A Novel Wood Log Measurement Combined Mask R-CNN and Stereo Vision Camera
Wood logs need to be measured for size when passing through customs to verify their quantity and volume. Due to the large number of wood logs needs through customs, a fast and accurate measurement method is required. The traditional log measurement methods are inefficient, have significant errors in...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/14/2/285 |
| _version_ | 1797620983063904256 |
|---|---|
| author | Chunjiang Yu Yongke Sun Yong Cao Jie He Yixing Fu Xiaotao Zhou |
| author_facet | Chunjiang Yu Yongke Sun Yong Cao Jie He Yixing Fu Xiaotao Zhou |
| author_sort | Chunjiang Yu |
| collection | DOAJ |
| description | Wood logs need to be measured for size when passing through customs to verify their quantity and volume. Due to the large number of wood logs needs through customs, a fast and accurate measurement method is required. The traditional log measurement methods are inefficient, have significant errors in determining the long and short diameters of the wood, and are difficult to achieve fast measurements in complex wood stacking environments. We use a Mask R-CNN instance segmentation model to detect the contour of the wood log and employ a binocular stereo camera to measure the log diameter. A rotation search algorithm centered on the wood contour is proposed to find long and short diameters and to optimal log size according to the Chinese standard. The experiments show that the Mask R-CNN we trained obtains 0.796 average precision and 0.943 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>I</mi><mi>O</mi><msub><mi>U</mi><mrow><mi>m</mi><mi>a</mi><mi>s</mi><mi>k</mi></mrow></msub></mrow></semantics></math></inline-formula>, and the recognition rate of wood log ends reaches 98.2%. The average error of the short diameter of the measurement results is 5.7 mm, the average error of the long diameter is 7.19 mm, and the average error of the diameter of the wood is 5.3 mm. |
| first_indexed | 2024-03-11T08:49:16Z |
| format | Article |
| id | doaj.art-d18f0c651850474e9034b63d677b271d |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-11T08:49:16Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-d18f0c651850474e9034b63d677b271d2023-11-16T20:33:51ZengMDPI AGForests1999-49072023-02-0114228510.3390/f14020285A Novel Wood Log Measurement Combined Mask R-CNN and Stereo Vision CameraChunjiang Yu0Yongke Sun1Yong Cao2Jie He3Yixing Fu4Xiaotao Zhou5School of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, ChinaSchool of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, ChinaInternational Engineering and Technology Institute, Hongkong 999077, ChinaSchool of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, ChinaSchool of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, ChinaSchool of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, ChinaWood logs need to be measured for size when passing through customs to verify their quantity and volume. Due to the large number of wood logs needs through customs, a fast and accurate measurement method is required. The traditional log measurement methods are inefficient, have significant errors in determining the long and short diameters of the wood, and are difficult to achieve fast measurements in complex wood stacking environments. We use a Mask R-CNN instance segmentation model to detect the contour of the wood log and employ a binocular stereo camera to measure the log diameter. A rotation search algorithm centered on the wood contour is proposed to find long and short diameters and to optimal log size according to the Chinese standard. The experiments show that the Mask R-CNN we trained obtains 0.796 average precision and 0.943 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>I</mi><mi>O</mi><msub><mi>U</mi><mrow><mi>m</mi><mi>a</mi><mi>s</mi><mi>k</mi></mrow></msub></mrow></semantics></math></inline-formula>, and the recognition rate of wood log ends reaches 98.2%. The average error of the short diameter of the measurement results is 5.7 mm, the average error of the long diameter is 7.19 mm, and the average error of the diameter of the wood is 5.3 mm.https://www.mdpi.com/1999-4907/14/2/285wood log measurementinstance segmentationMask R-CNNbinocular stereo camera |
| spellingShingle | Chunjiang Yu Yongke Sun Yong Cao Jie He Yixing Fu Xiaotao Zhou A Novel Wood Log Measurement Combined Mask R-CNN and Stereo Vision Camera Forests wood log measurement instance segmentation Mask R-CNN binocular stereo camera |
| title | A Novel Wood Log Measurement Combined Mask R-CNN and Stereo Vision Camera |
| title_full | A Novel Wood Log Measurement Combined Mask R-CNN and Stereo Vision Camera |
| title_fullStr | A Novel Wood Log Measurement Combined Mask R-CNN and Stereo Vision Camera |
| title_full_unstemmed | A Novel Wood Log Measurement Combined Mask R-CNN and Stereo Vision Camera |
| title_short | A Novel Wood Log Measurement Combined Mask R-CNN and Stereo Vision Camera |
| title_sort | novel wood log measurement combined mask r cnn and stereo vision camera |
| topic | wood log measurement instance segmentation Mask R-CNN binocular stereo camera |
| url | https://www.mdpi.com/1999-4907/14/2/285 |
| work_keys_str_mv | AT chunjiangyu anovelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera AT yongkesun anovelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera AT yongcao anovelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera AT jiehe anovelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera AT yixingfu anovelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera AT xiaotaozhou anovelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera AT chunjiangyu novelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera AT yongkesun novelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera AT yongcao novelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera AT jiehe novelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera AT yixingfu novelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera AT xiaotaozhou novelwoodlogmeasurementcombinedmaskrcnnandstereovisioncamera |