2012
DOI: 10.1016/j.compag.2012.03.011
|View full text |Cite
|
Sign up to set email alerts
|

LiDaR sensing to monitor straw output quality of a combine harvester

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

1
8
0

Year Published

2013
2013
2021
2021

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 16 publications
(9 citation statements)
references
References 8 publications
1
8
0
Order By: Relevance
“…It is expected that this would result in a more accurate measurement of the swathed-biomass volume. The correlation coefficient (R 2 = 0.79) reported by Lenaerts et al (2012) was comparable to the value found in this study. Similar to the present study, Lenaerts et al (2012) used a LIDAR sensor to correlate the sensed swath height with the combine operating parameters: threshing section setting, concave clearance, and rotor speed.…”
Section: Miscanthus Yield Correlationsupporting
confidence: 90%
See 2 more Smart Citations
“…It is expected that this would result in a more accurate measurement of the swathed-biomass volume. The correlation coefficient (R 2 = 0.79) reported by Lenaerts et al (2012) was comparable to the value found in this study. Similar to the present study, Lenaerts et al (2012) used a LIDAR sensor to correlate the sensed swath height with the combine operating parameters: threshing section setting, concave clearance, and rotor speed.…”
Section: Miscanthus Yield Correlationsupporting
confidence: 90%
“…To predict timothy grass yield, five sensors were mounted on a forage harvester (Savoie et al, 2002). To predict alfalfa yield, a torque sensor was used to measure the power consumed by the mower-conditioner rolls (Kumhála et al, 2007). To predict sugarcane yield on a billet-type sugarcane harvester, a weighing plate was used, and the prediction accuracy was 89% (Mailander et al, 2010).…”
mentioning
confidence: 99%
See 1 more Smart Citation
“…LiDAR, also referred as laser scanning (LS), has evolved into a state-of-the-art technology for highly accurate 3D data acquisition. By now several studies indicate a high value for 3D vegetation description, such as in agricultural monitoring of trees (Rosell and Sanz, 2012;Seidel et al, 2011), field crops (Höfle, 2013;Saeys et al, 2009;Lumme et al, 2008) or harvest residues (Lenaerts et al, 2012). Harvest residues play an important role in agricultural management, for instance concerning the calculation of biomass and subsequently the need of fertilization as 'humus compensation' (Fink, 1996) or for renewable energy production (Pimentel, 1981).…”
Section: Introductionmentioning
confidence: 99%
“…In the test stage, the model weights were fixed, and a resized raw image equal in size to the cropped image used for training was the input of the model. Extracted feature maps from the final conv-net layer were used to generate the CAMs that were calculated by summing the feature maps multiplied by their weight to correspond to the classes, as shown in Equation (2). The visualized CAMs show the pixel-level activations related to the corresponding classes, which can be used as the localization results.…”
Section: Crop Area Segmentationmentioning
confidence: 99%