Zhenghao Wu

The Hotan rose, a high-value specialty crop cultivated in Xinjiang, exhibits pronouncedly non-uniform flowering phenology, which has historically necessitated labor-intensive manual harvesting. To date, however, no integrated framework has been reported that concurrently addresses lightweight visual perception, precise picking-point localization, and three-dimensional path planning for this specific crop. In this study, we develop L-SOP, an end-to-end continuous picking methodology tailored to the unique requirements of Hotan rose harvesting. At the perception stage, we introduce YOLOv11n-LPD-Seg, a lightweight segmentation model that incorporates a joint compression strategy combining global pruning with channel-wise distillation (CWD). This design improves the mAP@0.5 values for flowers and buds by 0.1 and 0.7 percentage points, respectively. It also reduces the model size from 6.1 MB to 2.4 MB, representing a 60.7% reduction, and decreases the computational cost from 10.2 GFLOPs to 6.8 GFLOPs, representing a 33.3% reduction. For picking point localization, we develop the MGRO-Loc algorithm, which integrates multiple geometric constraints to achieve accurate spatial positioning. The algorithm achieves mean absolute errors of 2.33 mm under indoor conditions and 2.84 mm under outdoor conditions. For path planning, we propose the OG-LKH algorithm, which replaces the conventional orthogonal polyline distance metric with an oblique gate-shaped distance measure and incorporates a multi-start strategy and a gate-aware heuristic search. Compared with the standard LKH algorithm, OG-LKH reduces the average path length by 23.5% while maintaining a computation time of 0.0117 s. Even in high-density scenarios involving 36 waypoints, its computation time is only 0.0387 s on edge-computing devices. These three modules work synergistically to form a complete solution for selective continuous rose picking. The proposed framework can be deployed on edge devices, providing a viable technological pathway toward efficient autonomous harvesting of Hotan rose flower and bud.

Selective harvesting of Hotan roses requires distinguishing between buds and blooms for different industrial uses. However, balancing detection accuracy and computational efficiency for edge deployment remains a challenge. This study proposes an integrated framework combining a lightweight detection model, Rose_YOLO, with an adaptive path-planning algorithm, the ROSE algorithm, to address these issues. The Rose_YOLO model optimizes the YOLOv8n architecture by incorporating the C2f-Faster-CGLU module and a Rose_Head detection head to enhance feature extraction while reducing redundancy. The ROSE algorithm integrates an improved genetic algorithm (GA) with a reciprocating search mechanism to dynamically optimize picking sequences based on scene complexity. Experimental results demonstrate that Rose_YOLO achieves a precision of 90.4% and a mAP@0.5 of 96.6% for blooms and a precision of 88.4% with a mAP@0.5 of 91.7% for buds. Compared to the baseline YOLOv8n, the model reduces parameters by 47.46% to 1.579 million, compresses the size to 3.19 MB, and lowers computational complexity to 4.6 GFLOPs. For path planning, the ROSE algorithm generates optimal paths with an average length of 2796.94 pixels, which is 73.1% shorter than the reciprocating algorithm and 51.6% shorter than the standard GA. Furthermore, it achieves an average runtime of only 7.33 ms, significantly outperforming traditional methods with respect to computational speed. In conclusion, the proposed framework achieves a superior balance between lightweight design and detection performance. The successful deployment on edge devices validates its effectiveness in providing real-time visual guidance and efficient path planning, offering a robust technical solution for the automated selective harvesting of roses in complex field environments.

A key challenge in automated marigold harvesting lies in the accurate identification of picking points under complex environmental conditions, such as dense shading and intense illumination. To tackle this problem, this research proposes a lightweight instance segmentation model combined with a harvest position estimation method. Based on the YOLOv11n-seg segmentation framework, we develop a lightweight PDS-YOLO model through two key improvements: (1) structural pruning of the base model to reduce its parameter count, (2) incorporation of a Channel-wise Distillation (CWD)-based feature distillation method to compensate for the accuracy loss caused by pruning. The resulting lightweight segmentation model achieves a size of only 1.3 MB (22.8% of the base model) and a computational cost of 5 GFLOPs (49.02% of the base model). At the same time, it maintains high segmentation performance, with a precision of 93.6% and a mean average precision (mAP) of 96.7% for marigold segmentation. Furthermore, the proposed model demonstrates enhanced robustness under challenging scenarios including strong lighting, cloudy weather, and occlusion, improving the recall rate by 1.1% over the base model. Based on the segmentation results, a method for estimating marigold harvest positions using 3D point clouds is proposed. Fitting and deflection angle experiments confirm that the fitting errors are constrained within 3–12 mm, which lies within an acceptable range for automated harvesting. These results validate the capability of the proposed approach to accurately locate marigold harvest positions under top-down viewing conditions. The lightweight segmentation network and harvest position estimation method presented in this work offer effective technical support for selective harvesting of marigolds.

This study addresses the core challenges of precise marigold corollas recognition and efficient continuous path planning under complex natural conditions (strong illumination, occlusion, adhesion) by proposing an integrated lightweight visual recognition and real-time path planning framework. We introduce MPD-YOLO, an optimized model based on YOLOv11n, incorporating (1) a Multi-scale Information Enhancement Module (MSEE) to boost feature extraction; (2) structured pruning for significant model compression (final size: 2.1 MB, 39.6% of original); and (3) knowledge distillation to recover accuracy loss post-pruning. The resulting model achieves high precision (P: 89.8%, mAP@0.5: 95.1%) with reduced computational load (3.2 GFLOPs) while demonstrating enhanced robustness in challenging scenarios—recall significantly increased by 6.8% versus YOLOv11n. Leveraging these recognition outputs, an adaptive ant colony algorithm featuring dynamic parameter adjustment and an improved pheromone strategy reduces average path planning time to 2.2 s—a 68.6% speedup over benchmark methods. This integrated approach significantly enhances perception accuracy and operational efficiency for automated marigold harvesting in unstructured environments, providing robust technical support for continuous automated operations.

Accurate identification of picking points remains a critical challenge for automated marigold harvesting, primarily due to complex backgrounds and significant pose variations of the flowers. To overcome this challenge, this study proposes SCS-YOLO-Seg, a novel method based on a lightweight segmentation model. The approach enhances the baseline YOLOv8n-seg architecture by replacing its backbone with StarNet and introducing C2f-Star, a novel lightweight feature extraction module. These modifications achieve substantial model compression, significantly reducing the model size, parameter count, and computational complexity (GFLOPs). Segmentation efficiency is further optimized through a dual-path collaborative architecture (Seg-Marigold head). Following mask extraction, picking points are determined by intersecting the optimized elliptical mask fitting results with the stem skeleton. Experimental results demonstrate that SCS-YOLO-Seg effectively balances model compression with segmentation performance. Compared to YOLOv8n-seg, it maintains high accuracy while significantly reducing resource requirements, achieving a picking point identification accuracy of 93.36% with an average inference time of 28.66 ms per image. This work provides a robust and efficient solution for vision systems in automated marigold harvesting.

To address the challenge of precise picking point localization in morphologically diverse safflower plants, this study proposes PointSafNet—a novel three-stage 3D point cloud analysis framework with distinct architectural and methodological innovations. In Stage I, we introduce a multi-view reconstruction pipeline integrating Structure from Motion (SfM) and Multi-View Stereo (MVS) to generate high-fidelity 3D plant point clouds. Stage II develops a dual-branch architecture employing Star modules for multi-scale hierarchical geometric feature extraction at the organ level (filaments and frui balls), complemented by a Context-Anchored Attention (CAA) mechanism to capture long-range contextual information. This synergistic feature learning approach addresses morphological variations, achieving 86.83% segmentation accuracy (surpassing PointNet++ by 7.37%) and outperforming conventional point cloud models. Stage III proposes an optimized geometric analysis pipeline combining dual-centroid spatial vectorization with Oriented Bounding Box (OBB)-based proximity analysis, resolving picking coordinate localization across diverse plants with 90% positioning accuracy and 68.82% mean IoU (13.71% improvement). The experiments demonstrate that PointSafNet systematically integrates 3D reconstruction, hierarchical feature learning, and geometric reasoning to provide visual guidance for robotic harvesting systems in complex plant canopies. The framework’s dual emphasis on architectural innovation and geometric modeling offers a generalizable solution for precision agriculture tasks involving morphologically diverse safflowers.