AIRWiki - User contributions [en]

Machine Learning for Crop Weed Classification

2018-02-05T11:28:23Z

LodewijkVoorhoeve:

{{Project
| title=Machine Learning for Crop Weed Image Classification
| short_descr=Automatic detection of crops and weeds by using image data
| tutor=MatteoMatteucci
| students=LodewijkVoorhoeve
| resarea=Machine Learning
| restopic=Image Classification
| start=2017/09/4
| end=2018/01/31
| level=Ms
| type=Thesis
| status=Closed
| image=[[File:Bonirob 2016-05-23-10-37-10 0 frame23 GroundTruth color.png|200px]]
}}

=== Project short description ===

The aim of this project is to transfer the work of Stefano Cereda on crop/weed detection to TensorFlow and to train the model with new data.

=== Dates ===
Start date: 2017/09/04

End date: 2018/01/30

===== Project head(s) =====

[[User:MatteoMatteucci|M.Matteucci]]

===== Students currently working on the project =====

[[User:LodewijkVoorhoeve|Lodewijk Voorhoeve]]

=== Laboratory work and risk analysis ===

This project is related to software developing so there are no dangerous activities

=== Methods ===
Crop and weed classification can be accomplished by analyzing an image with the use of Machine Learning. Supervised Machine Learning makes use of data (for example: an image) and an annotation file (an image of the same size, with colours demarcating the area that belongs to a certain class). Therefore, the basis of this project is the availability of data.

===== Data =====
Two publicly available datasets are used: Crop/Weed Field Image Dataset (CWFID) and Sugar Beets 2016 (SB2016).

=== Results ===
With the modified code, both the CWFID and SB2016 datasets were analysed. For SB2016, a comparison was made with the paper by Milioto, Lottes and Stachniss. The comparison is shown in the image on the right, where the baseline classifiers RFC and SVM perform better than the SegNet architecture of Milioto, Lottes and Stachniss on the crop, but worse on the weed and comparable on the soil.

[[File:crop-weed-soil_comparison.png|200px|thumb|right|Comparison of crop, weed and soil with the metrics of IoU, Precision and Recall. The baseline classifiers RFC and SVM outperform the SegNet neural network architecture on crop, but perform worse on weed and similar on soil.]]

The final report can be found here [[Media:Final_Internship_Report_-_Machine_Learning_for_Crop_and_Weed_Classification_1.0.pdf]]

Machine Learning for Crop Weed Classification

2018-02-05T11:27:42Z

LodewijkVoorhoeve:

{{Project
| title=Machine Learning for Crop Weed Image Classification
| short_descr=Automatic detection of crops and weeds by using image data
| tutor=MatteoMatteucci
| students=LodewijkVoorhoeve
| resarea=Machine Learning
| restopic=Image Classification
| start=2017/09/4
| end=2018/01/31
| level=Ms
| type=Thesis
| status=Closed
| image=[[File:Bonirob 2016-05-23-10-37-10 0 frame23 GroundTruth color.png|150px|thumb]]
}}

=== Project short description ===

The aim of this project is to transfer the work of Stefano Cereda on crop/weed detection to TensorFlow and to train the model with new data.

=== Dates ===
Start date: 2017/09/04

End date: 2018/01/30

===== Project head(s) =====

[[User:MatteoMatteucci|M.Matteucci]]

===== Students currently working on the project =====

[[User:LodewijkVoorhoeve|Lodewijk Voorhoeve]]

=== Laboratory work and risk analysis ===

This project is related to software developing so there are no dangerous activities

=== Methods ===
Crop and weed classification can be accomplished by analyzing an image with the use of Machine Learning. Supervised Machine Learning makes use of data (for example: an image) and an annotation file (an image of the same size, with colours demarcating the area that belongs to a certain class). Therefore, the basis of this project is the availability of data.

===== Data =====
Two publicly available datasets are used: Crop/Weed Field Image Dataset (CWFID) and Sugar Beets 2016 (SB2016).

=== Results ===
With the modified code, both the CWFID and SB2016 datasets were analysed. For SB2016, a comparison was made with the paper by Milioto, Lottes and Stachniss. The comparison is shown in the image on the right, where the baseline classifiers RFC and SVM perform better than the SegNet architecture of Milioto, Lottes and Stachniss on the crop, but worse on the weed and comparable on the soil.

[[File:crop-weed-soil_comparison.png|200px|thumb|right|Comparison of crop, weed and soil with the metrics of IoU, Precision and Recall. The baseline classifiers RFC and SVM outperform the SegNet neural network architecture on crop, but perform worse on weed and similar on soil.]]

The final report can be found here [[Media:Final_Internship_Report_-_Machine_Learning_for_Crop_and_Weed_Classification_1.0.pdf]]

Machine Learning for Crop Weed Classification

2018-02-05T11:27:11Z

LodewijkVoorhoeve:

{{Project
| title=Machine Learning for Crop Weed Image Classification
| short_descr=Automatic detection of crops and weeds by using image data
| tutor=MatteoMatteucci
| students=LodewijkVoorhoeve
| resarea=Machine Learning
| restopic=Image Classification
| start=2017/09/4
| end=2018/01/31
| level=Ms
| type=Thesis
| status=Closed
| image=[[File:Bonirob 2016-05-23-10-37-10 0 frame23 GroundTruth color.png]]
}}

=== Project short description ===

The aim of this project is to transfer the work of Stefano Cereda on crop/weed detection to TensorFlow and to train the model with new data.

=== Dates ===
Start date: 2017/09/04

End date: 2018/01/30

===== Project head(s) =====

[[User:MatteoMatteucci|M.Matteucci]]

===== Students currently working on the project =====

[[User:LodewijkVoorhoeve|Lodewijk Voorhoeve]]

=== Laboratory work and risk analysis ===

This project is related to software developing so there are no dangerous activities

=== Methods ===
Crop and weed classification can be accomplished by analyzing an image with the use of Machine Learning. Supervised Machine Learning makes use of data (for example: an image) and an annotation file (an image of the same size, with colours demarcating the area that belongs to a certain class). Therefore, the basis of this project is the availability of data.

===== Data =====
Two publicly available datasets are used: Crop/Weed Field Image Dataset (CWFID) and Sugar Beets 2016 (SB2016).

=== Results ===
With the modified code, both the CWFID and SB2016 datasets were analysed. For SB2016, a comparison was made with the paper by Milioto, Lottes and Stachniss. The comparison is shown in the image on the right, where the baseline classifiers RFC and SVM perform better than the SegNet architecture of Milioto, Lottes and Stachniss on the crop, but worse on the weed and comparable on the soil.

[[File:crop-weed-soil_comparison.png|200px|thumb|right|Comparison of crop, weed and soil with the metrics of IoU, Precision and Recall. The baseline classifiers RFC and SVM outperform the SegNet neural network architecture on crop, but perform worse on weed and similar on soil.]]

The final report can be found here [[Media:Final_Internship_Report_-_Machine_Learning_for_Crop_and_Weed_Classification_1.0.pdf]]

Machine Learning for Crop Weed Classification

2018-02-05T11:26:31Z

LodewijkVoorhoeve:

{{Project
| title=Machine Learning for Crop Weed Image Classification
| short_descr=Automatic detection of crops and weeds by using image data
| tutor=MatteoMatteucci
| students=LodewijkVoorhoeve
| resarea=Machine Learning
| restopic=Image Classification
| start=2017/09/4
| end=2018/01/31
| level=Ms
| type=Thesis
| status=Inactive
| image=File:Bonirob 2016-05-23-10-37-10 0 frame23 GroundTruth color.png
}}

=== Project short description ===

The aim of this project is to transfer the work of Stefano Cereda on crop/weed detection to TensorFlow and to train the model with new data.

=== Dates ===
Start date: 2017/09/04

End date: 2018/01/30

===== Project head(s) =====

[[User:MatteoMatteucci|M.Matteucci]]

===== Students currently working on the project =====

[[User:LodewijkVoorhoeve|Lodewijk Voorhoeve]]

=== Laboratory work and risk analysis ===

This project is related to software developing so there are no dangerous activities

=== Methods ===
Crop and weed classification can be accomplished by analyzing an image with the use of Machine Learning. Supervised Machine Learning makes use of data (for example: an image) and an annotation file (an image of the same size, with colours demarcating the area that belongs to a certain class). Therefore, the basis of this project is the availability of data.

===== Data =====
Two publicly available datasets are used: Crop/Weed Field Image Dataset (CWFID) and Sugar Beets 2016 (SB2016).

=== Results ===
With the modified code, both the CWFID and SB2016 datasets were analysed. For SB2016, a comparison was made with the paper by Milioto, Lottes and Stachniss. The comparison is shown in the image on the right, where the baseline classifiers RFC and SVM perform better than the SegNet architecture of Milioto, Lottes and Stachniss on the crop, but worse on the weed and comparable on the soil.

[[File:crop-weed-soil_comparison.png|200px|thumb|right|Comparison of crop, weed and soil with the metrics of IoU, Precision and Recall. The baseline classifiers RFC and SVM outperform the SegNet neural network architecture on crop, but perform worse on weed and similar on soil.]]

The final report can be found here [[Media:Final_Internship_Report_-_Machine_Learning_for_Crop_and_Weed_Classification_1.0.pdf]]

File:Bonirob 2016-05-23-10-37-10 0 frame23 GroundTruth color.png

2018-02-05T11:26:09Z

LodewijkVoorhoeve: Ground truth image (nr. 23) of the Sugar Beets 2016 dataset, captured with the agricultural field robot bonirob. Image contains sugar beets (red) and multiple weeds (blue, yellow, orange)

Ground truth image (nr. 23) of the Sugar Beets 2016 dataset, captured with the agricultural field robot bonirob. Image contains sugar beets (red) and multiple weeds (blue, yellow, orange)

Machine Learning for Crop Weed Classification

2018-02-05T11:21:15Z

LodewijkVoorhoeve: /* Results */

{{Project
| title=Machine Learning for Crop Weed Image Classification
| short_descr=Automatic detection of crops and weeds by using image data
| tutor=MatteoMatteucci
| students=LodewijkVoorhoeve
| resarea=Machine Learning
| restopic=Image Classification
| start=2017/09/4
| end=2018/01/31
| level=Ms
| type=Thesis
| status=Active
| image=
}}

=== Project short description ===

The aim of this project is to transfer the work of Stefano Cereda on crop/weed detection to TensorFlow and to train the model with new data.

=== Dates ===
Start date: 2017/09/04

End date: 2018/01/30

===== Project head(s) =====

[[User:MatteoMatteucci|M.Matteucci]]

===== Students currently working on the project =====

[[User:LodewijkVoorhoeve|Lodewijk Voorhoeve]]

=== Laboratory work and risk analysis ===

This project is related to software developing so there are no dangerous activities

=== Methods ===
Crop and weed classification can be accomplished by analyzing an image with the use of Machine Learning. Supervised Machine Learning makes use of data (for example: an image) and an annotation file (an image of the same size, with colours demarcating the area that belongs to a certain class). Therefore, the basis of this project is the availability of data.

===== Data =====
Two publicly available datasets are used: Crop/Weed Field Image Dataset (CWFID) and Sugar Beets 2016 (SB2016).

=== Results ===
With the modified code, both the CWFID and SB2016 datasets were analysed. For SB2016, a comparison was made with the paper by Milioto, Lottes and Stachniss. The comparison is shown in the image on the right, where the baseline classifiers RFC and SVM perform better than the SegNet architecture of Milioto, Lottes and Stachniss on the crop, but worse on the weed and comparable on the soil.

[[File:crop-weed-soil_comparison.png|200px|thumb|right|Comparison of crop, weed and soil with the metrics of IoU, Precision and Recall. The baseline classifiers RFC and SVM outperform the SegNet neural network architecture on crop, but perform worse on weed and similar on soil.]]

The final report can be found here [[Media:Final_Internship_Report_-_Machine_Learning_for_Crop_and_Weed_Classification_1.0.pdf]]

Machine Learning for Crop Weed Classification

2018-02-05T11:01:49Z

LodewijkVoorhoeve: /* Results */

{{Project
| title=Machine Learning for Crop Weed Image Classification
| short_descr=Automatic detection of crops and weeds by using image data
| tutor=MatteoMatteucci
| students=LodewijkVoorhoeve
| resarea=Machine Learning
| restopic=Image Classification
| start=2017/09/4
| end=2018/01/31
| level=Ms
| type=Thesis
| status=Active
| image=
}}

=== Project short description ===

The aim of this project is to transfer the work of Stefano Cereda on crop/weed detection to TensorFlow and to train the model with new data.

=== Dates ===
Start date: 2017/09/04

End date: 2018/01/30

===== Project head(s) =====

[[User:MatteoMatteucci|M.Matteucci]]

===== Students currently working on the project =====

[[User:LodewijkVoorhoeve|Lodewijk Voorhoeve]]

=== Laboratory work and risk analysis ===

This project is related to software developing so there are no dangerous activities

=== Methods ===
Crop and weed classification can be accomplished by analyzing an image with the use of Machine Learning. Supervised Machine Learning makes use of data (for example: an image) and an annotation file (an image of the same size, with colours demarcating the area that belongs to a certain class). Therefore, the basis of this project is the availability of data.

===== Data =====
Two publicly available datasets are used: Crop/Weed Field Image Dataset (CWFID) and Sugar Beets 2016 (SB2016).

=== Results ===
With the modified code, both the CWFID and SB2016 datasets were analysed. For SB2016, a comparison was made with the paper by Milioto, Lottes and Stachniss. The comparison is shown in the image on the right, where the baseline classifiers RFC and SVM perform better than the SegNet architecture of Milioto, Lottes and Stachniss on the crop, but worse on the weed and comparable on the soil.

[[File:crop-weed-soil_comparison.png|200px|thumb|right|Comparison of crop, weed and soil with the metrics of IoU, Precision and Recall. The baseline classifiers RFC and SVM outperform the SegNet neural network architecture on crop, but perform worse on weed and similar on soil.]]

Machine Learning for Crop Weed Classification

2018-02-05T10:59:17Z

LodewijkVoorhoeve: /* Results */

{{Project
| title=Machine Learning for Crop Weed Image Classification
| short_descr=Automatic detection of crops and weeds by using image data
| tutor=MatteoMatteucci
| students=LodewijkVoorhoeve
| resarea=Machine Learning
| restopic=Image Classification
| start=2017/09/4
| end=2018/01/31
| level=Ms
| type=Thesis
| status=Active
| image=
}}

=== Project short description ===

The aim of this project is to transfer the work of Stefano Cereda on crop/weed detection to TensorFlow and to train the model with new data.

=== Dates ===
Start date: 2017/09/04

End date: 2018/01/30

===== Project head(s) =====

[[User:MatteoMatteucci|M.Matteucci]]

===== Students currently working on the project =====

[[User:LodewijkVoorhoeve|Lodewijk Voorhoeve]]

=== Laboratory work and risk analysis ===

This project is related to software developing so there are no dangerous activities

=== Methods ===
Crop and weed classification can be accomplished by analyzing an image with the use of Machine Learning. Supervised Machine Learning makes use of data (for example: an image) and an annotation file (an image of the same size, with colours demarcating the area that belongs to a certain class). Therefore, the basis of this project is the availability of data.

===== Data =====
Two publicly available datasets are used: Crop/Weed Field Image Dataset (CWFID) and Sugar Beets 2016 (SB2016).

=== Results ===
With the modified code, both the CWFID and SB2016 datasets were analysed. For SB2016, a comparison was made with the paper by Milioto, Lottes and Stachniss. The comparison is shown in the image on the right, where the baseline classifiers RFC and SVM perform better than the SegNet architecture of Milioto, Lottes and Stachniss on the crop, but worse on the weed and comparable on the soil.

[[File:crop-weed-soil_comparison.png|200px|thumb|left|alt text]]

File:Crop-weed-soil comparison.png

2018-02-05T10:57:45Z

LodewijkVoorhoeve: comparison of crop, weed and soil with the metrics of IoU, Precision and Recall. The baseline classifiers RFC and SVM outperform the SegNet neural network architecture on crop, but perform worse on weed and similar on soil.

comparison of crop, weed and soil with the metrics of IoU, Precision and Recall. The baseline classifiers RFC and SVM outperform the SegNet neural network architecture on crop, but perform worse on weed and similar on soil.

File:Final Internship Report - Machine Learning for Crop and Weed Classification 1.0.pdf

2018-02-05T10:55:07Z

LodewijkVoorhoeve: Academic internship report about crop and weed classification using machine learning. The project was supervised by Matteo Matteucci and carried out by Lodewijk Voorhoeve (Wageningen UR).

Academic internship report about crop and weed classification using machine learning. The project was supervised by Matteo Matteucci and carried out by Lodewijk Voorhoeve (Wageningen UR).

Machine Learning for Crop Weed Classification

2018-02-05T10:51:41Z

LodewijkVoorhoeve: /* Results */

{{Project
| title=Machine Learning for Crop Weed Image Classification
| short_descr=Automatic detection of crops and weeds by using image data
| tutor=MatteoMatteucci
| students=LodewijkVoorhoeve
| resarea=Machine Learning
| restopic=Image Classification
| start=2017/09/4
| end=2018/01/31
| level=Ms
| type=Thesis
| status=Active
| image=
}}

=== Project short description ===

The aim of this project is to transfer the work of Stefano Cereda on crop/weed detection to TensorFlow and to train the model with new data.

=== Dates ===
Start date: 2017/09/04

End date: 2018/01/30

===== Project head(s) =====

[[User:MatteoMatteucci|M.Matteucci]]

===== Students currently working on the project =====

[[User:LodewijkVoorhoeve|Lodewijk Voorhoeve]]

=== Laboratory work and risk analysis ===

This project is related to software developing so there are no dangerous activities

=== Methods ===
Crop and weed classification can be accomplished by analyzing an image with the use of Machine Learning. Supervised Machine Learning makes use of data (for example: an image) and an annotation file (an image of the same size, with colours demarcating the area that belongs to a certain class). Therefore, the basis of this project is the availability of data.

===== Data =====
Two publicly available datasets are used: Crop/Weed Field Image Dataset (CWFID) and Sugar Beets 2016 (SB2016).

=== Results ===
With the modified code, both the CWFID and SB2016 datasets were analysed. For SB2016, a comparison was made with the paper by Milioto, Lottes and Stachniss. The comparison is shown in the image on the right, where the baseline classifiers RFC and SVM perform better than the SegNet architecture of Milioto, Lottes and Stachniss on the crop, but worse on the weed and comparable on the soil.

Machine Learning for Crop Weed Classification

2018-01-29T15:14:00Z

LodewijkVoorhoeve:

Machine Learning for Crop Weed Classification

2018-01-29T14:09:37Z

LodewijkVoorhoeve:

Machine Learning for Crop Weed Classification

2018-01-29T14:05:36Z

LodewijkVoorhoeve: /* Dates */

Machine Learning for Crop Weed Classification

2017-09-04T08:08:44Z

LodewijkVoorhoeve: /* Students currently working on the project */

Machine Learning for Crop Weed Classification

2017-09-04T06:35:57Z

LodewijkVoorhoeve:

Machine Learning for Crop Weed Classification

2017-09-04T05:57:03Z

LodewijkVoorhoeve:

Machine Learning for Crop Weed Classification

2017-09-04T05:56:33Z

LodewijkVoorhoeve:

Machine Learning for Crop Weed Classification

2017-09-04T05:56:05Z

LodewijkVoorhoeve:

Machine Learning for Crop Weed Classification

2017-09-04T05:55:18Z

LodewijkVoorhoeve: Created page with "{{Project | title=Machine Learning for Crop Weed Image Classification | short_descr=Automatic detection of crops and weeds by using image data | tutor=Matteo Matteucci | stude..."

User:LodewijkVoorhoeve

2017-09-01T10:26:52Z

LodewijkVoorhoeve:

{{Student
|category=Student
|firstname=Lodewijk
|lastname=Voorhoeve
|photo=LodewijkVoorhoeve.jpg
|email=lodewijk.voorhoeve@wur.nl
|projectpage=Machine Learning for Crop Weed Classification
|advisor=Matteo Mateucci
|status=active
}}

User:LodewijkVoorhoeve

2017-09-01T10:26:15Z

LodewijkVoorhoeve: Created page with "{{Student |category=Student |firstname=Lodewijk |lastname=Voorhoeve |photo=LodewijkVoorhoeve.jpg |email=lodewijk.voorhoeve@wur.nl |projectpage=Machine Learning for Crop Weed C..."

File:LodewijkVoorhoeve.jpg

2017-09-01T10:23:44Z

LodewijkVoorhoeve: Me in the Pyrenees (Refuge Rulhe)

Me in the Pyrenees (Refuge Rulhe)