Lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environments
Abstract Background Spikelet number, a core phenotypic parameter for wheat yield composition, requires precise estimation through accurate spike contour extraction and differentiation between grain surfaces and spikelet surfaces. However, technical challenges persist in precise spike segmentation un...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | Plant Methods |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13007-025-01433-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849226222889861120 |
|---|---|
| author | Xin Xu Haiyang Zhang Jiangchuan Lu Ziyi Guo Juanjuan Zhang Jibo Yue Hongbo Qiao Xinming Ma |
| author_facet | Xin Xu Haiyang Zhang Jiangchuan Lu Ziyi Guo Juanjuan Zhang Jibo Yue Hongbo Qiao Xinming Ma |
| author_sort | Xin Xu |
| collection | DOAJ |
| description | Abstract Background Spikelet number, a core phenotypic parameter for wheat yield composition, requires precise estimation through accurate spike contour extraction and differentiation between grain surfaces and spikelet surfaces. However, technical challenges persist in precise spike segmentation under complex field backgrounds and morphological differentiation between grain/spikelet surfaces. Method Building on two-year multi-angle wheat spike imagery, we propose an enhanced YOLOv9-LDS multi-scale object detection framework. The algorithm innovatively constructs a lightweight depthwise separable network (LDSNet) as backbone, balancing computational efficiency and accuracy through channel re-parameterization strategy; incorporates an Efficient Local Attention (ELA) module to build feature enhancement networks, and employs dual-path feature fusion mechanisms to strengthen edge texture responses, significantly improving discrimination of overlapping spikes and complex backgrounds. Further optimizes the loss function system by replacing traditional IoU with Scylla Intersection over Union (SIoU) metric, enhancing bounding box regression through dynamic focus factors, and adding high-resolution small-object detection layers to mitigate dense spikelet feature loss. Results Independent test set validation shows the improved model achieves 83.9% contour integrity recognition rate and 92.4% mAP@0.5, exceeding baseline by 3.2 and 5.3% points respectively. Ablation studies confirm LDSNet-ELA integration reduces false positives by 27.6%, while the enhanced loss function system improves small-object recall by 19.4%. Conclusions The proposed framework demonstrates superior performance in complex field scenarios with dense targets and dynamic illumination. The multi-scale feature synergy enhancement mechanism overcomes traditional models’ limitations in detecting overlapping spikes. This method not only enables precise spike phenotyping but also provides robust algorithmic support for intelligent field spikelet counting systems, advancing translational applications in crop phenomics. |
| format | Article |
| id | doaj-art-8cd942b7d64e4f0bb0915a058c56cfc7 |
| institution | Kabale University |
| issn | 1746-4811 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMC |
| record_format | Article |
| series | Plant Methods |
| spelling | doaj-art-8cd942b7d64e4f0bb0915a058c56cfc72025-08-24T11:31:52ZengBMCPlant Methods1746-48112025-08-0121111810.1186/s13007-025-01433-1Lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environmentsXin Xu0Haiyang Zhang1Jiangchuan Lu2Ziyi Guo3Juanjuan Zhang4Jibo Yue5Hongbo Qiao6Xinming Ma7College of Information and Management Science, Henan Agricultural UniversityCollege of Information and Management Science, Henan Agricultural UniversityCollege of Information and Management Science, Henan Agricultural UniversityCollege of Information and Management Science, Henan Agricultural UniversityCollege of Information and Management Science, Henan Agricultural UniversityCollege of Information and Management Science, Henan Agricultural UniversityCollege of Information and Management Science, Henan Agricultural UniversityCollege of Information and Management Science, Henan Agricultural UniversityAbstract Background Spikelet number, a core phenotypic parameter for wheat yield composition, requires precise estimation through accurate spike contour extraction and differentiation between grain surfaces and spikelet surfaces. However, technical challenges persist in precise spike segmentation under complex field backgrounds and morphological differentiation between grain/spikelet surfaces. Method Building on two-year multi-angle wheat spike imagery, we propose an enhanced YOLOv9-LDS multi-scale object detection framework. The algorithm innovatively constructs a lightweight depthwise separable network (LDSNet) as backbone, balancing computational efficiency and accuracy through channel re-parameterization strategy; incorporates an Efficient Local Attention (ELA) module to build feature enhancement networks, and employs dual-path feature fusion mechanisms to strengthen edge texture responses, significantly improving discrimination of overlapping spikes and complex backgrounds. Further optimizes the loss function system by replacing traditional IoU with Scylla Intersection over Union (SIoU) metric, enhancing bounding box regression through dynamic focus factors, and adding high-resolution small-object detection layers to mitigate dense spikelet feature loss. Results Independent test set validation shows the improved model achieves 83.9% contour integrity recognition rate and 92.4% mAP@0.5, exceeding baseline by 3.2 and 5.3% points respectively. Ablation studies confirm LDSNet-ELA integration reduces false positives by 27.6%, while the enhanced loss function system improves small-object recall by 19.4%. Conclusions The proposed framework demonstrates superior performance in complex field scenarios with dense targets and dynamic illumination. The multi-scale feature synergy enhancement mechanism overcomes traditional models’ limitations in detecting overlapping spikes. This method not only enables precise spike phenotyping but also provides robust algorithmic support for intelligent field spikelet counting systems, advancing translational applications in crop phenomics.https://doi.org/10.1186/s13007-025-01433-1Wheat spikesLightweight deep networkLDSNet- ELAYOLOv9Contour extraction |
| spellingShingle | Xin Xu Haiyang Zhang Jiangchuan Lu Ziyi Guo Juanjuan Zhang Jibo Yue Hongbo Qiao Xinming Ma Lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environments Plant Methods Wheat spikes Lightweight deep network LDSNet- ELA YOLOv9 Contour extraction |
| title | Lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environments |
| title_full | Lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environments |
| title_fullStr | Lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environments |
| title_full_unstemmed | Lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environments |
| title_short | Lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environments |
| title_sort | lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environments |
| topic | Wheat spikes Lightweight deep network LDSNet- ELA YOLOv9 Contour extraction |
| url | https://doi.org/10.1186/s13007-025-01433-1 |
| work_keys_str_mv | AT xinxu lightweightdeepneuralnetworkforcontourdetectionandextractionofwheatspikesincomplexfieldenvironments AT haiyangzhang lightweightdeepneuralnetworkforcontourdetectionandextractionofwheatspikesincomplexfieldenvironments AT jiangchuanlu lightweightdeepneuralnetworkforcontourdetectionandextractionofwheatspikesincomplexfieldenvironments AT ziyiguo lightweightdeepneuralnetworkforcontourdetectionandextractionofwheatspikesincomplexfieldenvironments AT juanjuanzhang lightweightdeepneuralnetworkforcontourdetectionandextractionofwheatspikesincomplexfieldenvironments AT jiboyue lightweightdeepneuralnetworkforcontourdetectionandextractionofwheatspikesincomplexfieldenvironments AT hongboqiao lightweightdeepneuralnetworkforcontourdetectionandextractionofwheatspikesincomplexfieldenvironments AT xinmingma lightweightdeepneuralnetworkforcontourdetectionandextractionofwheatspikesincomplexfieldenvironments |