Grape yield estimation with a smartphone’s colour and depth cameras using machine learning and computer vision techniques

Grape yield estimation with a smartphone’s colour and depth cameras using machine learning and computer vision techniques. Parr, B., Legg, M., & Alam, F. Computers and Electronics in Agriculture, 213:108174, Elsevier, 10, 2023.

Paper doi abstract bibtex

A smartphone with both colour and time of flight depth cameras is used for automated grape yield estimation of Chardonnay grapes. A new technique is developed to automatically identify grape berries in the smartphone's depth maps. This utilises the distortion peaks in the depth map caused by diffused scattering of the light within each grape berry. This technique is then extended to allow unsupervised training of a YOLOv7 model for the detection of grape berries in the smartphone's colour images. A correlation coefficient (R2) of 0.946 was achieved when comparing the count of grape berries observed in RGB images to those accurately identified by YOLO. Additionally, an average precision score of 0.970 was attained. Two techniques are then presented to automatically estimate the size of the grape berries and generate 3D models of grape bunches using both colour and depth information.

@article{
 title = {Grape yield estimation with a smartphone’s colour and depth cameras using machine learning and computer vision techniques},
 type = {article},
 year = {2023},
 keywords = {Berry detection,Depth camera,Grapes,RGB-D,YOLO,Yield estimation},
 pages = {108174},
 volume = {213},
 month = {10},
 publisher = {Elsevier},
 day = {1},
 id = {0eb92be6-6b9a-3104-85d0-45a943b53730},
 created = {2023-10-27T06:13:29.083Z},
 accessed = {2023-10-27},
 file_attached = {true},
 profile_id = {f1f70cad-e32d-3de2-a3c0-be1736cb88be},
 group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
 last_modified = {2023-11-06T09:35:24.634Z},
 read = {true},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {A smartphone with both colour and time of flight depth cameras is used for automated grape yield estimation of Chardonnay grapes. A new technique is developed to automatically identify grape berries in the smartphone's depth maps. This utilises the distortion peaks in the depth map caused by diffused scattering of the light within each grape berry. This technique is then extended to allow unsupervised training of a YOLOv7 model for the detection of grape berries in the smartphone's colour images. A correlation coefficient (R2) of 0.946 was achieved when comparing the count of grape berries observed in RGB images to those accurately identified by YOLO. Additionally, an average precision score of 0.970 was attained. Two techniques are then presented to automatically estimate the size of the grape berries and generate 3D models of grape bunches using both colour and depth information.},
 bibtype = {article},
 author = {Parr, Baden and Legg, Mathew and Alam, Fakhrul},
 doi = {10.1016/J.COMPAG.2023.108174},
 journal = {Computers and Electronics in Agriculture}
}

Downloads: 0

{"_id":"2PkuDXNNW2HGmv95y","bibbaseid":"parr-legg-alam-grapeyieldestimationwithasmartphonescolouranddepthcamerasusingmachinelearningandcomputervisiontechniques-2023","author_short":["Parr, B.","Legg, M.","Alam, F."],"bibdata":{"title":"Grape yield estimation with a smartphone’s colour and depth cameras using machine learning and computer vision techniques","type":"article","year":"2023","keywords":"Berry detection,Depth camera,Grapes,RGB-D,YOLO,Yield estimation","pages":"108174","volume":"213","month":"10","publisher":"Elsevier","day":"1","id":"0eb92be6-6b9a-3104-85d0-45a943b53730","created":"2023-10-27T06:13:29.083Z","accessed":"2023-10-27","file_attached":"true","profile_id":"f1f70cad-e32d-3de2-a3c0-be1736cb88be","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2023-11-06T09:35:24.634Z","read":"true","starred":false,"authored":false,"confirmed":false,"hidden":false,"private_publication":false,"abstract":"A smartphone with both colour and time of flight depth cameras is used for automated grape yield estimation of Chardonnay grapes. A new technique is developed to automatically identify grape berries in the smartphone's depth maps. This utilises the distortion peaks in the depth map caused by diffused scattering of the light within each grape berry. This technique is then extended to allow unsupervised training of a YOLOv7 model for the detection of grape berries in the smartphone's colour images. A correlation coefficient (R2) of 0.946 was achieved when comparing the count of grape berries observed in RGB images to those accurately identified by YOLO. Additionally, an average precision score of 0.970 was attained. Two techniques are then presented to automatically estimate the size of the grape berries and generate 3D models of grape bunches using both colour and depth information.","bibtype":"article","author":"Parr, Baden and Legg, Mathew and Alam, Fakhrul","doi":"10.1016/J.COMPAG.2023.108174","journal":"Computers and Electronics in Agriculture","bibtex":"@article{\n title = {Grape yield estimation with a smartphone’s colour and depth cameras using machine learning and computer vision techniques},\n type = {article},\n year = {2023},\n keywords = {Berry detection,Depth camera,Grapes,RGB-D,YOLO,Yield estimation},\n pages = {108174},\n volume = {213},\n month = {10},\n publisher = {Elsevier},\n day = {1},\n id = {0eb92be6-6b9a-3104-85d0-45a943b53730},\n created = {2023-10-27T06:13:29.083Z},\n accessed = {2023-10-27},\n file_attached = {true},\n profile_id = {f1f70cad-e32d-3de2-a3c0-be1736cb88be},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2023-11-06T09:35:24.634Z},\n read = {true},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n private_publication = {false},\n abstract = {A smartphone with both colour and time of flight depth cameras is used for automated grape yield estimation of Chardonnay grapes. A new technique is developed to automatically identify grape berries in the smartphone's depth maps. This utilises the distortion peaks in the depth map caused by diffused scattering of the light within each grape berry. This technique is then extended to allow unsupervised training of a YOLOv7 model for the detection of grape berries in the smartphone's colour images. A correlation coefficient (R2) of 0.946 was achieved when comparing the count of grape berries observed in RGB images to those accurately identified by YOLO. Additionally, an average precision score of 0.970 was attained. Two techniques are then presented to automatically estimate the size of the grape berries and generate 3D models of grape bunches using both colour and depth information.},\n bibtype = {article},\n author = {Parr, Baden and Legg, Mathew and Alam, Fakhrul},\n doi = {10.1016/J.COMPAG.2023.108174},\n journal = {Computers and Electronics in Agriculture}\n}","author_short":["Parr, B.","Legg, M.","Alam, F."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/160a1e28-ab54-3e8b-288c-77837f07f20e/full_text.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"parr-legg-alam-grapeyieldestimationwithasmartphonescolouranddepthcamerasusingmachinelearningandcomputervisiontechniques-2023","role":"author","keyword":["Berry detection","Depth camera","Grapes","RGB-D","YOLO","Yield estimation"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["2252seNhipfTmjEBQ"],"keywords":["berry detection","depth camera","grapes","rgb-d","yolo","yield estimation"],"search_terms":["grape","yield","estimation","smartphone","colour","depth","cameras","using","machine","learning","computer","vision","techniques","parr","legg","alam"],"title":"Grape yield estimation with a smartphone’s colour and depth cameras using machine learning and computer vision techniques","year":2023}