A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network
In an orchard environment with a complex background and changing light conditions, the banana stalk, fruit, branches, and leaves are very similar in color. The fast and accurate detection and segmentation of a banana stalk are crucial to realize the automatic picking using a banana picking robot. In...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/9/3/66 |
| _version_ | 1797540858753449984 |
|---|---|
| author | Tianci Chen Rihong Zhang Lixue Zhu Shiang Zhang Xiaomin Li |
| author_facet | Tianci Chen Rihong Zhang Lixue Zhu Shiang Zhang Xiaomin Li |
| author_sort | Tianci Chen |
| collection | DOAJ |
| description | In an orchard environment with a complex background and changing light conditions, the banana stalk, fruit, branches, and leaves are very similar in color. The fast and accurate detection and segmentation of a banana stalk are crucial to realize the automatic picking using a banana picking robot. In this paper, a banana stalk segmentation method based on a lightweight multi-feature fusion deep neural network (MFN) is proposed. The proposed network is mainly composed of encoding and decoding networks, in which the sandglass bottleneck design is adopted to alleviate the information a loss in high dimension. In the decoding network, a different sized dilated convolution kernel is used for convolution operation to make the extracted banana stalk features denser. The proposed network is verified by experiments. In the experiments, the detection precision, segmentation accuracy, number of parameters, operation efficiency, and average execution time are used as evaluation metrics, and the proposed network is compared with Resnet_Segnet, Mobilenet_Segnet, and a few other networks. The experimental results show that compared to other networks, the number of network parameters of the proposed network is significantly reduced, the running frame rate is improved, and the average execution time is shortened. |
| first_indexed | 2024-03-10T13:07:01Z |
| format | Article |
| id | doaj.art-a2a5dcaacaf646b0aba88392d0b9b479 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-10T13:07:01Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-a2a5dcaacaf646b0aba88392d0b9b4792023-11-21T11:03:06ZengMDPI AGMachines2075-17022021-03-01936610.3390/machines9030066A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural NetworkTianci Chen0Rihong Zhang1Lixue Zhu2Shiang Zhang3Xiaomin Li4College of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaCollege of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, ChinaIn an orchard environment with a complex background and changing light conditions, the banana stalk, fruit, branches, and leaves are very similar in color. The fast and accurate detection and segmentation of a banana stalk are crucial to realize the automatic picking using a banana picking robot. In this paper, a banana stalk segmentation method based on a lightweight multi-feature fusion deep neural network (MFN) is proposed. The proposed network is mainly composed of encoding and decoding networks, in which the sandglass bottleneck design is adopted to alleviate the information a loss in high dimension. In the decoding network, a different sized dilated convolution kernel is used for convolution operation to make the extracted banana stalk features denser. The proposed network is verified by experiments. In the experiments, the detection precision, segmentation accuracy, number of parameters, operation efficiency, and average execution time are used as evaluation metrics, and the proposed network is compared with Resnet_Segnet, Mobilenet_Segnet, and a few other networks. The experimental results show that compared to other networks, the number of network parameters of the proposed network is significantly reduced, the running frame rate is improved, and the average execution time is shortened.https://www.mdpi.com/2075-1702/9/3/66banana stalkdilated convolutionlightweight networkmulti-feature structuresandglass structure |
| spellingShingle | Tianci Chen Rihong Zhang Lixue Zhu Shiang Zhang Xiaomin Li A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network Machines banana stalk dilated convolution lightweight network multi-feature structure sandglass structure |
| title | A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network |
| title_full | A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network |
| title_fullStr | A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network |
| title_full_unstemmed | A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network |
| title_short | A Method of Fast Segmentation for Banana Stalk Exploited Lightweight Multi-Feature Fusion Deep Neural Network |
| title_sort | method of fast segmentation for banana stalk exploited lightweight multi feature fusion deep neural network |
| topic | banana stalk dilated convolution lightweight network multi-feature structure sandglass structure |
| url | https://www.mdpi.com/2075-1702/9/3/66 |
| work_keys_str_mv | AT tiancichen amethodoffastsegmentationforbananastalkexploitedlightweightmultifeaturefusiondeepneuralnetwork AT rihongzhang amethodoffastsegmentationforbananastalkexploitedlightweightmultifeaturefusiondeepneuralnetwork AT lixuezhu amethodoffastsegmentationforbananastalkexploitedlightweightmultifeaturefusiondeepneuralnetwork AT shiangzhang amethodoffastsegmentationforbananastalkexploitedlightweightmultifeaturefusiondeepneuralnetwork AT xiaominli amethodoffastsegmentationforbananastalkexploitedlightweightmultifeaturefusiondeepneuralnetwork AT tiancichen methodoffastsegmentationforbananastalkexploitedlightweightmultifeaturefusiondeepneuralnetwork AT rihongzhang methodoffastsegmentationforbananastalkexploitedlightweightmultifeaturefusiondeepneuralnetwork AT lixuezhu methodoffastsegmentationforbananastalkexploitedlightweightmultifeaturefusiondeepneuralnetwork AT shiangzhang methodoffastsegmentationforbananastalkexploitedlightweightmultifeaturefusiondeepneuralnetwork AT xiaominli methodoffastsegmentationforbananastalkexploitedlightweightmultifeaturefusiondeepneuralnetwork |