MS-R outperforms RGB: Lightweight CYOLO-BiCNet enables efficient detection and storage optimization of cotton flowers

Precision agriculture requires accurate yet efficient crop organ detection methods that can be readily deployed under field conditions with limited storage and computing resources. This study therefore examined whether the independently acquired multispectral red single-band image (MS-R) can provide a more effective alternative to conventional RGB images for cotton flower detection.

We compared its performance with representative YOLO-series detectors, two mainstream non-YOLO detectors, and progressive ablation variants using MS-R, RGB, and RGB-R datasets. The evaluation metrics included Precision, Recall, mAP, storage efficiency, and computational cost. Additionally, we investigated the effect of MS-R image re-encoding with image-quality parameters down to N = 25 on detection performance and storage efficiency.

Across the nine compared detector variants, paired significance tests confirmed that MS-R achieved significantly higher Precision, Recall, and mAP than RGB and RGB-R. The exact P values ranged from 0.008 to 0.012. Specifically, the MS-R data achieved a Precision of 0.911, compared with 0.862 for RGB, and also showed higher Recall (0.917 vs. 0.830) and mAP (0.953 vs. 0.881). Moreover, the average size of MS-R images is 55% smaller than that of RGB images, significantly reducing storage requirements for large-scale applications. The impact of moderate compression on MS-R data was also investigated. When the image-quality parameter was reduced to N = 25, the storage space decreased by approximately 83% relative to the original MS-R dataset, with only a slight decrease in Precision from 0.911 to 0.906.

The study confirms that MS-R data paired with CYOLO-BiCNet offers a scalable solution for field-oriented cotton flower detection, balancing high accuracy with reduced storage and computational demands. These findings also indicate that the practical single-band alternative identified in this study is the independently acquired multispectral R-band, rather than the RGB-derived red channel in general. These findings advance precision agriculture by optimizing data selection and model design for crop organ recognition.