Accurate and robust recognition of daylily flower buds at the pre-bloom stage is essential for timely harvesting and quality preservation, yet remains highly challenging under natural field conditions due to the buds’ slender morphology, diverse orientations, dense distribution, and frequent occlusion by foliage. Existing horizontal-box object detectors struggle to capture the orientation and geometric structure of daylily buds, leading to inaccurate localization and unreliable guidance for automated harvesting. To address these challenges, we propose DDM-YOLO, a lightweight orientation-aware detection model tailored for daylily production environments. The model integrates three key components: (i) a Multi-scale Adaptive Feature Pyramid Network (MAFPN) that enhances the extraction and fusion of multi-dimensional features for densely distributed and occluded slender buds; (ii) a Lightweight Adaptive Direction-aware Head (LADH) that dynamically optimizes angle regression for rotated bounding boxes, improving orientation stability and reducing localization bias; and (iii) an Adaptive Down-sampling module (Adown) that preserves structurally critical spatial cues while reducing model complexity. Experiments conducted on a custom daylily field dataset demonstrate that DDM-YOLO achieves 96.8% precision and 98.1% mAP50, outperforming the baseline YOLOv11n-OBB by 1.3 percentage points in mAP while reducing model parameters by 17.0% to 2.2M. Deployment verification using a PySide5-based visualization prototype demonstrated a total system-level latency of less than 0.2 s, a duration encompassing the cumulative overhead of image input and output, pre-processing, post-processing including non-maximum suppression, and interface rendering. Furthermore, physical deployment on an NVIDIA Jetson AGX Orin embedded platform utilizing TensorRT optimization achieved an impressive inference speed of 114.5 FPS, corresponding to approximately 8.7 ms per frame. This performance confirms that the model meets the stringent real-time requirements for edge computing in mobile agricultural robotics. The model efficiently and accurately performs oriented detection and harvesting pose estimation for daylily buds, providing critical technical support for the visual perception system of harvesting robots.

With the continuous growth of global population and increasing pressure on food security, the transformation toward precise and intelligent agricultural production has become an inevitable trend. In this context, accurate identification of field weeds is crucial for improving crop yields and reducing agricultural inputs. However, agricultural Internet of Things (IoT) edge devices are generally subject to strict constraints in terms of power consumption, storage, and real-time performance. Existing lightweight convolutional neural networks often struggle to simultaneously achieve high accuracy and low resource consumption for fine-grained weed identification tasks. To address this challenge, this paper proposes a hardware aware lightweight convolutional neural network named Weed-Aware Ghost Enhanced Network (WAGENet) for microcontroller deployment. The network synergistically integrates Ghost low-cost feature generation, Mobile Inverted Bottleneck Convolution (MBConv) for deep semantic extraction, Squeeze and Excitation (SE) and Coordinate Attention (CA) dual attention mechanisms for channel space joint calibration, and Atrous Spatial Pyramid Pooling (ASPP) for multi-scale context fusion. It constructs a progressive feature abstraction system from shallow textures to high-level semantics. On the public DeepWeeds dataset, WAGENet achieves 95.71% classification accuracy and 93.80% F1 score with only 0.163 M parameters and 2.43 × 10⁸ multiply accumulate operations (MACC), attaining a parameter efficiency of 587.19%/M and significantly outperforming existing mainstream lightweight models. The model has been successfully deployed on the STM32H7B3I microcontroller development board, achieving a single inference latency of 94.63 ms, an internal Flash footprint of only 686.95 KiB, and a single inference energy consumption of 41.45 mJ. Experimental results demonstrate that WAGENet achieves a trade off among accuracy, latency, and energy consumption under strict resource constraints, providing a reproducible microcontroller deployment paradigm for battery powered field robots, drones, and other agricultural IoT edge devices.

To address the challenges of difficult feature extraction and insufficient recognition accuracy caused by the small size of chili flowers, occlusion by branches and leaves, and illumination variations in complex field environments, a dual-backbone-based chili flower pose estimation algorithm, termed DCFP-YOLO, is proposed. Built upon the YOLO11n framework, the proposed method performs classification and recognition of five typical upward-oriented chili flower poses. To alleviate the loss of local detail features of small chili flowers under complex backgrounds, a dual-backbone feature extraction network composed of StarNet and ShuffleNetV2 is constructed. Specifically, the StarNet backbone enhances the extraction of fine-grained local features from key floral regions, while the ShuffleNetV2 backbone improves the perception of global spatial structural information. The complementary fusion of dual-backbone features strengthens the representation capability of chili flower pose features in complex environments. To mitigate the attenuation of shallow detail information during multi-scale feature transmission, a Bidirectional Multi-branch Auxiliary Feature Pyramid Network (BiMAFPN) is designed to enhance feature propagation through cross-scale feature interaction, thereby improving pose recognition performance under occlusion and overlapping conditions. Furthermore, a Programmable Gradient Information (PGI)-assisted training mechanism is introduced to optimize gradient propagation paths and alleviate information bottlenecks in deep networks, thereby enhancing the robustness of multi-pose feature extraction under occlusion, blur, and complex illumination conditions. Experimental results demonstrate that DCFP-YOLO achieves recall, mAP50, and mAP50 values of 87.4%, 92.0%, and 66.9%, respectively, representing improvements of 1.7, 1.3, and 3.5 percentage points over the baseline model. Overall performance surpasses that of current mainstream object detection algorithms. After deployment on the NVIDIA Jetson AGX Orin platform, the model achieves an inference speed of 20.9 frames/s, which can basically satisfy the real-time perception requirements of chili flower pose recognition in complex agricultural environments. The proposed method provides an effective visual perception framework for chili flower pose recognition in complex agricultural environments. Rather than constituting a complete robotic pollination solution, the developed model serves as a potential perception component for future intelligent pollination robotic systems, providing reliable flower pose information for subsequent research on target localization, end-effector alignment, and robotic pollination in unstructured greenhouse environments.