Tillage Machine Control Based on a Vision System for Soil Roughness and Soil Cover Estimation
Soil roughness and soil cover are important control variables for plant cropping. A certain level of soil roughness can prevent soil erosion, but to rough soil prevents good plant emergence. Local heterogeneities in the field make it difficult to get homogeneous soil roughness. Residues, like straw, influences the soil roughness estimation and play an important role in preventing soil erosion. We propose a system to control the tillage intensity of a power harrow by varying the driving speed and PTO speed of a tractor. The basis for the control algorithm is a roughness estimation system based on an RGB stereo camera. A soil roughness index is calculated from the reconstructed soil surface point cloud. The vision system also integrates an algorithm to detect soil cover, like residues. Two different machine learning methods for pixel-wise semantic segmentation of soil cover were implemented, an entangled random forest and a convolutional neural net. The pixel-wise classification of each image into soil, living organic matter, dead organic matter and stone allow for mapping of soil cover during tillage. The results of the semantic segmentation of soil cover were compared to ground truth labelled data using the grid method. The soil roughness measurements were validated using the manual sieve analysis. The whole control system was validated in field trials on different locations.
KeywordsStereo camera Soil roughness Soil cover Convolutional neural network
The research leading to this work has received funding from the Lower Austrian government (WST3-T-140/002-2014). As well as from the Austrian Research Promotion Agency under the program “Bridge 1”.
- 2.Kirchmeier, H., Geischeder, R., Demmel, M.: Tillage effect and requirements of rotaty harrows with different rotor geometries. Landtechnik 60(4), 196–197 (2005)Google Scholar
- 6.Riegler, T., Rechberger, C., Handler, F., Prankl, H.: Image processing system for evaluation of tillage quality. Landtechnik 69(3), 125–130 (2014)Google Scholar
- 10.Kırcı, M., Güneş, E. O., Çakır, Y.: Vegetation measurement using image processing methods. In The Third International Conference on Agro-Geoinformatics (2014)Google Scholar
- 12.Mortensen, A. K., Dyrmann, M., Karstoft, H., Nyholm Jørgensen, R., Gislum, R.: Semantic Segmentation of Mixed Crops using Deep Convolutional Neural Network. In: CIGR-AgEng Conference (2016)Google Scholar
- 14.Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: Enet: a deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147 (2016)
- 17.Milioto, A., C. Stachniss, C.: Bonnet: an open-source training and deployment framework for semantic segmentation in robotics using CNNs. In: Proceedings of the IEEE International Conference on Robotics & Automation (ICRA) (2019)Google Scholar
- 18.OpenCV library. http://opencv.org/. Accessed 9 May 2019
- 19.PCL library. http://www.pointclouds.org/. Accessed 9 May 2019