A Modern Approach for Classification of Soil Aggregates based on Stereo Vision

ماشین های کشاورزی

Article 4, Volume 10, Issue 2 - Serial Number 20, 2020, Pages 155-167   

Document Type: Research Article

DOI: 10.22067/jam.v10i2.82853

Authors

A. Azizi¹; Y. Abbaspour Gilandeh^{* 1}; T. Mesri Gundoshmian¹; H. Abrishami Moghaddam²

¹Department of Biosystems Engineering, Faculty of Agriculture and Natural Resources, University of Mohaghegh Ardabili, Ardabil, Iran

²Department of Biomedical Engineering, Faculty of Electrical Engineering, K. N. Toosi University of Technology, Tehran, Iran

Abstract

Introduction
Stereo vision is an approach to 3D information from multiple 2D views of a scene. The 3D information can be extracted from a pair image, as known stereo pair by estimating the relative depth of points in the scene.
Soil aggregate size distribution is one of the most important issues in the agriculture sector which highly affects energy consumed for preparing the field before planting. Mean weight diameter of clods is a standard metric for determining clod (big aggregates) size. Conventional methods are based on sieving soil samples to calculate the MWD. However, they are faced with several challenges in larger scales and practical applications. Furthermore, due to inherent limitations of soil environment and also being a tedious work, traditional methods would beuse to estimate the metric higher or lower than actual value.
As new methods, researchers are using computer vision techniques as virtual sieve so that the size of clods can be determined via processing digital images which have been taken from soil surface. Although, image-based methods have solved many of previous problems, their accuracy is not so high due to the complexity of soil environment and overlapping colds, and needs to be improved. In order to overcome the mentioned challenges, in the current study stereo vision method was developed so that it is possible to extract the third dimension information as height of clods which helps us to categorize clods into their own class.
Materials and Methods
In this study, the W3-Fujifilm stereo camera equipped with two 10-megapixel CCD sensors for both left and right lenses, and baseline spacing of 7.5 cm was used. The distance between the camera lens and the ground was also set to 60 cm.
In order to get three components of soil clods including (x, y, z), point cloud was investigated. For this, local features were extracted using a SIFT feature detector. The SIFT algorithm is robust against scale, rotation and illumination changes, so that these specifications have made it as a strong tool in the field of stereo vision. Then, the extracted features (keypoints) were matched between two stereo pair images by means of Brute Force algorithm and the location of all corresponding points were determined and point cloud was obtained.
At the final stage, three features including length, width and height of all six classes of soil clods were entered into a linear classifier entitled discriminant analysis. This classifier as a linear separator classified these six classes based on appropriate functions in a 5 dimensional space.
Results and Discussion
Results of classification model showed that the height (thickness) of clods have more distinguishing different soil clods. The reason for this refers to the event of overlapping, because most of clods were touched each other after sieving. Consequently, the length and width of clods had not significant effect in soil aggregates classification.
In order to analysis the result of soil aggregate classification, confusion matrix was calculated and the overall classification accuracy was achieved 83.7%. The lowest and highest accuracy were obtained for class 1 (the littlest class) and class 6 (the biggest class), respectively due to their low and high height from the soil surface.
Conclusion
In this research, the basic geometrical features including length, width and height were extracted from stereo pair digital images via stereo vision techniques to classify six classes of soil clods. This aim was reached by 3-D reconstruction of image data, so that the height of each image as the third component of (x,y,z) was obtained as well as the length and width. The results of classification indicated that the stereo vision technique had the satisfactory performance in determining the aggregate size distribution which is one of the most important indices for tilled soil quality.

Keywords

Mean weight diameter; Soil clod; Stereo vision; Tillage

References

1. Abbaspour-Gilandeh, Y., and R. Sedghi. 2015. Predicting soil fragmentation during tillage operation using fuzzy logic approach. Journal of Terramechanics 57: 61-69.

2. Bogrekci, I., and R. J. Godwin. 2007. Development of an image processing technique for soil tilth sensing. Biosystems Engineering 97: 323-331.

3. Bradski, G., and A. Kaehler. 2008. Learning OPenCV: computer vision with the OpenCV library. O’Reilly Media, Inc. USA.

4. Chepil, W. S., and F. Bisal. 1943. A rotary sieve method for determining the size distribution of soil clods. Soil Science 56: 95-100.

5. Chimi-Chiadjeu, O., E. Vannier, R. Dusseaux, and O. Taconet. 2011. Influence of Gradient Estimation on Clod Identification on a Seedbed Digital Elevation Model. Environmental & Engineering Geoscience 4: 337-352.

6. Chimi-Chiadjeu, O., S. Le Hegarat-Mascle, E. Vannier, O. Taconet, and R. Dusseaux. 2014. Automatic clod detection and boundary estimation from Digital Elevation Model images using different approaches. Catena 118: 73-83.

7. Czachor, H., and J. Lipiec. 2004. Quantification of soil macroporosity with image analysis. Int. Agrophys 18: 217-223.

8. Faraji-Mahyari, Z., and Sh. Rafiee. 2016. Principles of stereo vision and its applications in automated farming operations. National Conference on Research Findings in Natural and Agricultural Ecosystems Tehran, Iran. (In Farsi).

9. Gardel_Kurka, P. R., and A. A. Diaz-Salazar. 2019. Applications of image processing in robotics and instrumentation. Mechanical Systems and Signal Processing 124: 142-169.

10. Gilliot, J. M., E. Vaudour, and J. Michelin. 2017. Soil surface roughness measurement: A new fully automatic photogrammetric approach applied to agricultural bare fields. Computers and Electronics in Agriculture 134: 63-78.

11. Hartley, R., and A. Zisserman. 2003. Multiple view geometry in computer vision. Cambridge University Press. New York, USA.

12. Itoh, H., K. Matsuo, A. Oida, H. Nakashima, J. Miyasaka, and T. Izumi. 2008. Aggregate size measurement by machine vision. Journal of Terramechanics 45:137-145.

13. Jafari-Malekabadi, A., M. Khojastehpour, and B. Emadi. 2019. Disparity map computation of tree stereo vision system and effect of canopy shapes and foliage density. Computers and Electronics in Agriculture 156: 627-644.

14. Kemper, W. D., and W. S. Chepil. 1965. Size distribution of aggregates. In C. A. Black et al. (ed). Methods of soil analysis, Part 1. Agronomy 9: 499- 510.

15. Kemper, W. D., T. J. Trout, M. J. Brown, and R. C. Rosenau. 1985b. Furrow erosion and water and soil management. Transactions of the American Society of Agricultural Engineering 28: 1564- 1572.

16. Kise, M., Q. Zhang, and F. Rovira Mas. 2005. A stereovision-based crop row detection method for tractor-automated guidance. Biosystems Engineering 90 (4): 357-367.

17. Lindeberg, T. 1994. Scale-space theory: a basic tool for analyzing structures at different scales. Journal of Applied Statistics 21 (2): 224-270.

18. Loop, C., and Z. Zhang. 1999. Computing rectifying homographies for stereo vision. IEEE, CVPR 125-131.

19. Lowe, D. G. 2004. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60 (2): 91-110.

20. Lyles, L., J. D. Dickerson, and L. A. Disrud. 1970. Modified rotary sieve for improved accuracy. Soil Science 109: 207-210.

21. Nasr, H. M., and F. Selles. 1995. Seedling emergence as influenced by aggregate size, bulk density, and penetration resistance of the seedbed. Soil & Tillage research 34: 61-76.

22. Nasiri, A., H. Mobli, S. Hosseinpour, and Sh. Rafiee. 2017. Creation greenhouse environment map using localization of edge of cultivation platforms based on stereo vision. Journal of Agricultural Machinery 7 (2): 336-349. (In Farsi).

23. Neal-Smith, L., W. Zhang, F. M. Hansen, I. John-Hales, and M. Lionel-Smith. 2018. Innovative 3D and 2D machine vision methods for analysis of plants and crops in the field. Computers in Industry 97: 122-131.

24. Piers, L. F., J. A. Rosa, and L. C. Timm. 2011. Comparison of methods to evaluate soil bulk density. Acta Science. Agron 33 (1): 161-170.

25. Rahimi-Ajdadi, F., Y. Abbaspour-Gilandeh, K. Mollazade, and R. Hasanzadeh-Pakrezaie. 2016. Application of machine vision for classification of soil aggregate size. Soil & Tillage Research 162: 8-17.

26. Riegler, T., C. Rechberger, F. Handler, and H. Prankl. 2014. Image processing system for evaluation of tillage quality. Landtechnik 69: 125-131.

27. Sandri, R., T. Anken, T. Hilfiker, L. Sartori, and H. Bollhalder. 1998. Comparison of methods for determining cloddiness in seedbed preparation. Soil & Tillage Research 45: 75-90.

28. Sankowski, W., M. Wlodarczyk, D. Kacperski, and K. Grabowski. 2017. Estimation of measurement uncertainty in stereo vision system. Image and Vision Computing 61: 70-81.

29. Stafford, J. V., and B. Amber. 1990. Computer vision as a sensing system for soil cultivator control. Proceedings of ImecE, C419/0441 123-129.

30. Stehman, S. V. 1997. Selecting and interpreting measures of thematic classification accuracy. Remote Sensing of Environment 62: 77- 89.

31. Taconet, O., and V. Ciarletti. 2007. Estimating soil roughness indices on a ridge-and furrow surface using stereo photogrammetry. Soil & Tillage Research 93: 64-76.

32. Taconet, O., R. Dusseaux, E. Vannier, and O. Chimi-Chiadjeu. 2013. Statistical description of seedbed cloddiness by structuring objects using digital elevation models. Computers & Geosciences 60:117-125.

33. Thmosen, L. M., J. E. M. Baartman, R. J. Barneveld, T. Starkloff, and J. Stolte. 2015. Soil surface roughness: comparing old and new measuring methods and application in a soil erosion model. Soil Journal 1: 399-410.

34. Trucco, E., and A. Verri.1998. Introductory techniques for 3-D computer vision. Prentice Hall. Englewood Cliffs, New Jersey, USA.

35. Van Bavel, C. H. M. 1949. Mean weight diameter of soil aggregates as a statistical index of aggregation. Soil Science Society of America Journal 14: 20-23.

36. Vannier, E., V. Ciarletti, and F. Darboux. 2009. Wavelet-based detection of clods on a soil surface. Computers & Geosciences 35: 2259-2267.

37. Vannier, E., O. Taconet, R. Dusseaux, and F. Darboux. 2018. A study of clod evolution in simulated rain on the basis of digital elevation models. Catena 160: 212-221.

38. Zhang, X., and W. Dahu. 2019. Application of artificial intelligence algorithms in image processing. Journal of Visual Communication and Image Representation 61: 42-49.