August 22, 2025Plant MethodsOpen Access

Lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environments

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Enhanced YOLOv9-LDS framework improves contour extraction accuracy in complex wheat field environments, indicating better yield estimates.

The improved model achieved an 83.9% contour integrity recognition rate, enhancing segmentation accuracy in wheat fields.
With multi-scale feature synergy, the approach overcomes traditional model limitations, improving detection of overlapping spikes.
Ablation studies show the LDSNet-ELA integration reduces false positives by 27.6%, improving overall model reliability in field conditions.
This framework advances intelligent spikelet counting systems for wheat, demonstrating significant implications for crop phenomics.

Xu et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

August 22, 2025Plant MethodsOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Enhanced YOLOv9-LDS framework improves contour extraction accuracy in complex wheat field environments, indicating better yield estimates.

The improved model achieved an 83.9% contour integrity recognition rate, enhancing segmentation accuracy in wheat fields.
With multi-scale feature synergy, the approach overcomes traditional model limitations, improving detection of overlapping spikes.
Ablation studies show the LDSNet-ELA integration reduces false positives by 27.6%, improving overall model reliability in field conditions.
This framework advances intelligent spikelet counting systems for wheat, demonstrating significant implications for crop phenomics.

Xu et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark