Development of uncut crop edge detection system based on laser rangefinder for combine harvesters

The objective of this research was to develop an uncut crop edge detection system for a combine harvester. A laser rangefinder (LF) was selected as a primary sensor, combined with a pan-tilt unit (PTU) and an inertial measurement unit (IMU). Three-dimensional field information can be obtained when the PTU rotates the laser rangefinder in the vertical plane. A field profile was modeled by analyzing range data. Otsu’s method was used to detect the crop edge position on each scanning profile, and the least squares method was applied to fit the uncut crop edge. Fundamental performance of the system was first evaluated under laboratory conditions. Then, validation experiments were conducted under both static and dynamic conditions in a wheat field during harvesting season. To verify the error of the detection system, the real position of the edge was measured by GPS for accuracy evaluation. The results showed an average lateral error of ±12 cm, with a Root-Mean-Square Error (RMSE) of 3.01 cm for the static test, and an average lateral error of ±25 cm, with an RMSE of 10.15 cm for the dynamic test. The proposed laser rangefinder-based uncut crop edge detection system exhibited a satisfactory performance for edge detection under different conditions in the field, and can provide reliable information for further study. Keywords: laser rangefinder technology, crop edge detection, combine harvester, navigation, field profile modeling DOI: 10.3965/j.ijabe.20160902.1959 Citation: Zhao T, Noguchi N, Yang L L, Ishii K, Chen J. Development of uncut crop edge detection system based on laser rangefinder for combine harvesters. Int J Agric & Biol Eng, 2016; 9(2): 21－28.

[1]  Thierry Chateau,et al.  Automatic guidance of agricultural vehicles using a laser sensor. , 2000 .

[2]  Noboru Noguchi,et al.  Development of a crawler-type robot tractor using RTK-GPS and IMU , 2014 .

[3]  Ryohei Masuda,et al.  Using multiple sensors to detect uncut crop edges for autonomous guidance systems of head-feeding combine harvesters , 2014 .

[4]  G.W.A.M. van der Heijden,et al.  Image-based particle filtering for navigation in a semi-structured agricultural environment. , 2014 .

[5]  Michihisa Iida,et al.  Vision-based uncut crop edge detection for automated guidance of head-feeding combine , 2014 .

[6]  Kazunobu Ishii,et al.  Development of an Autonomous Navigation System using a Two-dimensional Laser Scanner in an Orchard Application , 2007 .

[7]  Noboru Noguchi,et al.  Development of a robot tractor controlled by a human-driven tractor system , 2015 .

[8]  Kazunobu Ishii,et al.  Development of a Robot Combine Harvester , 2015 .

[9]  Liu Pei,et al.  Navigation control for orchard mobile robot in curve path. , 2012 .

[10]  Noboru Noguchi,et al.  Development of a Laser Scanner-based Navigation System for a Combine Harvester , 2013 .

[11]  杨 亮亮.  Development of a robot tractor implemented an omni-directional safety system , 2013 .

[12]  Philippe Martinet,et al.  A guidance-assistance system for agricultural vehicles , 2000 .

[13]  Ming Li,et al.  Review of research on agricultural vehicle autonomous guidance , 2009 .

[14]  Chen Du,et al.  Navigation line detection arithmetic based on image rotation and projection. , 2009 .

[15]  D. Ehlert,et al.  Sources of angle-dependent errors in terrestrial laser scanner-based crop stand measurement , 2013 .