Accurate estimates of cotton seedling abundance and spatial distribution support emergence assessment and field management. However, seedlings occupy few pixels in unmanned aerial vehicle (UAV) imagery, occur at high densities, and frequently overlap. This study proposes a High-Resolution Center-Guided Feature Fusion model (HCF-YOLO) that combines a P2 detection layer, Lightweight Multi-Scale Feature Fusion (LMSFF), and training-only Gaussian Center Guidance (GCG). The dataset contained 1040 images and 101,824 annotated cotton seedlings and was divided into 832 training, 104 validation, and 104 test images. On the main test split, HCF-YOLO11n achieved an mAP50 of 0.9354 and an mAP50-95 of 0.4431, improvements of 5.10 and 3.74 percentage points over YOLO11n, while reducing the parameter count and FLOPs by 14.18% and 14.63%. The performance ranking was consistent across three random seeds and was retained in the external-source evaluation. Under the pruning protocol, the 5%-pruned HCF-YOLO11n achieved an mAP50-95 of 0.4578 on the same 104-image test split while reducing parameters and FLOPs by 11.19% and 6.87%, respectively. TensorRT FP16 reduced network inference latency to 1.453 ms, and Raspberry Pi 5 deployment reached 6.67 FPS. Overall, HCF-YOLO balances accuracy, model size, and edge efficiency for UAV-assisted cotton seedling recognition and image-plane localization, although onboard validation remains necessary.

Canopy 3D architecture is a critical determinant of light interception, photosynthetic efficiency, and final yield in cotton, yet its rapid and accurate characterisation remains challenging in field conditions. To achieve efficient, non-destructive, and quantitative monitoring of the canopy structure of field-grown cotton, this study proposes a 3D structure-based technology stack for high-efficiency, low-cost, and high-precision phenotyping extraction. This stack directly addresses the technical bottlenecks of traditional 3D data acquisition, namely high cost, long processing time, and low operational efficiency, which have hindered large-scale application. We developed a pipeline that integrates a fast reconstruction algorithm with a scale-recovery mechanism using ground control points (GCPs), enabling the generation of true-scale 3D point clouds from UAV aerial images in a cost- and time-effective manner. Using only 141 UAV images and with a reconstruction time of approximately 20 min, we efficiently reconstructed high-quality, scale-accurate point clouds of two 5.5 m × 5.5 m cotton plots, significantly outperforming SfM-MVS and Instant-NGP in terms of both reconstruction efficiency and point cloud completeness. This method, whose current validation is confined to a single season, one growth stage, and two experimental plots, not only achieves a breakthrough by using fewer input images with high efficiency, but also ensures point cloud accuracy and completeness, showing strong potential for rapid field monitoring and real-time management. Based on the high-quality reconstructed point clouds, we further quantitatively evaluated canopy characteristics at harvest, analyzing the coefficient of variation of canopy height, porosity distribution, and canopy volume fraction. The core shortcomings and optimization strategies for the existing canopy structure were identified, providing scientific data support and practical technical references for precision cultivation management and mechanization-compatible planting in cotton.

Accurate point-cloud segmentation of cotton organs is essential for precise phenotypic characterization. However, reliable instance segmentation of cotton bolls in field-derived point clouds remains challenging because foliage occlusion, contact between adjacent bolls and incomplete reconstruction obscure instance boundaries. Here we present RQ-PointNeXt, an end-to-end framework that directly maps input point clouds to boll instance masks within a unified trainable network. Built on PointNeXt, it incorporates relative-elevation geometric channel attention in the shallow encoder to fuse global channel context with elevation and surface-normal cues. Its Query–mask branch integrates semantic guidance, center-seeded queries and a center-aware mask prior to suppress background responses, localize instances and constrain mask extent. Hungarian matching and multitask optimization establish one-to-one query–instance assignments, whereas query-based decoding produces instance masks without external geometric clustering. We evaluated the framework on 226 field-grown cotton plants containing 720 annotated boll instances reconstructed from UAV multi-view imagery using neural radiance fields. On the held-out test set, overall accuracy, mean class accuracy and mean intersection over union reached 0.8942, 0.8980 and 0.8076, respectively. AP25, AP50 and AP75 were 0.7359, 0.5585 and 0.2777, yielding an mAP25/50/75 of 0.5240. The framework provides instance-level outputs for boll counting and spatial analysis in high-throughput field phenotyping.