Tillage boundary detection based on RGB imagery classification for an autonomous tractor

다국어 초록 (Multilingual Abstract)

In this study, a deep learning-based tillage boundary detection method for autonomous tillage by a tractor was developed, which consisted of image cropping, object classification, area segmentation, and boundary detection methods. Full HD (1920 × 1080) images were obtained using a RGB camera installed on the hood of a tractor and were cropped to 112 × 112 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the path boundary was detected using a probability map, which was generated by the integration of softmax outputs.
The results show that the F1-score of the classification was approximately 0.91, and it had a similar performance as the deep learning-based classification task in the agriculture field. The path boundary was determined with edge detection and the Hough transform, and it was compared to the actual path boundary. The average lateral error was approximately 11.4 cm, and the average angle error was approximately 8.9º. The proposed technique can perform as well as other approaches; however, it only needs low cost memory to execute the process unlike other deep learning-based approaches. It is possible that an autonomous farm robot can be easily developed with this proposed technique using a simple hardware configuration.

참고문헌 (Reference)

1 전찬준, "완전 합성곱 신경망을 활용한 자동 포트홀 탐지 기술의 개발 및 평가" 한국ITS학회 17 (17): 55-64, 2018

2 이대현, "영상기반 축사 내 육계 검출 및 밀집도 평가 연구" 한국정보전자통신기술학회 12 (12): 373-379, 2019

3 김완수, "Work load analysis for determination of the reduction gear ratio for a 78 kW all wheel drive electric tractor design" 농업과학연구소 46 (46): 613-627, 2019

4 Stefas N, "Vision-based monitoring of orchards with UAVs" 163 : 104814-, 2019

5 Ming L, "Review of research on agricultural vehicle autonomous guidance" 2 : 1-16, 2009

6 Han XZ, "Path-tracking simulation and field tests for an autoguidance tillage tractor for a paddy field" 112 : 161-171, 2015

7 Shalal N, "Orchard mapping and mobile robot localisation using on-board camera and laser scanner data fusion-Part B : Mapping and localisation" 119 : 267-278, 2015

8 Lenain R, "Mixed kinematic and dynamic sideslip angle observer for accurate control of fast off-road mobile robots" 27 : 181-196, 2010

9 Kim WS, "Machine vision-based automatic disease symptom detection of onion downy mildew" 168 : 105099-, 2020

10 Wang Z, "Machine vision assessment of mango orchard flowering" 151 : 501-511, 2018

11 Malavazi FBP, "LiDAR-only based navigation algorithm for an autonomous agricultural robot" 154 : 71-79, 2018

12 Zhou B, "Learning deep features for discriminative localization" 2921-2929, 2016

13 Krizhevsky A, "Imagenet classification with deep convolutional neural networks" 25 : 1-9, 2012

14 Stombaugh TS, "Guidance of agricultural vehicles at high field speeds" Transactions of the ASABE 537-544, 1999

15 LeCun Y, "Gradient-based learning applied to document recognition" 86 : 2278-2323, 1998

16 Lutz W, "Dimensions of global population projections: What do we know about future population trends and structures" 365 : 2779-2791, 2010

17 Kim YJ, "Development of automation technology for manual transmission of a 50 HP autonomous tractor" 51 : 20-22, 2018

18 Li S, "Development of a following agricultural machinery automatic navigation system" 158 : 335-344, 2019

19 Dian Bah M, "CRowNet : Deep network for crop row detection in UAV images" 8 : 5189-5200, 2019

20 Bakker T, "Autonomous navigation using a robot platform in a sugar beet field" 109 : 357-368, 2011

21 Bell T, "Automatic tractor guidance using carrier-phase differential GPS" 25 : 53-66, 2000

22 Han XZ, "Application of a 3D tractor-driving simulator for slip estimation-based path-tracking control of auto-guided tillage operation" 178 : 70-85, 2019

23 Shehata A, "A survey on hough transform, theory, techniques and applications" 2015

24 Kamilaris A, "A review on the practice of big data analysis in agriculture" 143 : 23-37, 2017