Over the recent years, the advantages of using unmanned aerial vehicles (UAVs) have provided fascinating working areas, particularly for photogrammetric goals. One of the main problems preventing the UAV data to achieve fully automated processing is the image stretching error and reduced resolution or image blurring, which is caused by camera shake during shooting or slow shutter speed. Movements of the sensors may be due to normal motions during the flight, strong winds, lack of proper functioning of the gimbal stabilizer or an operator’s lack of skill for properly controlling the drone. Image blurring negatively affects data interpretation and visual analysis, which in turn raises challenges for detection and matching algorithms; as a result, the precision of automatic processing and accuracy of the extracted geometrical information would decrease. Time-consuming and costly manual methods are typically adopted to identify and remove images with radiometric errors. Such methods are tedious, especially for large datasets and bring about high margin of errors. In this paper, an automatic and reliable algorithm is presented to identify and distinguish blurred images. The aim is to extract the saturation blue difference (SBD) parameter from the sets of images. It is known that SBD value has a direct relationship with the amount of blurring. The numerical value of the parameter is determined based on the variation in the extracted edge pixels of blurred and non-blurred images. Evaluation on two datasets indicates that the proposed algorithm based on the selected threshold limit (defined with regard to the geometric and visual requirements of images) for the SBD values can recognize the images with the SBD values less than the threshold value as blurred images with 100% certainty and extract them from the sets of obtained images.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
Han, X.: Using Refined Least Square Image Matching to Improve 3D Reconstruction under Gaussian Blur and Motion Blur images. The Ohio State University, Columbus (2017)
Liang, X.; Wang, X.; Guo, J.; Zheng, J.: Automatic segmentation of blurry region using Haar-wavelet transform. In: 2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), 15–17 Dec 2017, pp. 132–136 (2017)
Kedzierski, M.; Wierzbicki, D.: Methodology of improvement of radiometric quality of images acquired from low altitudes. Measurement 92, 70–78 (2016). https://doi.org/10.1016/j.measurement.2016.06.003
Koik, B.T.; Ibrahim, H.: Exploration of current trend on blur detection method utilized in digital image processing. J. Ind. Intell. Inf. 1(3), 143–147 (2013)
Teo, T.-A.; Zhan, K.-Z.: Integration of image-derived and pos-derived features for image blur detection. Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. 41, 1051 (2016)
Ong, E.; Lin, W.; Lu, Z.; Yang, X.; Yao, S.; Pan, F.; Jiang, L.; Moschetti, F.: A no-reference quality metric for measuring image blur. In: Seventh International Symposium on Signal Processing and Its Applications. Proceedings, 1–4 July 2003, vol. 461, pp. 469–472 (2003)
Joshi, N.; Szeliski, R.; Kriegman, D.J.: PSF estimation using sharp edge prediction. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, 23–28 June 2008, pp. 1–8 (2008)
Narvekar, N.D.; Karam, L.J.: A no-reference perceptual image sharpness metric based on a cumulative probability of blur detection. In: 2009 International Workshop on Quality of Multimedia Experience, 29–31 July 2009, pp. 87–91 (2009)
Rahtu, E.; Heikkil, J.; Ojansivu, V.; Ahonen, T.: Local phase quantization for blur-insensitive image analysis. Image Vis. Comput. 30(8), 501–512 (2012). https://doi.org/10.1016/j.imavis.2012.04.001
Sieberth, T.; Wackrow, R.; Chandler, J.H.: Automatic detection of blurred images in UAV image sets. ISPRS J. Photogramm. Remote Sens. 122, 1–16 (2016). https://doi.org/10.1016/j.isprsjprs.2016.09.010
Rengarajan, V.; Rajagopalan, A.N.; Aravind, R.; Seetharaman, G.: Image registration and change detection under rolling shutter motion blur. IEEE Trans. Pattern Anal. Mach. Intell. 39(10), 1959–1972 (2017). https://doi.org/10.1109/TPAMI.2016.2630687
Kieu, V.C.; Cloppet, F.; Vincent, N.: Adaptive fuzzy model for blur estimation on document images. Pattern Recognit. Lett. 86, 42–48 (2017). https://doi.org/10.1016/j.patrec.2016.12.015
Pertuz, S.; Puig, D.; Garcia, M.A.: Analysis of focus measure operators for shape-from-focus. Pattern Recognit. 46(5), 1415–1432 (2013). https://doi.org/10.1016/j.patcog.2012.11.011
Pech-Pacheco, J.L.; Cristóbal, G.; Chamorro-Martinez, J.; Fernández-Valdivia, J.: Diatom autofocusing in brightfield microscopy: a comparative study. In: 15th International Conference on Pattern Recognition, 2000. Proceedings, pp. 314–317. IEEE (2000)
Crete, F.; Dolmiere, T.; Ladret, P.; Nicolas, M.: The blur effect: perception and estimation with a new no-reference perceptual blur metric, pp. 64920I–64911 (2007)
About this article
Cite this article
Mahdinezhad Gargari, A., Ebadi, H. & Esmaeili, F. An Efficient Algorithm for Detection of Image Stretching Error from a Collection of Images Acquired by Unmanned Aerial Vehicles. Arab J Sci Eng 44, 489–504 (2019). https://doi.org/10.1007/s13369-018-3634-z
- Image stretching
- Radiometric errors
- UAV (unmanned aerial