What question did this study set out to answer?

Develop a deep learning framework using multiview image fusion to count soybean pods and rank genotype seed yield from in-field robotic video data.

January 1, 2021Plant PhenomicsOpen Access

Deep Multiview Image Fusion for Soybean Yield Estimation in Breeding Applications

View Full Paper

Ask AI

Bookmark

Develop a deep learning framework using multiview image fusion to count soybean pods and rank genotype seed yield from in-field robotic video data.
Designed a multiview deep learning architecture that fuses plant video footage captured from multiple angles by an in-field ground robot.
Evaluated model efficacy in both controlled in-field environments and active breeding test plots against manual pod counting and harvest yield benchmarks.
Multiview image fusion effectively predicted seed yield ranks across soybean genotypes relative to ground-truth manual counts.
The automated framework achieved these breeding evaluations with substantial reductions in human labor and field assessment time.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Experimental study reveals deep multiview image fusion reliably predicts seed yield in soybeans, suggesting automated robot imaging can streamline crop breeding decisions.

Cite This Study

Riera et al. (2021) studied this question.

synapsesocial.com/papers/6a15d1a479ff98d0de4f29a5 https://doi.org/10.34133/2021/9846470

View Full Paper

Ask AI

Bookmark

Implication

Experimental study reveals deep multiview image fusion reliably predicts seed yield in soybeans, suggesting automated robot imaging can streamline crop breeding decisions.

Deep Multiview Image Fusion for Soybean Yield Estimation in Breeding Applications

Key Points

Discussion

Implication

Cite This Study

Deep Multiview Image Fusion for Soybean Yield Estimation in Breeding Applications

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider