Mechanized harvesting is the key technology to solving the high cost and low efficiency of manual harvesting, and the key to realizing mechanized harvesting lies in the accurate and fast identification and localization of targets. In this paper, a lightweight YOLOv5s model is improved for efficiently identifying grape fruits and stems. On the one hand, it improves the CSP module in YOLOv5s using the Ghost module, reducing model parameters through ghost feature maps and cost-effective linear operations. On the other hand, it replaces traditional convolutions with deep convolutions to further reduce the model’s computational load. The model is trained on datasets under different environments (normal light, low light, strong light, noise) to enhance the model’s generalization and robustness. The model is applied to the recognition of grape fruits and stems, and the experimental results show that the overall accuracy, recall rate, mAP, and F1 score of the model are 96.8%, 97.7%, 98.6%, and 97.2% respectively. The average detection time on a GPU is 4.5 ms, with a frame rate of 221 FPS, and the weight size generated during training is 5.8 MB. Compared to the original YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x models under the specific orchard environment of a grape greenhouse, the proposed model improves accuracy by 1%, decreases the recall rate by 0.2%, increases the F1 score by 0.4%, and maintains the same mAP. In terms of weight size, it is reduced by 61.1% compared to the original model, and is only 1.8% and 5.5% of the Faster-RCNN and SSD models, respectively. The FPS is increased by 43.5% compared to the original model, and is 11.05 times and 8.84 times that of the Faster-RCNN and SSD models, respectively. On a CPU, the average detection time is 23.9 ms, with a frame rate of 41.9 FPS, representing a 31% improvement over the original model. The test results demonstrate that the lightweight-improved YOLOv5s model proposed in the study, while maintaining accuracy, significantly reduces the model size, enhances recognition speed, and can provide fast and accurate identification and localization for robotic harvesting.

Plant height is regarded as a key indicator that is crucial for assessing the crop growth status and predicting yield. In this study, an advanced method based on solid-state LiDAR technology is proposed, which is specifically designed to accurately capture the phenotypic characteristics of plant height during the maize growth cycle. By segmenting the scanned point cloud of maize, detailed point cloud data of a single maize plant were successfully extracted, from which stem information was accurately measured to obtain accurate plant height information. In this study, we will concentrate on the analysis of individual maize plants. Leveraging the advantages of solid-state LiDAR technology in precisely capturing phenotypic information, the data processing approach for individual maize plants, as compared to an entire maize community, will better restore the maize’s original growth patterns. This will enable the acquisition of more accurate maize plant height information and more clearly demonstrate the potential of solid-state LiDAR in capturing detailed phenotypic information. To enhance the universality of the research findings, this study meticulously selected key growth stages of maize for data validation and comparison, encompassing the tasseling, silking, and maturity phases. At these crucial stages, 20 maize plants at the tasseling stage, 40 at the flowering stage, and 40 at the maturity stage were randomly selected, totaling 100 samples for analysis. Each sample not only included actual measurement values but also included plant height information extracted using point cloud technology. The observation period was set from 20 June to 20 September 2021. This period encompasses the three key growth stages of maize described above, and each growth stage included one round of data collection, with three rounds of data collection each, each spaced about a week apart, for a total of nine data collections. To ensure the accuracy and reliability of the data, all collections were performed at noon when the natural wind speed was controlled within the range of 0 to 1.5 m/s and the weather was clear. The findings demonstrate that the root mean square error (RMSE) of the maize plant height data, procured through LiDAR technology, stands at 1.27 cm, the mean absolute percentage error (MAPE) hovers around 0.77%, and the peak R² value attained is 0.99. These metrics collectively attest to the method’s ongoing high efficiency and precision in capturing the plant height information. In the comparative study of different stem growth stages, especially at the maturity stage, the MAPE of the plant height was reduced to 0.57%, which is a significant improvement compared to the performance at the nodulation and sprouting stage. These results effectively demonstrate that the maize phenotypic information extraction method based on solid-state LiDAR technology is not only highly accurate and effective but is also effective on individual plants, which provides a reliable reference for applying the technique to a wider range of plant populations and extending it to the whole farmland.

The soluble solids content (SSC) is one of the important evaluation indicators for the internal quality of fresh grapes. However, the current non-destructive detection method based on hyperspectral imaging (HSI) relies on manual operation and is relatively cumbersome, making it difficult to achieve automatic detection in batches. Therefore, in this study, we aimed to conduct research on an improved non-destructive detection method for the SSC of bunch-harvested grapes. This study took the Shine-Muscat grape as the research object. Using Mask R-CNN to establish a grape image segmentation model based on deep learning (DL) applied to near-infrared hyperspectral images (400~1000 nm), 35 characteristic wavelengths were selected using Monte Carlo Uninformative Variable Elimination (MCUVE) to establish a prediction model for SSC. Based on the two abovementioned models, the improved non-destructive detection method for the SSC of bunch-harvested grapes was validated. The comprehensive evaluation index F₁ of the image segmentation model was 95.34%. The R_m² and RMSEM of the SSC prediction model were 0.8705 and 0.5696 Brix%, respectively, while the R_p² and RMSEP were 0.8755 and 0.9177 Brix%, respectively. The non-destructive detection speed of the improved method was 16.6 times that of the existing method. These results prove that the improved non-destructive detection method for the SSC of bunch-harvested grapes based on DL and HSI is feasible and efficient.

Accurate segmentation of the stem of pumpkin seedlings has a great influence on the modernization of pumpkin cultivation, and can provide detailed data support for the growth of pumpkin plants. We collected and constructed a pumpkin seedling point cloud dataset for the first time. Potting soil and wall background in point cloud data often interfere with the accuracy of partial cutting of pumpkin seedling stems. The stem shape of pumpkin seedlings varies due to other environmental factors during the growing stage. The stem of the pumpkin seedling is closely connected with the potting soil and leaves, and the boundary of the stem is easily blurred. These problems bring challenges to the accurate segmentation of pumpkin seedling point cloud stems. In this paper, an accurate segmentation algorithm for pumpkin seedling point cloud stems based on CPHNet is proposed. First, a channel residual attention multilayer perceptron (CRA-MLP) module is proposed, which suppresses background interference such as soil. Second, a position-enhanced self-attention (PESA) mechanism is proposed, enabling the model to adapt to diverse morphologies of pumpkin seedling point cloud data stems. Finally, a hybrid loss function of cross entropy loss and dice loss (HCE-Dice Loss) is proposed to address the issue of fuzzy stem boundaries. The experimental results show that CPHNet achieves a 90.4% average cross-to-merge ratio (mIoU), 93.1% average accuracy (mP), 95.6% average recall rate (mR), 94.4% F1 score (mF1) and 0.03 plants/second (speed) on the self-built dataset. Compared with other popular segmentation models, this model is more accurate and stable for cutting the stem part of the pumpkin seedling point cloud.

Accurate collection of plant phenotyping is critical to optimising sustainable farming practices in precision agriculture. Traditional phenotyping in controlled laboratory environments, while valuable, falls short in understanding plant growth under real-world conditions. Emerging sensor and digital technologies offer a promising approach for direct phenotyping of plants in farm environments. This study investigates a learning-based phenotyping method using neural implicit surfaces reconstruction to achieve accurate in situ phenotyping of pepper plants in greenhouse environments. To quantitatively evaluate the performance of this method, traditional point cloud registration on 3D scanning data is implemented for comparison. Experimental result shows that NIR (neural implicit surfaces reconstruction) achieves competitive accuracy compared to the 3D scanning method. The mean distance error between the scanner-based method and the NeRF (neural radiance fields)-based method is 0.811 mm. This study shows that the learning-based NeRF method has similar accuracy to the 3D scanning-based method but with greater scalability and faster deployment capabilities.

Industrialized seeding production is one of the most important methods used to raise seedlings in a standardized and efficient manner. However, its consumption of light energy limits its development. In this paper, we studied the effects of LED light intensities (30 (L1), 60 (L2), 90 (L3), 120 (L4), 150 (L5), 180 (L6), and 210 (L7) µmol·m⁻²·s⁻¹) on the phenotypic parameters and health index of seedlings during different growth stages (cotyledon flattening (CF), one bud and one leaf (OBOL), and one bud and two leaves (OBTL)). Ten out of sixteen plants were selected to measure the parameters in every treatment. The control group was treated with 150 µmol·m⁻²·s⁻¹ all the time. The results show that the height of the L1-treated plants was greatest during the cotyledon flattening stage. The L7 treatment produced the largest stem diameter, the greatest biomass, the largest leaf area, and the largest leaf circumference, the values of which were 2.61 mm, 3.3 g, 60.67 cm², and 39.71 cm, respectively. During the one bud and one leaf stage, the L1 treatment produced the tallest plants. The L7 treatment resulted in the largest stem diameter, the greatest biomass, the largest leaf area, and the largest leaf circumference. During the one bud and two leaves stage, the plant height, stem diameter, leaf circumference, and biomass produced of the L6 treatment were the greatest, with values of 68.37 mm, 3.09 mm, 51.54 cm, and 4.47 g. L5 resulted in the largest leaf area (63.91 cm²). The seedling index of the three stages showed an inflection point at the L4 level. The experimental results showed that the light intensity required by the cucumber seedlings was 120 µmol·m⁻²·s⁻¹, 150 µmol·m⁻²·s⁻¹, and 120 µmol·m⁻²·s⁻¹ during the three stages, from the cotyledon flattening stage to the one bud and two leaves stage. The results provide references regarding the light required during the cultivation of cucumber seedlings.