Search Results (195)

Betula luminifera, an indigenous hardwood tree in South China, possesses significant economic and ecological value. In view of the current severe drought situation, it is urgent to enhance this tree’s drought tolerance. However, traditional artificial methods fall short of meeting the demands of breeding efforts due to their inefficiency. To monitor drought situations in a high-throughput and automatic approach, a deep learning model based on phenotype characteristics was proposed to identify and classify drought stress in B. luminifera seedlings. Firstly, visible-light images were obtained from a drought stress experiment conducted on B. luminifera shoots. Considering the images’ characteristics, we proposed an SAM-CNN architecture by incorporating spatial attention modules into classical CNN models. Among the four classical CNNs compared, ResNet50 exhibited superior performance and was, thus, selected for the construction of the SAM-CNN. Subsequently, we analyzed the classification performance of the SAM-ResNet50 model in terms of transfer learning, training from scratch, model robustness, and visualization. The results revealed that SAM-ResNet50 achieved an accuracy of 1.48% higher than that of ResNet50, at 99.6%. Furthermore, there was a remarkable improvement of 18.98% in accuracy, reaching 82.31% for the spatial transform images generated from the test set images by applying movement and rotation for robustness testing. In conclusion, the SAM-ResNet50 model achieved outstanding performance, with 99.6% accuracy and realized high-throughput automatic monitoring based on phenotype, providing a new perspective for drought stress classification and technical support for B. luminifera-related breeding work. Full article

Germin-like proteins (GLPs) play important roles in the regulation of various plant development processes, such as seed vigor, root and leaf development and disease resistance, while the roles of GLPs on agronomic traits are rarely studied in Brassica napus. Here, we identified GLPs family genes in rapeseed and analyzed their potential functions. There are 77 GLPs family genes (BnGLPs) in the Zhongshuang11 rapeseed reference genome, divided into a, b, c, d, e, f six subfamilies. Tissue expression profile analysis of BnGLPs revealed the following: e subfamily genes were highly expressed in early stages of silique, cotyledon, vegetative rosette and leaf development; f subfamily genes were highly expressed in seed development; genes of a subfamily were mainly expressed in the root; and genes of b, c, d subfamily exhibited low-level or no expression in above mentioned tissues. RT-qPCR analysis confirmed that the transcripts of two f subfamily members decreased dramatically during seed germination, suggesting that f subfamily proteins may play vital roles in the early stage of seed germination. Transcriptome analysis of axillary buds in sequential developing stages revealed that the transcripts of eight e subfamily genes showed a rapid increase at the beginning of shoot branching, implying that the e subfamily members played vital roles in branch development. These results demonstrate that rapeseed BnGLPs likely play essential roles in seedling development, root development and plant architecture, indicating that harnessing certain BnGLPs may contribute to the improvement of rapeseed yield. Full article

Cowpea (Vigna unguiculata (L.) Walp.) is appreciated for its suitability for cultivation and obtaining good yields in relatively extreme farming conditions. It is resistant to high temperatures and drought. Moreover, food products prepared from Vigna are rich in many nutrients such as proteins, amino acids, carbohydrates, minerals, fiber, vitamins, and other bioactive compounds. However, in East and Southeast Asia, where the products of this crop are in demand, the climate is characterized by excessive humidity. Under these conditions, the vast majority of cowpea varieties tend to have indeterminate growth (elongated shoot length) and are unsuitable for mechanized harvesting. The molecular mechanisms for tolerance to high relative humidity remain the least studied in comparison with those for other abiotic stress factors (drought, heat, cold, flooding, etc.). The purpose of the work was to reveal and investigate differentially expressed genes in cowpea accessions having contrasting growth habits (determinate and indeterminate) under humid and drought conditions. We performed RNA-seq analysis using selected cowpea accessions from the VIR collection. Among the genotypes used, some have significant changes in their plant architecture in response to high relative humidity, while others were tolerant to these conditions. In total, we detected 1697 upregulated and 1933 downregulated genes. The results showed that phytohormone-related genes are involved in cowpea response to high relative humidity. DEGs associated with jasmonic acid signaling are proposed to be key contributors in the maintenance of compact architecture under humid conditions. Full article

Strigolactones (SLs) are essential phytohormones involved in plant development and interaction with the rhizosphere, regulating shoot branching, root architecture, and leaf senescence for nutrient reallocation. The Zea mays L. zmccd8 mutant, defective in SL biosynthesis, shows various architectural changes and reduced growth. This study investigates zmccd8 and wild-type (WT) maize plants under two nutritional treatments (N-shortage vs. N-provision as urea). Morphometric analysis, chlorophyll and anthocyanin indexes, drought-related parameters, and gene expression were measured at specific time points. The zmccd8 mutant displayed reduced growth, such as shorter stems, fewer leaves, and lower kernel yield, regardless of the nutritional regime, confirming the crucial role of SLs. Additionally, zmccd8 plants exhibited lower chlorophyll content, particularly under N-deprivation, indicating SL necessity for proper senescence and nutrient mobilization. Increased anthocyanin accumulation in zmccd8 under N-shortage suggested a stress mitigation attempt, unlike WT plants. Furthermore, zmccd8 plants showed signs of increased water stress, likely due to impaired stomatal regulation, highlighting SLs role in drought tolerance. Molecular analysis confirmed higher expression of SL biosynthesis genes in WT under N-shortage, while zmccd8 lacked this response. These findings underscore SL importance in maize growth, stress responses, and nutrient allocation, suggesting potential agricultural applications for enhancing crop resilience. Full article

Industrial waste and sewage deposit heavy metals into the soil, where they can remain for long periods. Although there are several methods to manage heavy metals in agricultural soil, microorganisms present a promising and effective solution for their detoxification. We isolated a rhizofungus, Aspergillus terreus (GenBank Acc. No. KT310979.1), from Parthenium hysterophorus L., and investigated its growth-promoting and metal detoxification capabilities. The isolated fungus was evaluated for its ability to mitigate lead (25 and 75 ppm) and copper (100 and 200 ppm) toxicity in Triticum aestivum L. seedlings. The experiment utilized a completely randomized design with three replicates for each treatment. A. terreus successfully colonized the roots of wheat seedlings, even in the presence of heavy metals, and significantly enhanced plant growth. The isolate effectively alleviates lead and copper stress in wheat seedlings, as evidenced by increases in shoot length (142%), root length (98%), fresh weight (24%), dry weight (73%), protein content (31%), and sugar content (40%). It was observed that wheat seedlings possess a basic defense system against stress, but it was insufficient to support normal growth. Fungal inoculation strengthened the host’s defense system and reduced its exposure to toxic heavy metals. In treated seedlings, exposure to heavy metals significantly upregulated MT1 gene expression, which aided in metal detoxification, enhanced antioxidant defenses, and maintained metal homeostasis. A reduction in metal exposure was observed in several areas, including normalizing the activities of antioxidant enzymes that had been elevated by up to 67% following exposure to Pb (75 mg/kg) and Cu (200 mg/kg). Heavy metal exposure elevated antioxidant levels but also increased ROS levels by 86%. However, with Aspergillus terreus colonization, ROS levels stayed within normal ranges. This decrease in ROS was associated with reduced malondialdehyde (MDA) levels, enhanced membrane stability, and restored root architecture. In conclusion, rhizofungal colonization improved metal tolerance in seedlings by decreasing metal uptake and increasing the levels of metal-binding metallothionein proteins. Full article

As a significant global source of vegetable oil, the oil palm’s ability to withstand abiotic stresses, particularly drought, is crucial for sustainable agriculture. This is especially significant in tropical regions, where water scarcity is becoming more common. Nitrogen, a vital nutrient, plays an essential role in various physiological and biochemical processes in plants, directly influencing growth and stress tolerance. This study investigates the interaction between nitrogen sources (ammonium vs. nitrate) and drought stress in oil palm (Elaeis guineensis) seedlings, which is critical in enhancing productivity in this economically important crop. The experiment evaluated five commercial oil palm genotypes, which were supplied with nitrogen solutions (15 mM NH₄⁺ or NO₃⁻) for 46 days, followed by 30 days of progressive drought. The results showed that drought conditions universally reduced the biomass, with ammonium-fed plants exhibiting greater shoot biomass sensitivity than nitrate-fed plants. Drought also significantly decreased the chlorophyll a, PhiPS2, and root-reducing sugar levels—critical indicators of photosynthetic efficiency and overall plant health. The effects on the root architecture were complex, with ammonium nutrition differentially influencing the lateral root length under well-watered versus drought conditions, highlighting nitrogen forms’ nuanced role in root development. Importantly, substantial genotypic variability was observed in most traits, affecting the responses to both the nitrogen source and drought stress. This variability suggests that certain genotypes may be better suited to cultivation in specific environmental conditions, particularly drought-prone areas. In conclusion, this study underscores the intricate interplay between nitrogen nutrition, genotypic variability, and drought tolerance in oil palm seedlings. These findings highlight the need to integrate these factors into agricultural management strategies to improve resilience and productivity in oil palm plantations. Full article

Some citrus orchards in China often experience nitrogen (N) deficiency. For the first time, targeted metabolomics was used to examine N-deficient effects on hormones in sweet orange (Citrus sinensis (L.) Osbeck cv. Xuegan) leaves and roots. The purpose was to validate the hypothesis that hormones play a role in N deficiency tolerance by regulating root/shoot dry weight ratio (R/S), root system architecture (RSA), and leaf and root senescence. N deficiency-induced decreases in gibberellins and indole-3-acetic acid (IAA) levels and increases in cis(+)-12-oxophytodienoic acid (OPDA) levels, ethylene production, and salicylic acid (SA) biosynthesis might contribute to reduced growth and accelerated senescence in leaves. The increased ethylene formation in N-deficient leaves might be caused by increased 1-aminocyclopropanecarboxylic acid and OPDA and decreased abscisic acid (ABA). N deficiency increased R/S, altered RSA, and delayed root senescence by lowering cytokinins, jasmonic acid, OPDA, and ABA levels and ethylene and SA biosynthesis, increasing 5-deoxystrigol levels, and maintaining IAA and gibberellin homeostasis. The unchanged IAA concentration in N-deficient roots involved increased leaf-to-root IAA transport. The different responses of leaf and root hormones to N deficiency might be involved in the regulation of R/S, RSA, and leaf and root senescence, thus improving N use efficiency, N remobilization efficiency, and the ability to acquire N, and hence conferring N deficiency tolerance. Full article

The search for structural and microstructural defects using simple human vision is associated with significant errors in determining voids, large pores, and violations of the integrity and compactness of particle packing in the micro- and macrostructure of concrete. Computer vision methods, in particular convolutional neural networks, have proven to be reliable tools for the automatic detection of defects during visual inspection of building structures. The study’s objective is to create and compare computer vision algorithms that use convolutional neural networks to identify and analyze damaged sections in concrete samples from different structures. Networks of the following architectures were selected for operation: U-Net, LinkNet, and PSPNet. The analyzed images are photos of concrete samples obtained by laboratory tests to assess the quality in terms of the defection of the integrity and compactness of the structure. During the implementation process, changes in quality metrics such as macro-averaged precision, recall, and F1-score, as well as IoU (Jaccard coefficient) and accuracy, were monitored. The best metrics were demonstrated by the U-Net model, supplemented by the cellular automaton algorithm: precision = 0.91, recall = 0.90, F1 = 0.91, IoU = 0.84, and accuracy = 0.90. The developed segmentation algorithms are universal and show a high quality in highlighting areas of interest under any shooting conditions and different volumes of defective zones, regardless of their localization. The automatization of the process of calculating the damage area and a recommendation in the “critical/uncritical” format can be used to assess the condition of concrete of various types of structures, adjust the formulation, and change the technological parameters of production. Full article

Climate-change-related increases in the frequency and intensity of heatwaves affect viticulture, leading to losses in yield and grape quality. We assessed whether canopy-architecture manipulation mitigates the effects of summer stress in a Mediterranean vineyard. The Vitis vinifera L variety Muscat of Alexandria plants were monitored during 2019–2020. Two canopy shoot-positioning treatments were applied: vertical shoot positioning (VSP) and modulated shoot positioning (MSP). In MSP, the west-side upper foliage was released to promote partial shoot leaning, shading the clusters. Clusters were sampled at pea size (PS), veraison (VER), and full maturation (FM). Measurements included rachis anatomy and hydraulic conductance (Kh) and aquaporins (AQP) and stress-related genes expression in cluster tissues. The results show significant seasonal and interannual differences in Kh and vascular anatomy. At VER, the Kh of the rachis and rachis+pedicel and the xylem diameter decreased but were unaffected by treatments. The phloem–xylem ratio was either increased (2019) or reduced (2020) in MSP compared to VSP. Most AQPs were down-regulated at FM in pedicels and up-regulated at VER in pulp. A potential maturation shift in MSP was observed and confirmed by the up-regulation of several stress-related genes in all tissues. The study pinpoints the role of canopy architecture in berry–water relations and stress response during ripening. Full article

This article primarily focuses on the study of image-based localization technology. While traditional methods have made significant advancements in technology and applications, the emerging field of visual image-based localization technology demonstrates tremendous potential for research. Deep learning has exhibited a strong performance in image processing, particularly in developing visual navigation and localization techniques using large-scale visual models. This paper introduces a sophisticated scene image localization technique based on large models in a vast spatial sample environment. The study involved training convolutional neural networks using millions of geographically labeled images, extracting image position information using large model algorithms, and collecting sample data under various conditions in elastic scene space. Through visual computation, the shooting position of photos was inferred to obtain the approximate position information of users. This method utilizes geographic location information to classify images and combines it with landmarks, natural features, and architectural styles to determine their locations. The experimental results show variations in positioning accuracy among different models, with the most optimal model obtained through training on a large-scale dataset. They also indicate that the positioning error in urban street-based images is relatively small, whereas the positioning effect in outdoor and local scenes, especially in large-scale spatial environments, is limited. This suggests that the location information of users can be effectively determined through the utilization of geographic data, to classify images and incorporate landmarks, natural features, and architectural styles. The study’s experimentation indicates the variation in positioning accuracy among different models, highlighting the significance of training on a large-scale dataset for optimal results. Furthermore, it highlights the contrasting impact on urban street-based images versus outdoor and local scenes in large-scale spatial environments. Full article

In order to promote the accurate recognition and application of visual navigation robots to the environment, this paper carried out research on the road pattern recognition of a vision-guided robot based on improved YOLOv8 on the basis of road pattern calibration and experimental sampling. First, an experimental system for road image shooting was built independently, and 21 different kinds of road pattern image data were obtained by sampling roads with different weather conditions, road materials, and degrees of damage. Second, the road pattern recognition model based on the classical neural network Resnet 18 was constructed for model training and testing, and the initial recognition of road pattern was realized. Third, the YOLOv8 target detection model was introduced to build the road pattern recognition model based on YOLOv8n, and the model was trained and tested, improving road pattern recognition accuracy and recognition response speed by 3.1% and 200%, respectively. Finally, to further improve the accuracy of road pattern recognition, improvement research was carried out on the YOLOv8n road pattern recognition model based on the C2f-ODConv module, the AWD adaptive weight downsampling module, the EMA attention mechanism, and the collaboration of the three modules. Three network architectures, classical CNN (Resnet 18), YOLOv8n, and improved YOLOv8n, were compared. The results show that four different optimization models can further improve the accuracy of road pattern recognition, among which the accuracy of the improved YOLO v8 road pattern recognition model based on multimodule cooperation is the highest, reaching more than 93%. Full article

Unmanned aerial vehicle (UAV) aerial images often present challenges such as small target sizes, high target density, varied shooting angles, and dynamic poses. Existing target detection algorithms exhibit a noticeable performance decline when confronted with UAV aerial images compared to general scenes. This paper proposes an outstanding small target detection algorithm for UAVs, named Fine-Grained Feature Perception YOLOv8s-P2 (FGFP-YOLOv8s-P2), based on YOLOv8s-P2 architecture. We specialize in improving inspection accuracy while meeting real-time inspection requirements. First, we enhance the targets’ pixel information by utilizing slice-assisted training and inference techniques, thereby reducing missed detections. Then, we propose a feature extraction module with deformable convolutions. Decoupling the learning process of offset and modulation scalar enables better adaptation to variations in the size and shape of diverse targets. In addition, we introduce a large kernel spatial pyramid pooling module. By cascading convolutions, we leverage the advantages of large kernels to flexibly adjust the model’s attention to various regions of high-level feature maps, better adapting to complex visual scenes and circumventing the cost drawbacks associated with large kernels. To match the excellent real-time detection performance of the baseline model, we propose an improved Random FasterNet Block. This block introduces randomness during convolution and captures spatial features of non-linear transformation channels, enriching feature representations and enhancing model efficiency. Extensive experiments and comprehensive evaluations on the VisDrone2019 and DOTA-v1.0 datasets demonstrate the effectiveness of FGFP-YOLOv8s-P2. This achievement provides robust technical support for efficient small target detection by UAVs in complex scenarios. Full article

Wood volume is an important indicator in timber trading, and log diameter is one of the primary parameters used to calculate wood volume. Currently, the most common methods for measuring log diameters are manual measurement or visual estimation by log scalers, which are laborious, time consuming, costly, and error prone owing to the irregular placement of logs and large numbers of roots. Additionally, this approach can easily lead to misrepresentation of data for profit. This study proposes a model for automatic log diameter measurement that is based on deep learning and uses images to address the existing problems. The specific measures to improve the performance and accuracy of log-diameter detection are as follows: (1) A dual network model is constructed combining the Yolov3 algorithm and DeepLabv3+ architecture to adapt to different log-end color states that considers the complexity of log-end faces. (2) AprilTag vision library is added to estimate the camera position during image acquisition to achieve real-time adjustment of the shooting angle and reduce the effect of log-image deformation on the results. (3) The backbone network is replaced with a MobileNetv2 convolutional neural network to migrate the model to mobile devices, which reduces the number of network parameters while maintaining detection accuracy. The training results show that the mean average precision of log-diameter detection reaches 97.28% and the mean intersection over union (mIoU) of log segmentation reaches 92.22%. Comparisons with other measurement models demonstrate that the proposed model is accurate and stable in measuring log diameter under different environments and lighting conditions, with an average accuracy of 96.26%. In the forestry test, the measurement errors for the volume of an entire truckload of logs and a single log diameter are 1.20% and 0.73%, respectively, which are less than the corresponding error requirements specified in the industry standards. These results indicate that the proposed method can provide a viable and cost-effective solution for measuring log diameters and offering the potential to improve the efficiency of log measurement and promote fair trade practices in the lumber industry. Full article

With the continuous expansion of the transport network, the safe operation of high-speed railway rails has become a crucial issue. Defect detection on the surface of rails is a key part of ensuring the safe operation of trains. Despite the progress of deep learning techniques in defect detection on the rails’ surface, there are still challenges related to various problems, such as small datasets and the varying scales of defects. Based on this, this paper proposes an improved encoder–decoder architecture based on Swin Transformer network, named Rail-STrans, which is specifically designed for intelligent segmentation of high-speed rail surface defects. The problem of a small and black-and-white rail dataset is solved using self-made large and multiple rail surface defect datasets through field shooting, data labelling, and data expansion. In this paper, two Local Perception Modules (LPMs) are added to the encoding network, which helps to obtain local context information and improve the accuracy of detection. Then, the Multiscale Feature Fusion Module (MFFM) is added to the decoding network, which helps to effectively fuse the feature information of defects at different scales in the decoding process and improves the accuracy of defect detection at multiple scales. Meanwhile, the Spatial Detail Extraction Module (SDEM) is added to the decoding network, which helps to retain the spatial detail information in the decoding process and further improves the detection accuracy of small-scale defects. The experimental results show that the mean accuracy of the semantic segmentation of the method proposed in this paper can reach 90.1%, the mean dice coefficient can reach 89.5%, and the segmentation speed can reach 37.83 FPS, which is higher than other networks’ segmentation accuracy. And, at the same time, it can achieve higher efficiency. Full article

Branching is an important agronomic trait that is conducive to plant architecture and yield in flowering Chinese cabbage. Plant branching is regulated by a complex network mediated by hormones; gibberellin (GA) is one of the important hormones which is involved in the formation of shoot branching. Research on the regulatory mechanism of GA influencing rosette branch numbers is limited for flowering Chinese cabbage. In this study, the exogenous application of 600 mg/L GA₃ effectively inhibited rosette branching and promoted internode elongation in flowering Chinese cabbage. RNA-Seq analysis further found that these DEGs were significantly enriched in ‘the plant hormone signal transduction’ pathways, and auxin-related genes were significantly differentially expressed between MB and MB_GA. The upregulation of auxin (AUX) and the upregulation of auxin/indole-3-acetic acid (AUX/IAA), as well as the downregulation of SMALL AUXIN-UPREGULATED RNA (SAUR), were found in the negative regulation of the rosette branching. The qRT-PCR results showed that the expression of AUX/IAA and SAUR from IAA gene family members were consistent with the results of transcriptome data. Phytohormone profiling by targeted metabolism revealed that endogenous auxin contents were significantly increased in MB_GA. Transcriptome and metabolome analysis clarified the main plant hormones and genes underlying the rosette branching in flowering Chinese cabbage, confirming that auxin could inhibit rosette branching. In this regard, the results present a novel angle for revealing the mechanism of gibberellin acting on the branching architecture in flowering Chinese cabbage. Full article