Journals / Bilgisayar Bilimleri / 2016 / Cilt: 1 - Sayı: 1

The Texture Feature Extraction of Agricultural Field Images by HOG Algorithms and Soil Moisture Estimation based on the Texture Features

Tarımsal İmge Dokularından HOG Algoritması ile Öznitelik Çıkarımı ve Öznitelik Tabanlı Toprak Neminin Tahmini

Pages
1–7
Publication Date
2016-12-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The obtained feature vectors are then classified into three (much, middle and little) groups by using k-Nearest Neighbor (k-NN) and Multilayer Perceptron (MLP) classifiers.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Knowing the value of soil surface moisture in the agricultural areas are very important in many ways such as minimizing the harmful effects of drought cases, preventing salinity caused by over watering, protecting agricultural lands and using the irrigation system efficiently.
📊
Key Findings & Data:The main purpose of this study is that determining a relationship between measurements of local soil moisture and images in agricultural Mardin region and prediction of soil moisture with the determined relationship.
💡
Conclusion & Impact:The obtained feature vectors are then classified into three (much, middle and little) groups by using k-Nearest Neighbor (k-NN) and Multilayer Perceptron (MLP) classifiers.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Toprak Nemi Tahmini · İmge İşleme · Sınıflandırma

Abstract

Knowing the value of soil surface moisture in the agricultural areas are very important in many ways such as minimizing the harmful effects of drought cases, preventing salinity caused by over watering, protecting agricultural lands and using the irrigation system efficiently. The main purpose of this study is that determining a relationship between measurements of local soil moisture and images in agricultural Mardin region and prediction of soil moisture with the determined relationship. The images are derived from TARBIL (http://www.tarbil.org) database. The texture feature vectors are extracted from the images by using Histogram of Oriented Gradients (HOG) algorithm. The obtained feature vectors are then classified into three (much, middle and little) groups by using k-Nearest Neighbor (k-NN) and Multilayer Perceptron (MLP) classifiers.

Özet

Tarımsal alanlardaki toprak nem düzeyinin bilinmesi; kuraklık durumu zararlarının en aza indirgenmesi, fazla sulama nedeni ile oluşan tuzluluğun önlenmesi, tarımsal alanlarının korunması ve sulama sisteminin verimli olarak kullanılması gibi birçok yönden önem taşımaktadır. Bu çalışmada, Mardin tarımsal alan imgelerine ait doku öznitelik vektörleri ile yerel toprak nem ölçümleri arasındaki ilişkinin kurulması ve bu ilişkiye dayalı toprak nem düzeyinin tahmini amaçlanmıştır. İmgeler TARBİL (http://www.tarbil.org) veritabanından elde edilmiştir. İmge dokusuna duyarlı yeni yöntemlerden biri olan Yönlü Gradyan Histogramı (HOG) algoritması kullanılarak, öznitelik vektörleri elde edilmiştir. Elde edilen öznitelik vektörleri daha sonra k En Yakın Komşu (k-NN) ve Çok Katmanlı Algılayıcı (MLP) sınıflandırıcılarının girişlerine verilerek toprak nemi üç (Çok, Orta ve Az nemli) grubta sınıflandırılmıştır.

🔖

Cite This Article

ACAR, E., ÖZERDEM, M. S. (2016). The Texture Feature Extraction of Agricultural Field Images by HOG Algorithms and Soil Moisture Estimation based on the Texture Features. Bilgisayar Bilimleri, Cilt: 1 - Sayı: 1, 1–7. https://ajindex.com/articles/743247

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (10)

  1. H. S. Srivastava, P. Patel, Y. Sharma, et R. R. Navalgund, “Large-area soil moisture estimation using multi-incidenceangle RADARSAT-1 SAR data “, Geosci. Remote Sens. IEEE Trans. On, vol. 47, no 8, p. 2528 2535, 2009
  2. M. Zribi, A. Chahbi, M. Shabou, Z. Lili-Chabaane, B. Duchemin, N. Baghdadi, R. Amri, et A. Chehbouni, ”Soil surface moisture estimation over a semi-arid region using ENVISAT ASAR radar data for soil evaporation evaluation.”, Hydrol. Earth Syst. Sci., vol. 15, no 1, 2011
  3. N. Baghdadi, S. Gaultier, et C. King, “Retrieving surface roughness and soil moisture from SAR data using neural networks.”, in Retrieval of Bio-and Geo-Physical Parameters from SAR Data for Land Applications, 2002, vol. 475, p. 315 319
  4. El-Hajj, M.; Baghdadi, N.; Belaud, G.; Zribi, M.; Cheviron, B.; Courault, D.; Charron, F. "Soil moisture retrieval over grassland using X-band SAR data", Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International, On page(s): 3638 – 3641
  5. Buttrey, S. and Karo, C.2001. Using k-nearest-neighbor classification in the leaves of a tree. Computational Statistics & Data Analysis, 40 (2002) 27-37
  6. Li, X., Nie, P., Jun,Z. and He, Y. 2011.Using wavelet transform and multi-class least square support vector machine in multi-spectral imaging classification of Chinese famous tea. Expert Systems with Applications 38(9):11149-11159
  7. N. Dalal and B. Triggs "Histograms of oriented gradients for human detection", Proc. IEEE Computer Soc. Conf. Comput. Vis. Pattern Recognit., pp.886 -893 2005
  8. R. Kadota and H. Sugano "Hardware architecture for HOG feature extraction", Proc. 5th Int. Conf. Intell. Inf. Hiding Multimedia Signal, pp.1330 -1333 2009 [9] O. Ludwig, D. Delgado, V. Goncalves, and U. Nunes, 'Trainable Classifier-Fusion Schemes: An Application To Pedestrian Detection,' In: 12th International IEEE Conference On Intelligent Transportation Systems, 2009, St. Louis, 2009. V
  9. P. 432-437
  10. Acar, E. and Özerdem, M.S., “Image Classification of Kiziltepe cropland by using Gabor Wavelet Transform”, 20th Signal Processing and Communications Applications Conference (SIU), On page(s): 1 – 4, Muğla, 2012.