Attention-aided lightweight networks friendly to smart weeding robot hardware resources for crops and weeds semantic segmentation
Weed control is a global issue of great concern, and smart weeding robots equipped with advanced vision algorithms can perform efficient and precise weed control. Furthermore, the application of smart weeding robots has great potential for building environmentally friendly agriculture and saving hum...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-12-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1320448/full |
| _version_ | 1797384272061923328 |
|---|---|
| author | Yifan Wei Yuncong Feng Yuncong Feng Yuncong Feng Xiaotang Zhou Xiaotang Zhou Guishen Wang Guishen Wang |
| author_facet | Yifan Wei Yuncong Feng Yuncong Feng Yuncong Feng Xiaotang Zhou Xiaotang Zhou Guishen Wang Guishen Wang |
| author_sort | Yifan Wei |
| collection | DOAJ |
| description | Weed control is a global issue of great concern, and smart weeding robots equipped with advanced vision algorithms can perform efficient and precise weed control. Furthermore, the application of smart weeding robots has great potential for building environmentally friendly agriculture and saving human and material resources. However, most networks used in intelligent weeding robots tend to solely prioritize enhancing segmentation accuracy, disregarding the hardware constraints of embedded devices. Moreover, generalized lightweight networks are unsuitable for crop and weed segmentation tasks. Therefore, we propose an Attention-aided lightweight network for crop and weed semantic segmentation. The proposed network has a parameter count of 0.11M, Floating-point Operations count of 0.24G. Our network is based on an encoder and decoder structure, incorporating attention module to ensures both fast inference speed and accurate segmentation while utilizing fewer hardware resources. The dual attention block is employed to explore the potential relationships within the dataset, providing powerful regularization and enhancing the generalization ability of the attention mechanism, it also facilitates information integration between channels. To enhance the local and global semantic information acquisition and interaction, we utilize the refinement dilated conv block instead of 2D convolution within the deep network. This substitution effectively reduces the number and complexity of network parameters and improves the computation rate. To preserve spatial information, we introduce the spatial connectivity attention block. This block not only acquires more precise spatial information but also utilizes shared weight convolution to handle multi-stage feature maps, thereby further reducing network complexity. The segmentation performance of the proposed network is evaluated on three publicly available datasets: the BoniRob dataset, the Rice Seeding dataset, and the WeedMap dataset. Additionally, we measure the inference time and Frame Per Second on the NVIDIA Jetson Xavier NX embedded system, the results are 18.14 msec and 55.1 FPS. Experimental results demonstrate that our network maintains better inference speed on resource-constrained embedded systems and has competitive segmentation performance. |
| first_indexed | 2024-03-08T21:33:03Z |
| format | Article |
| id | doaj.art-485d0a2b1287405fa1abc06e798afc2a |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-03-08T21:33:03Z |
| publishDate | 2023-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-485d0a2b1287405fa1abc06e798afc2a2023-12-21T04:41:04ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-12-011410.3389/fpls.2023.13204481320448Attention-aided lightweight networks friendly to smart weeding robot hardware resources for crops and weeds semantic segmentationYifan Wei0Yuncong Feng1Yuncong Feng2Yuncong Feng3Xiaotang Zhou4Xiaotang Zhou5Guishen Wang6Guishen Wang7College of Computer Science and Engineering, Changchun University of Technology, Changchun, Jilin, ChinaCollege of Computer Science and Engineering, Changchun University of Technology, Changchun, Jilin, ChinaArtificial Intelligence Research Institute, Changchun University of Technology, Changchun, Jilin, ChinaKey Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, Jilin, ChinaCollege of Computer Science and Engineering, Changchun University of Technology, Changchun, Jilin, ChinaArtificial Intelligence Research Institute, Changchun University of Technology, Changchun, Jilin, ChinaCollege of Computer Science and Engineering, Changchun University of Technology, Changchun, Jilin, ChinaArtificial Intelligence Research Institute, Changchun University of Technology, Changchun, Jilin, ChinaWeed control is a global issue of great concern, and smart weeding robots equipped with advanced vision algorithms can perform efficient and precise weed control. Furthermore, the application of smart weeding robots has great potential for building environmentally friendly agriculture and saving human and material resources. However, most networks used in intelligent weeding robots tend to solely prioritize enhancing segmentation accuracy, disregarding the hardware constraints of embedded devices. Moreover, generalized lightweight networks are unsuitable for crop and weed segmentation tasks. Therefore, we propose an Attention-aided lightweight network for crop and weed semantic segmentation. The proposed network has a parameter count of 0.11M, Floating-point Operations count of 0.24G. Our network is based on an encoder and decoder structure, incorporating attention module to ensures both fast inference speed and accurate segmentation while utilizing fewer hardware resources. The dual attention block is employed to explore the potential relationships within the dataset, providing powerful regularization and enhancing the generalization ability of the attention mechanism, it also facilitates information integration between channels. To enhance the local and global semantic information acquisition and interaction, we utilize the refinement dilated conv block instead of 2D convolution within the deep network. This substitution effectively reduces the number and complexity of network parameters and improves the computation rate. To preserve spatial information, we introduce the spatial connectivity attention block. This block not only acquires more precise spatial information but also utilizes shared weight convolution to handle multi-stage feature maps, thereby further reducing network complexity. The segmentation performance of the proposed network is evaluated on three publicly available datasets: the BoniRob dataset, the Rice Seeding dataset, and the WeedMap dataset. Additionally, we measure the inference time and Frame Per Second on the NVIDIA Jetson Xavier NX embedded system, the results are 18.14 msec and 55.1 FPS. Experimental results demonstrate that our network maintains better inference speed on resource-constrained embedded systems and has competitive segmentation performance.https://www.frontiersin.org/articles/10.3389/fpls.2023.1320448/fullconvolutional neural networkattention mechanismlightweight semantic segmentationcrop and weed segmentationprecision farming |
| spellingShingle | Yifan Wei Yuncong Feng Yuncong Feng Yuncong Feng Xiaotang Zhou Xiaotang Zhou Guishen Wang Guishen Wang Attention-aided lightweight networks friendly to smart weeding robot hardware resources for crops and weeds semantic segmentation Frontiers in Plant Science convolutional neural network attention mechanism lightweight semantic segmentation crop and weed segmentation precision farming |
| title | Attention-aided lightweight networks friendly to smart weeding robot hardware resources for crops and weeds semantic segmentation |
| title_full | Attention-aided lightweight networks friendly to smart weeding robot hardware resources for crops and weeds semantic segmentation |
| title_fullStr | Attention-aided lightweight networks friendly to smart weeding robot hardware resources for crops and weeds semantic segmentation |
| title_full_unstemmed | Attention-aided lightweight networks friendly to smart weeding robot hardware resources for crops and weeds semantic segmentation |
| title_short | Attention-aided lightweight networks friendly to smart weeding robot hardware resources for crops and weeds semantic segmentation |
| title_sort | attention aided lightweight networks friendly to smart weeding robot hardware resources for crops and weeds semantic segmentation |
| topic | convolutional neural network attention mechanism lightweight semantic segmentation crop and weed segmentation precision farming |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1320448/full |
| work_keys_str_mv | AT yifanwei attentionaidedlightweightnetworksfriendlytosmartweedingrobothardwareresourcesforcropsandweedssemanticsegmentation AT yuncongfeng attentionaidedlightweightnetworksfriendlytosmartweedingrobothardwareresourcesforcropsandweedssemanticsegmentation AT yuncongfeng attentionaidedlightweightnetworksfriendlytosmartweedingrobothardwareresourcesforcropsandweedssemanticsegmentation AT yuncongfeng attentionaidedlightweightnetworksfriendlytosmartweedingrobothardwareresourcesforcropsandweedssemanticsegmentation AT xiaotangzhou attentionaidedlightweightnetworksfriendlytosmartweedingrobothardwareresourcesforcropsandweedssemanticsegmentation AT xiaotangzhou attentionaidedlightweightnetworksfriendlytosmartweedingrobothardwareresourcesforcropsandweedssemanticsegmentation AT guishenwang attentionaidedlightweightnetworksfriendlytosmartweedingrobothardwareresourcesforcropsandweedssemanticsegmentation AT guishenwang attentionaidedlightweightnetworksfriendlytosmartweedingrobothardwareresourcesforcropsandweedssemanticsegmentation |