Drought stress is a major environmental constraint for plant growth. Climate-change-driven increases in ambient temperatures resulted in reduced or unevenly distributed rainfalls, leading to increased soil drought. Carex duriuscula C. A. Mey is a typical drought-tolerant sedge, but few reports have examined the mechanisms conferring its tolerant traits. In the present study, the drought responses of C. duriuscula were assessed by quantifying activity of antioxidant enzymes in its leaf and root tissues and evaluating the relative contribution of organic and inorganic osmolyte in plant osmotic adjustment, linking it with the patterns of the ion acquisition by roots. Two levels of stress—mild (MD) and severe (SD) drought treatments—were used, followed by re-watering. Drought stress caused reduction in a relative water content and chlorophyll content of leaves; this was accompanied by an increase in the hydrogen peroxide (H₂O₂) and superoxide (O_2⁻) contents in leaves and roots. Under MD stress, the activities of catalase (CAT), peroxidase (POD), and glutathione peroxidase (GPX) increased in leaves, whereas, in roots, only CAT and POD activities increased. SD stress led to an increase in the activities of CAT, POD, superoxide dismutase (SOD), and GPX in both tissues. The levels of proline, soluble sugars, and soluble proteins in the leaves also increased. Under both MD and SD stress conditions, C. duriuscula increased K⁺, Na⁺, and Cl⁻ uptake by plant roots, which resulted in an increased K⁺, Na⁺, and Cl⁻ concentrations in leaves and roots. This reliance on inorganic osmolytes enables a cost-efficient osmotic adjustment in C. duriuscula. Overall, this study revealed that C. duriuscula was able to survive arid environments due to an efficient operation of its ROS-scavenging systems and osmotic adjustment mechanisms.

Introduction: Nondestructive detection of crop phenotypic traits in the field is very important for crop breeding. Ground-based mobile platforms equipped with sensors can efficiently and accurately obtain crop phenotypic traits. In this study, we propose a dynamic 3D data acquisition method in the field suitable for various crops by using a consumer-grade RGB-D camera installed on a ground-based movable platform, which can collect RGB images as well as depth images of crop canopy sequences dynamically.Methods: A scale-invariant feature transform (SIFT) operator was used to detect adjacent date frames acquired by the RGB-D camera to calculate the point cloud alignment coarse matching matrix and the displacement distance of adjacent images. The data frames used for point cloud matching were selected according to the calculated displacement distance. Then, the colored ICP (iterative closest point) algorithm was used to determine the fine matching matrix and generate point clouds of the crop row. The clustering method was applied to segment the point cloud of each plant from the crop row point cloud, and 3D phenotypic traits, including plant height, leaf area and projected area of individual plants, were measured.Results and Discussion: We compared the effects of LIDAR and image-based 3D reconstruction methods, and experiments were carried out on corn, tobacco, cottons and Bletilla striata in the seedling stage. The results show that the measurements of the plant height (R²= 0.9~0.96, RSME = 0.015~0.023 m), leaf area (R²= 0.8~0.86, RSME = 0.0011~0.0041 m² ) and projected area (R² = 0.96~0.99) have strong correlations with the manual measurement results. Additionally, 3D reconstruction results with different moving speeds and times throughout the day and in different scenes were also verified. The results show that the method can be applied to dynamic detection with a moving speed up to 0.6 m/s and can achieve acceptable detection results in the daytime, as well as at night. Thus, the proposed method can improve the efficiency of individual crop 3D point cloud data extraction with acceptable accuracy, which is a feasible solution for crop seedling 3D phenotyping outdoors.

With the progress of agricultural modernization, intelligent fruit harvesting is gaining importance. While fruit detection and recognition are essential for robotic harvesting, existing methods suffer from limited generalizability, including adapting to complex environments and handling new fruit varieties. This problem stems from their reliance on unimodal visual data, which creates a semantic gap between image features and contextual understanding. To solve these issues, this study proposes a multi-modal fruit detection and recognition framework based on visual language models (VLMs). By integrating multi-modal information, the proposed model enhances robustness and generalization across diverse environmental conditions and fruit types. The framework accepts natural language instructions as input, facilitating effective human–machine interaction. Through its core module, Enhanced Contrastive Language–Image Pre-Training (E-CLIP), which employs image–image and image–text contrastive learning mechanisms, the framework achieves robust recognition of various fruit types and their maturity levels. Experimental results demonstrate the excellent performance of the model, achieving an F1 score of 0.752, and an mAP@0.5 of 0.791. The model also exhibits robustness under occlusion and varying illumination conditions, attaining a zero-shot mAP@0.5 of 0.626 for unseen fruits. In addition, the system operates at an inference speed of 54.82 FPS, effectively balancing speed and accuracy, and shows practical potential for smart agriculture. This research provides new insights and methods for the practical application of smart agriculture.

Verticillium wilt is one of the most critical cotton diseases, which is widely distributed in cotton-producing countries. However, the conventional method of verticillium wilt investigation is still manual, which has the disadvantages of subjectivity and low efficiency. In this research, an intelligent vision-based system was proposed to dynamically observe cotton verticillium wilt with high accuracy and high throughput. Firstly, a 3-coordinate motion platform was designed with the movement range 6,100 mm × 950 mm × 500 mm, and a specific control unit was adopted to achieve accurate movement and automatic imaging. Secondly, the verticillium wilt recognition was established based on 6 deep learning models, in which the VarifocalNet (VFNet) model had the best performance with a mean average precision (mAP) of 0.932. Meanwhile, deformable convolution, deformable region of interest pooling, and soft non-maximum suppression optimization methods were adopted to improve VFNet, and the mAP of the VFNet-Improved model improved by 1.8%. The precision–recall curves showed that VFNet-Improved was superior to VFNet for each category and had a better improvement effect on the ill leaf category than fine leaf. The regression results showed that the system measurement based on VFNet-Improved achieved high consistency with manual measurements. Finally, the user software was designed based on VFNet-Improved, and the dynamic observation results proved that this system was able to accurately investigate cotton verticillium wilt and quantify the prevalence rate of different resistant varieties. In conclusion, this study has demonstrated a novel intelligent system for the dynamic observation of cotton verticillium wilt on the seedbed, which provides a feasible and effective tool for cotton breeding and disease resistance research.

Phenotyping robots have the potential to obtain crop phenotypic traits on a large scale with high throughput. Autonomous navigation technology for phenotyping robots can significantly improve the efficiency of phenotypic traits collection. This study developed an autonomous navigation method utilizing an RGB‐D camera, specifically designed for phenotyping robots in field environments. The PP‐LiteSeg semantic segmentation model was employed due to its real‐time and accurate segmentation capabilities, enabling the distinction of crop areas in images captured by the RGB‐D camera. Navigation feature points were extracted from these segmented areas, with their three‐dimensional coordinates determined from pixel and depth information, facilitating the computation of angle deviation (α) and lateral deviation (d). Fuzzy controllers were designed with α and d as inputs for real‐time deviation correction during the walking of phenotyping robot. Additionally, the method includes end‐of‐row recognition and row spacing calculation, based on both visible and depth data, enabling automatic turning and row transition. The experimental results showed that the adopted PP‐LiteSeg semantic segmentation model had a testing accuracy of 95.379% and a mean intersection over union of 90.615%. The robot's navigation demonstrated an average walking deviation of 1.33 cm, with a maximum of 3.82 cm. Additionally, the average error in row spacing measurement was 2.71 cm, while the success rate of row transition at the end of the row was 100%. These findings indicate that the proposed method provides effective support for the autonomous operation of phenotyping robots.