Accurate and real-time recognition of rice plants is the premise underlying the implementation of precise weed control. However, achieving desired results in paddy fields using the traditional visual method is difficult due to the occlusion of rice leaves and the interference of weeds. The objective of this study was to develop a novel rice plant recognition sensor based on a tactile method which acquires tactile information through physical touch. The tactile sensor would be mounted on the paddy field weeder to provide identification information for the actuator. First, a flexible gasbag filled with air was developed, where vibration features produced by tactile and sliding feedback were acquired when this apparatus touched rice plants or weeds, allowing the subtle vibration data with identification features to be reflected through the voltage value of an air-pressured sensor mounted inside the gasbag. Second, voltage data were preprocessed by three algorithms to optimize recognition features, including dimensional feature, dimensionless feature, and fractal dimension. The three types of features were used to train and test a neural network classifier. To maximize classification accuracy, an optimum set of features (b (variance), f (kurtosis), h (waveform factor), l (box dimension), and m (Hurst exponent)) were selected using a genetic algorithm. Finally, the feature-optimized classifier was trained, and the actual performances of the sensor at different contact positions were tested. Experimental results showed that the recognition rates of the end, middle, and root of the sensor were 90.67%, 98%, and 96% respectively. A tactile-based method with intelligence could produce high accuracy for rice plant recognition, as demonstrated in this study.

Accurate and automatic real-time recognition of shrimp with and without shells is the key to improve the efficiency of automatic peeling machines and reduce the labor cost. Existing methods cannot obtain excellent accuracy in the absence of target samples because there are too many species of shrimp to obtain a complete dataset. In this paper, we propose a tactile recognition method with universal applicability. First, we obtained tactile data, e.g., the texture and hardness of the surface of the shrimp, through a novel layout using the same type of sensors, and constructed fusion features based on the energy and nonstationary volatility (ENSV). Second, the ENSV features were input to an adaptive recognition boundary model (ARBM) for training to obtain the recognition boundary of shrimp with and without shells. Finally, the effectiveness of the proposed model was verified by comparison with other tactile models. The method was tested with different species of shrimp and the results were 88.2%, 87.0%, and 89.4%, respectively. The recognition accuracy of the overall, shrimp with shells and shrimp without shells verified the generalizability of the proposed method. This method can help to improve the efficiency of automatic peeling machines and reduce the labor cost.

Affected by moisture cohesion, wet rice seeds exhibit poor flowability and frequent arching blockage during silo discharging, which seriously restricts stable grain storage and conveying. To address this issue and reveal its intrinsic flow mechanism, this study establishes a discrete element method (DEM) model for wet rice seed-silo systems adopting the Hertz-Mindlin with Johnson-Kendall-Roberts (JKR) contact model, which incorporates surface energy to reflect moisture-induced cohesive effects. The model is verified via physical silo discharge tests, with consistent flow patterns, wall pressure error below 3.7% and discharge time error of 2.14%. EDEM parametric simulations are conducted to analyze velocity fluctuation at different silo heights. Coordination number and normalized contact force distribution are adopted to assess micro-contact force distribution in discharge areas, and a force chain extraction algorithm is used to explore variations in force chain length and orientation. Results demonstrate that during discharge, average particle velocity drops from silo bottom to top with growing fluctuation amplitude, presenting obvious stratified flow and intense upper-layer velocity pulsation. Weak contacts dominate wet rice seed groups and conform to exponential decay distribution. The force chain network undergoes three evolution phases: formation, force arch generation and collapse. Quantitative analysis reveals long force chain proportion falls steadily from 81.40% to 3.68% throughout discharge. Short force chains rise to 60.54% in the arch-forming stage and reach 96.32% after arch collapse. Horizontal force chains account for a maximum of 71.09% during arch formation, while vertical ones decline from 99.52% initially to 61.57% post collapse. This research offers mechanical references and quantitative parameters for the design and operation of silos for wet granular farm grains like rice seeds, and is particularly relevant to post-harvest engineering, grain storage safety, and agricultural machinery design.

To address the issues of a low single-seed qualification index and a high missed-seeding index in the process of leafy vegetable plug seedling sowing, this study proposes a lightweight seeding performance detection model named VS-YOLO based on YOLO11n. The model is then deployed on the edge device, the NVIDIA Jetson Xavier NX. A concise and intuitive graphical user interface (GUI) was developed and an automated detection system for vegetable seeding performance was constructed. Based on the empty cells identified by the system, a real-time data transmission mechanism between the Jetson device and a PLC-based control unit is established, enabling the intelligent reseeding device to perform precise reseeding at the designated cell location, achieving row-wise and cell-specific intelligent planting. VS-YOLO incorporates several innovative improvements, including the introduction of a Context Anchor Attention (CAA) module to form the C2PSA_CAA module, the adoption of the Wise Intersection over Union version 3 (WIoU v3) loss function, and the addition of an extra-small object detection head. These enhancements significantly improve the classification and recognition capability for small-sized vegetable seeds while notably reducing the number of model parameters. Experimental results show that VS-YOLO achieves a mAP@0.5 of 96.5% and an F1 Score of 93.45% in detecting the seeding performance of three types of vegetable seeds, outperforming YOLO11n’s 91.5% and 85.19% by 5.0% and 8.26%. The parameter count of VS-YOLO is only 1.61 M, which is 37.6% lower than YOLO11n’s 2.58 M, making it lightweight. Operating at a productivity rate of 120 trays per hour, the system achieved an accuracy of 99.03%, 89.83%, and 92.26% for single-seed prediction, multiple-seeding prediction, and missed-seeding prediction. The single-seed qualification index and missed-seeding index were 93.43% and 4.68%. After reseeding, these indices improved to 97.61% and 0.32%, representing an increase of 4.18% in the single-seed qualification index and a decrease of 4.36% in the missed-seeding index. The significant enhancement offers new ideas and technical approaches for the advancement of seeding performance detection and reseeding systems for vegetable plug seedling production.

To address inaccurate weed segmentation under crop overlap, occlusion, and complex field backgrounds, this study developed a combined method integrating DViT-YOLOv8-seg with confidence-guided SLIC voting. The dataset contained 1872 field images (800 × 600 pixels) of Guangzhou soft-stem lettuce and four common weed species: Eleusine indica, Digitaria sanguinalis, Portulaca oleracea, and Amaranthus blitum. All weed species were merged into one weed class, while lettuce, soil, and other field regions were treated as non-weed. Real-ESRGAN and data augmentation enhanced the training samples; Dual-ViT strengthened global–local feature interaction; GSConv reduced redundant computation; BiFPN improved multi-scale fusion; and SLIC refined ambiguous boundaries. After super-resolution preprocessing and three-fold expansion, baseline mPA increased by 10.9 percentage points. The improved network achieved 88.3% mPA at 7.9 GFLOPs, corresponding to +3.6 percentage points and -1.0 GFLOPs relative to the baseline. SLIC voting increased FWIoU to 95.6%, 4.1 percentage points above the network without SLIC. Compared with YOLOv5-seg and Fast-SCNN, mPA improved by 2.0 and 6.5 percentage points, respectively; GFLOPs were 87.7% and 95.5% lower than those of YOLOv5-seg and DeepLabv3+, respectively. The method therefore provides a favorable trade-off between segmentation accuracy and theoretical network computation for complex lettuce field imagery.

Achieving high sowing precision for small and irregularly shaped seeds remains a significant challenge in air-suction plug-tray seeding systems due to frequent seed slipping and detachment during the seed-picking and conveying processes. To address this issue, a novel seed cap incorporating a seed-carrying plate structure was developed. A DEM-CFD gas–solid coupling model of the seed-metering device was established for metering chili pepper seeds. With suction (negative) pressure, seed-carrying plate height, and suction-hole diameter as affecting factors, simulations with a quadratic orthogonal rotational combination were conducted. Response surface methodology (RSM) was employed for multi-objective parameter optimization, followed by comparative bench test verification. The results indicate that the interaction between suction pressure and suction-hole diameter had a highly significant effect on the multiple-filling rate. The optimal combination of working parameters was determined as a suction pressure of 25.5 kPa, a seed-carrying plate height of 0.2 mm, and a suction-hole diameter of 0.4 mm. Experiments with the seed-metering machine demonstrated that under these optimal parameters, the single-seed qualification rate reached 95.09%, the miss-seeding rate was 3.06%, and the re-seeding rate was 1.85%. Compared to the conventional seed cap without a seed-carrying plate, the single-seed qualification rate increased by 4.49%, while the miss-seeding and re-seeding rates decreased by 2.06% and 2.43%, respectively. The seed-carrying plate structure effectively reduced the dependence of the seed-metering device on high suction pressure, providing a technical reference for the research and development of precision plug-tray seeding of irregular seeds.