Using multiple sensors to detect uncut crop edges for autonomous guidance systems of head-feeding combine harvesters

Cho, Wonjae; Iida, Michihisa; Suguri, Masahiko; Masuda, R.; Kurita, Hiroki

doi:10.1016/j.eaef.2014.02.004

Cited by 16 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These factors require real-time and accurate coordination to achieve optimal performance. Sensor and information communication technology integrated in intelligent harvesting robot could provide the best solution [100][101][102] . A computer program written in Visual Basic could be used to select optimum operating performance in grain crop thresher.…”

Section: Twin Rotor and Four Drum Of New Hollandmentioning

confidence: 99%

Review of grain threshing theory and technology

Chen

Han

et al. 2018

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

Threshing is the most important function of grain harvester. Grain loss and damage in harvesting are significantly related to threshing theory and technology. There are four kinds of threshing principles including impact, rubbing, combing and grinding. Four types of contact models between grain and threshing components have been constructed correspondently. Grain damage can be regarded as a function of peripheral velocity and contact pattern of impacting. Grain loss can be regarded as a function of contact pattern of rasp bars. Grain loss coming from cleaning and separation in the subsequent process of combing threshing was significantly decreased. Tangential and axial threshing technologies have been applied in grain threshing system widely. It showed that in the combined application, tangential rolls are used to accelerate grain flow, and axial rolls are used to increase threshing quality especially lower loss and damage. Conical concave may take the place of the traditional cylindrical one. With the development of sensor technology and communication technology, intelligent harvesting robot and automatic threshing system will be integrated together to improve grain quality and operation comfort.

show abstract

Section: Twin Rotor and Four Drum Of New Hollandmentioning

confidence: 99%

Review of grain threshing theory and technology

Chen

Han

et al. 2018

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

show abstract

“…One of the autonomous agricultural machine developments was carried out on a combine harvester. Several studies on combine harvester: combine harvester guidance system by detecting cutting edges using machine vision [1], combine harvester robot trajectory control [2], development of laser navigation system for combine harvester [3], detecting the cutting edge of a combine harvester using multiple sensors [4], estimating the heading position of the combine harvester during turning maneuvers [5], and developing an automatic guidance system for the combine harvester [6]. These various studies use different methods but have the same ultimate goal to get a combine harvester that can operate autonomously.…”

Section: Introductionmentioning

confidence: 99%

Development of the turn algorithm of an autonomous combine harvester at the corner of paddy fields

Sutisna

Subrata

Setiawan

et al. 2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

One of the problems that occur in harvesting rice using a combine harvester is when at the corner of the paddy field, especially in harvesting the outermost path. The outer harvesting path is very close to the edge of the paddy field, so that the free space for its maneuverer is very limited. This study aims to develop an algorithm to overcome difficulties when the combine harvester turns at the corner of the paddy field. The turning algorithm was designed using two methods: turning 90° without backward movement and turning 90° with backward movement. The first method is applied to several paths closest to the paddy field bunds, while the second method is applied to the remaining paths close to the midpoint of the paddy fields. The reason for applying the second method in the middle of the paddy field is that there is sufficient free space for backward movement. The combination of the two methods was tested on a simulated paddy field area of 225 m2. The test results of the combination of the two turning methods showed that the total area of the plant that was not cut was 3.25 m2, with an average turning time of 12.4 seconds.

show abstract

“…Research into machine-vision-based assistance or guidance systems for combine harvesters has been going on for the past few decades [ 1 , 6 ]. Methods have been developed based on various data sources: color space [ 5 , 7 , 8 ] and distance information obtained via stereo camera [ 1 , 9 , 10 ], LiDAR [ 11 , 12 , 13 ], and depth camera [ 14 , 15 ]. These usually extract the boundary between the harvested and unharvested areas by detecting the uncut crop area.…”

Section: Introductionmentioning

confidence: 99%

Weakly Supervised Crop Area Segmentation for an Autonomous Combine Harvester

Kim

Lee

Kim

et al. 2021

Sensors

View full text Add to dashboard Cite

Machine vision with deep learning is a promising type of automatic visual perception for detecting and segmenting an object effectively; however, the scarcity of labelled datasets in agricultural fields prevents the application of deep learning to agriculture. For this reason, this study proposes weakly supervised crop area segmentation (WSCAS) to identify the uncut crop area efficiently for path guidance. Weakly supervised learning has advantage for training models because it entails less laborious annotation. The proposed method trains the classification model using area-specific images so that the target area can be segmented from the input image based on implicitly learned localization. This way makes the model implementation easy even with a small data scale. The performance of the proposed method was evaluated using recorded video frames that were then compared with previous deep-learning-based segmentation methods. The results showed that the proposed method can be conducted with the lowest inference time and that the crop area can be localized with an intersection over union of approximately 0.94. Additionally, the uncut crop edge could be detected for practical use based on the segmentation results with post-image processing such as with a Canny edge detector and Hough transformation. The proposed method showed the significant ability of using automatic perception in agricultural navigation to infer the crop area with real-time level speed and have localization comparable to existing semantic segmentation methods. It is expected that our method will be used as essential tool for the automatic path guidance system of a combine harvester.

show abstract

Using multiple sensors to detect uncut crop edges for autonomous guidance systems of head-feeding combine harvesters

Cited by 16 publications

References 4 publications

Review of grain threshing theory and technology

Review of grain threshing theory and technology

Development of the turn algorithm of an autonomous combine harvester at the corner of paddy fields

Weakly Supervised Crop Area Segmentation for an Autonomous Combine Harvester

Contact Info

Product

Resources

About