v. Nevatia and i. understanding,1998, Building detection and description from a single intensity image, 72(2): 101-121.
  25. Ma, W. Y. & B. J. J. o. t. A. S. f. I. S. Manjunath,1998, A texture thesaurus for browsing large aerial photographs, 49(7): 633-648.
  26. Marcu, A. E. J. a. p. a., 2016, A local-global approach to semantic segmentation in aerial images.
  27. Mnih, V., 2013, Machine learning for aerial image labeling, University of Toronto (Canada).
  28. Moranduzzo, T., F. J. I. T. o. G. Melgani & R. Sensing, 2014, Automatic car counting method for unmanned aerial vehicle images, 52(3): 1635-1647.
  29. Nagarajan, S., T. J. I. J. o. P. Schenk & R. Sensing, 2016, Feature-based registration of historical aerial images by area minimization, 116: 15-23.
  30. Ojala, T., M. Pietikainen, T. J. I. T. o. p. a. Maenpaa and m. intelligence, 2002, Multiresolution gray-scale and rotation invariant texture classification with local binary patterns, 24(7): 971-987.
  31. Ozdemir, B. & S. Aksoy, 2010, Image classification using subgraph histogram representation, Pattern Recognition (ICPR), 2010 20th International Conference on, IEEE.
  32. Penatti, O. A., K. Nogueira & J. A. dos Santos, 2015, Do deep features generalize from everyday objects to remote sensing and aerial scenes domains? Proceedings of the IEEE conference on computer vision and pattern recognition workshops.
  33. Ruiz, L., A. Fdez-Sarria & J. Recio, 2004, Texture feature extraction for classification of remote sensing data using wavelet decomposition: a comparative study, 20th ISPRS Congress.
  34. Saito, S. & Y. Aoki, 2015, Building and road detection from large aerial imagery. Image Processing: Machine Vision Applications VIII, International Society for Optics and Photonics.
  35. Saito, S., T. Yamashita & Y. J. E. I. Aoki, 2016, Multiple object extraction from aerial imagery with convolutional neural networks, 2016(10): 1-9.
  36. Sharma, M. & S. Singh, 2001, Evaluation of texture methods for image analysis, Intelligent Information Systems Conference, The Seventh Australian and New Zealand 2001, IEEE.
  37. Sommer, D. & M. Golz, 2002, Multiple training of vector-based neural networks to detect density centers in input space, Proceedings of the European symposium on intelligent technologies, hybrid systems and their implementation on smart adaptive systems.
  38. Stehling, R. O., M. A. Nascimento & A. X. Falcão, 2002, A compact and efficient image retrieval approach based on border/interior pixel classification, Proceedings of the eleventh international conference on Information and knowledge management, ACM.
  39. Tan, Q., J. Wang & D. A. Aldred, 2008, Road vehicle detection and classification from very-high-resolution color digital orthoimagery based on object-oriented method. Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International, IEEE.
  40. Tan, X. & B. J. I. t. o. i. p. Triggs, 2010, Enhanced local texture feature sets for face recognition under difficult lighting conditions, 19(6): 1635-1650.
  41. Thuy, N. T. J. D. d., Graz University of Technology, 2009, Object Detection from Aerial Image.
  42. Vapnik, V. N. J. I. t. o. n. n., 1999, An overview of statistical learning theory, 10(5): 988-999.
  43. Wei, W., Y. J. I. Xin & V. Computing (2010, Rapid, man-made object morphological segmentation for aerial images using a multi-scaled, geometric image analysis, 28(4): 626-633.
  44. Xia, Y., J. Chen, J. Li & Y. J. M. s. Zhang, 2016, Geometric discriminative features for aerial image retrieval in social media, 22(4): 497-507.