EUVIMEDEUVIMED entdecken
Crossref

CRS-YOLO: EFFICIENT INSTANCE SEGMENTATION FOR CROP ROW DETECTION AND NAVIGATION IN TOBACCO FIELDS

Feng LIU, Bingjie CHEN, Yong PANG, Yue LUO, Baoshan WANG, Chenhui ZHU, Wanzhang WANG

INMATEH - Agricultural Engineering · 30.04.2026 · 558

DOI: 10.35633/inmateh-78-45 ↗

Kurz gefasst

Fachartikel in der Zeitschrift INMATEH - Agricultural Engineering, online erschienen am 30.04.2026. Verfasst von Feng LIU und 6 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This research aimed to develop a robust crop row detection framework for tobacco fields, where existing methods have not addressed the unique challenges of stratified harvesting, which progressively alters plant morphology from dense lower canopy structures to sparse upper leaf arrangements across multiple collection cycles. CropRowSeg-YOLO (CRS-YOLO), an instance segmentation framework built on YOLOv11, was developed and integrates three core innovations: a Spatial Enhanced Calibration Block (SECB) utilizing depth-wise separable convolutions for spatial feature enhancement; a Hierarchical Adaptive Segmentation Head (HASH) employing asymmetric kernels for long-range dependency capture; and an Enhanced Post-processing Algorithm (EPA) for mask-to-trajectory conversion. Experimental validation in tobacco fields demonstrated 98.4% AP@50 for instance segmentation, with 96.6% precision and 94.2% recall. The model requires 5.1 GFLOPs and 2.7 M parameters, processing individual frames in 2.8 ms, with the complete pipeline executing in 16.99 ms at a resolution of 1920 × 1080.

Zitieren

APA

LIU, F., CHEN, B., PANG, Y., LUO, Y., WANG, B., ZHU, C., & WANG, W. (2026). CRS-YOLO: EFFICIENT INSTANCE SEGMENTATION FOR CROP ROW DETECTION AND NAVIGATION IN TOBACCO FIELDS. INMATEH - Agricultural Engineering, 558. https://doi.org/10.35633/inmateh-78-45

Vancouver

LIU F, CHEN B, PANG Y, LUO Y, WANG B, ZHU C, et al. CRS-YOLO: EFFICIENT INSTANCE SEGMENTATION FOR CROP ROW DETECTION AND NAVIGATION IN TOBACCO FIELDS. INMATEH - Agricultural Engineering. 2026:558. doi:10.35633/inmateh-78-45

BibTeX
@article{LIU2026,
  author = {LIU, Feng and CHEN, Bingjie and PANG, Yong and LUO, Yue and WANG, Baoshan and ZHU, Chenhui and WANG, Wanzhang},
  title = {CRS-YOLO: EFFICIENT INSTANCE SEGMENTATION FOR CROP ROW DETECTION AND NAVIGATION IN TOBACCO FIELDS},
  journal = {INMATEH - Agricultural Engineering},
  year = {2026},
  pages = {558},
  doi = {10.35633/inmateh-78-45}
}
Kostenlos starten →