Camellia Oleifera Research Articles

The tetraploid Camellia oleifera genome provides insights into evolution, agronomic traits, and genetic architecture of oil Camellia plants

The tetraploid Camellia oleifera genome provides insights into evolution, agronomic traits, and genetic architecture of oil Camellia plants

Progress in the resistance mechanism and breeding of Camellia oleifera with resistance to anthracnose

Camellia oleifera is an important woody oil crop in China, and its seed oil has a high economic value. Anthracnose, one of the main diseases in C. oleifera, occurs in a wide range in the production areas, limiting the growth and development of plants and causing serious losses of oil production. With the rapid development of the C. oleifera industry in recent years, great progress has been achieved in the research on anthracnose in C. oleifera. This paper summarized the resistance mechanisms, the mining of resistance genes, and the evaluation of resistant germplasm resources, aiming to provide a theoretical basis for the prevention and control of anthracnose and the breeding of C. oleifera germplasm with resistance to anthracnose.

Camellia oleifera trunks detection and identification based on improved YOLOv7

<i>Camellia oleifera</i> trunks detection and identification based on improved YOLOv7

Camellia oleifera Tree Detection and Counting Based on UAV RGB Image and YOLOv8

The detection and counting of Camellia oleifera trees are important parts of the yield estimation of Camellia oleifera. The ability to identify and count Camellia oleifera trees quickly has always been important in the context of research on the yield estimation of Camellia oleifera. Because of their specific growing environment, it is a difficult task to identify and count Camellia oleifera trees with high efficiency. In this paper, based on a UAV RGB image, three different types of datasets, i.e., a DOM dataset, an original image dataset, and a cropped original image dataset, were designed. Combined with the YOLOv8 model, the detection and counting of Camellia oleifera trees were carried out. By comparing YOLOv9 and YOLOv10 in four evaluation indexes, including precision, recall, mAP, and F1 score, Camellia oleifera trees in two areas were selected for prediction and compared with the real values. The experimental results show that the cropped original image dataset was better for the recognition and counting of Camellia oleifera, and the mAP values were 8% and 11% higher than those of the DOM dataset and the original image dataset, respectively. Compared to YOLOv5, YOLOv7, YOLOv9, and YOLOv10, YOLOv8 performed better in terms of the accuracy and recall rate, and the mAP improved by 3–8%, reaching 0.82. Regression analysis was performed on the predicted and measured values, and the average R2 reached 0.94. This research shows that a UAV RGB image combined with YOLOv8 provides an effective solution for the detection and counting of Camellia oleifera trees, which is of great significance for Camellia oleifera yield estimation and orchard management.

Safety and efficacy of a feed additive consisting of a Camellia oleifera C.Abel seed extract for use in all animal species except fin fish (NOR-FEED SAS).

Following a request from the European Commission, EFSA was asked to deliver a scientific opinion on the safety and efficacy of a Camellia oleifera C.Abel seed extract (Cosap®) as technological feed additive for all animal species except fin fish. In the absence of adequate tolerance studies in the target species or toxicological studies with the additive under assessment, the EFSA Panel on Additives and Products or Substances used in Animal Feed (FEEDAP) could not conclude on the safety of C. oleifera extract for the target species. The use of the additive in animal nutrition is not expected to cause concern for consumer safety. The additive is considered as irritant to the eyes and mucous membranes. No conclusions can be reached on the potential of the additive to be irritant to the skin or to be a dermal sensitiser. The use of the additive under the proposed conditions of use is considered safe for the terrestrial compartment. However, no conclusion can be reached on the safety of the additive for the environment when used in feed of aquatic animals other than fin fish. The Panel concluded that the additive has the potential to be efficacious as an emulsifier when used according to proposed conditions of use.

Non-antibiotic feed additives production by Acremonium terricola solid-fermented Camellia oleifera meal

The Camellia oleifera meal (COM), a primary byproduct of oil-tea processing, often being discarded or used as a low-grade fertilizer due to its low value. The underutilization has become a significant bottleneck hindering the high-quality development of the oil-tea industry. In this study, the production of antibiotic-free feed additives through the solid-state fermentation of COM by Acremonium terricola was investigated. Our findings revealed that a saponin concentration of 5 mg/mL significantly enhanced the production of cordycepic acid (70.4 mg/g), ergosterol (3.32 mg/g), and chitin (110 mg/g) by A. terricola. This concentration also promoted chitin production and the activities of peroxidase (POD) and Na+/K+-ATPase, thereby maintaining cellular homeostasis and energy balance in A. terricola. Solid-state fermented rice bran (RB), wheat bran (WB), and desaponificated COM (containing 2.6 mg/100 g of tea saponin) were all found to be beneficial for increasing the production of cordycepic acid and ergosterol. The blend of COM, RB, and WB in the ratio of 15:65:20 was particularly advantageous for the production and accumulation of cordycepic acid and ergosterol, yielding 1.54 and 1.43 times, 1.27 and 1.37 times, and 1.98 and 5.52 times more than those produced by WB, RB, and COM alone, respectively.Meantime, the difference in contents of sugar and protein in A. terricola cultures (ATCs) using combination were not significant compared to RB and WB. These results indicated that COM can partially replace foodstuffs or food by-products to prepare antibiotic-free feed additives by A. terricola.Graphical

Detection of Camellia oleifera fruit maturity in orchards based on modified lightweight YOLO

Fruit maturity is the main factor affecting the quality and yield of Camellia oil. At present, accurate and efficient detection of the maturity level of Camellia oleifera fruits in orchards and enabling selective picking for harvesting robots is a crucial issue. Aiming at the challenge of low detection efficiency of Camellia oleifera fruit maturity and complex object detection models that are difficult to deploy to Camellia oleifera selective harvesting robots, a modified lightweight You Only Look Once model (YOLO-LM) based on YOLOv7-tiny is proposed. Specifically, three Criss-Cross Attention (CCA) modules are introduced to the backbone network to reduce the influence of leaves and branches occlusion as well as mutual occlusion between fruits. Then, the Adaptively Spatial Feature Fusion (ASFF) module is applied as the head to solve the limitation of inconsistency across different feature scales on the feature pyramid. Furthermore, the GSConv is introduced to replace the standard convolution of the Neck network to enable the model to simultaneously preserve model accuracy and reduce model complexity. Experiment results demonstrate that the precision, recall, mAP@0.5, parameters, FLOPs, and model size of YOLO-LM reached 93.96 %, 93.32 %, 93.18 %, 10.17 million, 19.46 G, and 19.82 MB, which outperformed YOLOv3, Faster R-CNN (VGG16), Faster R-CNN (ResNet50), YOLOv4, and YOLOv5m. Compared to YOLOv3-tiny, YOLOv4-tiny, YOLOv5s, YOLOv7-tiny, and YOLOv8s, the mAP@0.5 of YOLO-LM increased by 6.24 %, 6.11 %, 2.52 %, 2.45 %, and 0.57 %, respectively. Meanwhile, the parameters and model size of YOLO-LM are slightly higher than that of YOLOv3-tiny, YOLOv4-tiny, YOLOv5s and YOLOv7-tiny, and significantly lower than that of YOLOv8s. In addition, the detection heatmaps of YOLOv7-tiny and YOLO-LM demonstrate these optimization operations contribute to the enhanced performance of maturity detection for Camellia oleifera fruits within natural orchard environments. Overall, the YOLO-LM model can be used for the maturity detection of Camellia oleifera fruits in orchards, which is expected to provide theoretical reference for orchard yield estimation, growth monitoring, planting management optimization and the development of Camellia oleifera selective harvesting robots.

Biochar Applied in Places Where Its Feedstock Was Produced Mitigated More CO2 Emissions from Acidic Red Soils

Agricultural soil is the main source of greenhouse gas emissions, among which carbon dioxide (CO2) is an important greenhouse gas, impacting the global climate. In China, as a large rice-producing country, carbon sequestration and CO2 mitigation in paddy soil are crucial for the mitigation of global climate change. While biochar has been widely used in the mitigation of soil greenhouse gas emissions, the application site of biochar, i.e., whether or not it is the same as its feedstocks, may generate different effects on soil CO2 emissions due to the differences in the element and nutrient concentrations in its feedstocks, especially when applied in fertilized soil. In order to explore the effects of biochar application with different feedstocks on the mitigation of CO2 emissions from paddy soil, this experiment took paddy soil in a red soil area as the research object, using rice straw and Camellia oleifera fruit shell as raw materials to produce biochar (adding an amount of 40 g kg−1 soil) and urea as an external nitrogen source (adding an amount of 200 mg kg−1 soil). The effects of two different types of biochar derived from feedstocks with different producing origins on the CO2 emissions from paddy soil were studied via laboratory control incubation studies. The results showed that (1) the effects of rice straw biochar addition on the soil pH, NO3−-N and total available nitrogen (AN) content were significantly higher than those of Camellia oleifera fruit shell biochar (the scale of the increase was higher by 6.40%, 579.7% and 180.1%, respectively). (2) The CO2 emission rate and cumulative emissions of soil supplemented with rice straw biochar were significantly lower than in that supplemented with Camellia oleifera fruit shell biochar (decreases of 28.0% and 27.5%, respectively). Our findings suggest that the efficiency of emission mitigation of rice straw biochar is better than that of Camellia oleifera fruit shell applied to paddy soil. While future studies considering more types of greenhouse gases will be necessary to expand these findings, this study indicates that biochar prepared from in situ feedstock can be used to reduce greenhouse gas emissions in rice fields, so as to ensure sustainable development and achieve energy conservation and emission reduction goals. This study will benefit future agricultural practices when choosing biochar as a greenhouse gas mitigation strategy in the context of global warming, as well as other global changes following global warming, caused by elevated atmospheric greenhouse gases.

Research on the Design Method of Camellia oleifera Fruit Picking Machine

Camellia oleifera fruit pickers are essential for improving picking efficiency and promoting the Camellia oleifera industry. However, it is challenging to develop pickers that meet user needs. Current design tools and methods have limitations, such as a single model, poor synergy between integrated models, and subjective bias when analysing user requirements and translating them into product attributes. To solve these problems, this study proposes a new design decision model based on the Fuzzy Analytic Hierarchy Process (FAHP), Function Analysis System Technique (FAST), Theory of Inventive Problem Solving (TRIZ Theory), and extension transformation theory. The model was developed and applied to design an Camellia oleifera fruit picker. In this paper, an empirical investigation of an Camellia oleifera base in Wuhan was carried out, and multi-level demand analysis was used to identify the design demands in the behavioural process; FAHP was used to calculate the demand weights to clarify the design focus; expert knowledge was used to convert the demands into specific product functional features, and FAST was used to decompose these features to find the contradictory conflicts; TRIZ theory was used to determine the principles of resolving the contradictions, and the extension transformation theory were used to generate the creative design solutions for the products. By integrating FAHP, FAST, TRIZ theory and the extension transformation theory, the subjective bias in product design is eliminated, the design decision-making process is improved, and new methods and ideas are provided for the design of oleaginous tea fruit pickers and similar products. Finally, the conceptual design of an Camellia oleifera fruit picking machine was produced. However, the conceptual design has yet to be subjected to exhaustive simulation experiments and prototype testing. Future research will focus on conducting the necessary simulations, prototypes, and field tests to fully assess the feasibility and effectiveness of the design and make the required iterative improvements accordingly to commercialize the product eventually.

Integrated transcriptome and endogenous hormone analyses reveal the factors affecting the yield of Camellia oleifera

Camellia oleifera is an important woody oil tree in China, in which the flowers and fruits appear during the same period. The endogenous hormone changes and transcription expression levels in different parts of the flower tissue (sepals, petals, stamens, and pistils), flower buds, leaves, and seeds of Changlin 23 high-yield (H), Changlin low-yield (L), and control (CK) C. oleifera groups were studied. The abscisic acid (ABA) content in the petals and stamens in the L group was significantly higher than that in the H and CK groups, which may be related to flower and fruit drops. The high N6-isopentenyladenine (iP) and indole acetic acid (IAA) contents in the flower buds may be associated with a high yield. Comparative transcriptome analysis showed that the protein phosphatase 2C (PP2C), jasmonate-zim-domain protein (JAZ), and WRKY-related differentially expressed genes (DEGs) may play an important role in determining leaf color. Gene set enrichment analysis (GSEA) comparison showed that jasmonic acid (JA) and cytokinin play an important role in determining the pistil of the H group. In this study, endogenous hormone and transcriptome analyses were carried out to identify the factors influencing the large yield difference in C. oleifera in the same year, which provides a theoretical basis for C. oleifera in the future.

Optimization of the Camellia oleifera Fruit Harvester Engine Compartment Heat Dissipation Based on Temperature Experiments and Airflow Field Simulation

The Camellia oleifera fruit harvester, a specialized agricultural device, is engineered for efficient operation within the densely planted C. oleifera groves of China’s undulating terrains. Its design features a notably small footprint to navigate the constrained spaces between trees. With the enhancement of the functionality and power of the harvester, the engine compartment becomes even more congested. This, while beneficial for performance, complicates heat dissipation and reduces harvesting efficiency. In this study, experiments were initially conducted to collect temperature data from the main heat-generating components and parts susceptible to high temperatures within the harvester’s engine compartment. Subsequently, a 3D model was developed for numerical simulations, leading to the proposal of optimization schemes for the engine compartment’s structure and the validation of these schemes’ feasibility. A comparison of the experimental data, both before and after optimization, revealed a significant reduction in the surface temperatures of components within the engine compartment following optimization. As a result, the heat dissipation of the engine compartment has been greatly optimized. The harvester has demonstrated prolonged normal operation, enhancing the reliability and economy of the harvester.

Effect of peanut straw mulching on the soil nitrogen change and functional genes in the Camellia oleifera intercropping system

Effect of peanut straw mulching on the soil nitrogen change and functional genes in the Camellia oleifera intercropping system

Selective electrosorption of heavy metal ions from wastewater with S-doped hierarchical porous carbon derived from waste Camellia oleifera shell

Capacitive deionization (CDI) has garnered significant attention in desalination and the removal of heavy metal ions. The quest for cost-effective and high-performance electrode materials is crucial to advance CDI applications. Herein, we report a sulfur-doped hierarchical porous carbon (SPC) derived from waste camellia oleifera shells via a sustainable hydrothermal carbonization process followed by KOH/ammonium salt activation. The optimized SPC-0.2 exhibits exceptional characteristics, featuring a high specific surface area of 1875 m2 g−1 and substantial sulfur doping at 8.65 %, leading to enhanced specific capacitance (161.3 F g−1) in a 1 M NaCl solution. Under optimal operating conditions (1.2 V, 10 mL min−1, 500 mg L−1 NaCl), the SPC-0.2 electrode achieves a notable desalination capacity of 26.64 mg g−1. In particular, the electrode can selectively remove >99 % of Cr3+ and Cu2+ ions (each 10 mg L−1) in a 100 mg L−1 NaCl solution. This high selectivity is attributed to the formation of sulfides via low adsorption energies between the doped sulfur atoms and the targeted heavy metal ions. Furthermore, the SPC-0.2 electrode demonstrates robust reusability and high efficiency in the actual water body. Collectively, our findings underscore the significant potential of the synthesized SPC as an electrode material for CDI, particularly in the selective capacitive removal of heavy metal ions from wastewater. This work not only contributes to the circular economy by using waste biomass, but also offers a viable solution for environmental remediation.

Mitochondrial genome study of Camellia oleifera revealed the tandem conserved gene cluster of nad5-nads in evolution.

Camellia oleifera is a kind of high-quality oil supply species. Its seeds contain rich unsaturated fatty acids and antioxidant active ingredients, which is a kind of high-quality edible oil. In this study, we used bioinformatics methods to decipher a hexaploid Camellia oil tree's mitochondrial (mt) genome based on second-generation sequencing data. A 709,596 bp circular map of C. oleifera mt genome was found for the first time. And 74 genes were annotated in the whole genome. Mt genomes of C. oleifera and three Theaceae species had regions with high similarity, including gene composition and gene sequence. At the same time, five conserved gene pairs were found in 20 species. In all of the mt genomes, most of nad genes existed in tandem pairs. In addition, the species classification result, which, according to the gene differences in tandem with nad5 genes, was consistent with the phylogenetic tree. These initial results provide a valuable basis for the further researches of Camellia oleifera and a reference for the systematic evolution of plant mt genomes.

Serendipita indica: A Promising Biostimulant for Improving Growth, Nutrient Uptake, and Sugar Accumulation in Camellia oleifera

Serendipita indica is a very promising root-associated endophytic fungus that is widely used on various plants; however, whether it affects the growth and physiological activity of an oilseed crop (Camellia oleifera) under field conditions remains unclear. In this study, we analyzed the effects of S. indica inoculation on root colonization rate, growth rate, photosynthetic parameters, mineral element concentrations and related gene expression, and sugar concentrations and expression of their transporter genes in four-year-old C. oleifera trees in the field. The results showed that the root colonization rate of C. oleifera increased from 3.37% to 9.42% following being inoculated with S. indica. Inoculation with S. indica significantly increased the plant height (46.81%), net photosynthetic rate (69.16%), nitrogen balance index (14.44%), chlorophyll index (21.08%), leaf K (7.4%), leaf Ca (13.52%), root P (17.75%), root K (12.80%), soil NH4+-N (17.78%), available K (26.66%), Olsen-P (184.30%), easily extractable glomalin-related soil protein (39.26%), and soil organic carbon (16.25%) concentrations compared to the uninoculated treatment. Inoculation with S. indica also significantly up-regulated the expression of CoHKT1;1 and CoCAX1;2 in the leaves and roots and CoPht1;1, CoPht1;2, and CoPht1;3 in the leaves. Plants inoculated with S. indica also presented significantly higher leaf glucose, fructose, and sucrose concentrations, accompanied by up-regulated expression of CoSWEET2a, CoSWEET7, CoSWEET9b, CoSWEET17a, and CoSWEET17b. These results suggest that S. indica has significant potential as a biostimulant for enhancing the growth and nutritional profile of C. oleifera, thereby contributing to sustainable oilseed production.

Tree species identity affects soil P bioavailability by altering labile organic P after tree mixing in subtropical China

AbstractConverting monocultures to mixed plantations has been emphasized to improve ecosystem productivity and services. However, the impact of tree species identity on phosphorus (P) bioavailability in acidic soils in subtropical China, where P is relatively scarce, is not fully understood. This study explored the changes in soil biologically‐based P fractions and the effect of mineral and microbial properties on P transformation after mixing five broadleaved trees (Bretschneidera sinensis, Manglietia conifera, Cercidiphyllum japonicum, Michelia maudiae and Camellia oleifera) individually with coniferous trees (Pinus massoniana). The results showed that most mixed plantations significantly increased pH and citric acid and decreased exchangeable Fe3+ and Al3+ and the activation of Fe and Al oxides compared with monospecific plantations, which significantly reduced P precipitation and adsorption. Mixed planting significantly increased phosphatase activity and altered the community composition of P‐mobilizing bacteria carrying phoD and pqqC genes, which contributed to organic P mineralization and inorganic P (Pi) desorption. Mixed planting increased microbial biomass and the relative rate of microbial biomass P turnover. Labile organic P (Enzyme‐P) was a potentially significant source of soluble Pi (CaCl2‐P) among the biologically‐based P fractions, plus microbial biomass P. Overall, introducing broadleaved species, especially in species (e.g. Cercidiphyllum japonicum, Michelia maudiae and Camellia oleifera) with relatively high litter quality and belowground secretions (e.g. citric acid, phosphatase), significantly increased the solubilization of recalcitrant Pi (HCl‐P), desorption of chemisorbed Pi (Citrate‐P) and accumulation and mineralization of Enzyme‐P, thereby increasing the available P pools. Redundancy analysis demonstrated that P fractions were mainly driven by phosphatases, exchangeable cations, floor fresh litter lignin/N and citric acid. Altogether, we highlight the importance of choosing tree species mixtures that have synergistic or complementary effects when constructing mixed plantations in order to alleviate soil P limitations.

Catalytic depolymerization of Camellia oleifera shell lignin to phenolic monomers: Insights into the effects of solvent, catalyst and atmosphere

Camellia oleifera shell (COS) is a renewable biomass resource abundant in lignin with significant potential for producing phenolic monomers. However, the dearth of research has led to considerable resource wastage and environmental pollution. Herein, reductive catalytic fractionation (RCF) of COS was performed using noble metal catalysts in different solvents. An 11.1 wt% yield of phenolic monomers was achieved with 91% selectivity toward propylene-substituted monomers in H2O/EtOH (3:7, v/v) cosolvent under N2 atmosphere. Notably, the highest phenolic monomer yield of 17.0 wt% was obtained with impressive selectivity (86.9%) toward propanol-substituted monomers in the presence of H2. The GPC analysis and 2D HSQC NMR spectra indicated the effective depolymerization of lignin oligomers with catalysts. Phenolic monomers with ethyl, propyl, or propanol side chain could be produced from lignin-derived oligomers through hydrogenolysis, hydrogenation, and decarboxylation reactions. Overall, this study has paved the way for the valorization of COS lignin through the RCF strategy.

Characteristics and adsorption of methylene blue on activated carbon derived from enzyme-pretreated Camellia oleifera shells

Activated carbon is a porous material extensively utilized in water treatment field. In this study, an efficient activated carbon (E-AC) adsorbent was prepared from agricultural by-product Camellia oleifera shells (COS) by enzymatic pretreatment combined with phosphoric acid activation. The enzymatic pretreatment was beneficial for increasing the volume of mesopores and loosening the structure of the synthesized activated carbon, which ultimately led to an increased adsorption capacity of E-AC. The characteristics and adsorption performances of E-AC were thoroughly investigated. The results showed that E-AC exhibited a high adsorption capacity of 1249.01 mg/g on methylene blue (MB), and the adsorption process was a spontaneous endothermic process. The adsorption kinetics aligned closely with the pseudo-second-order kinetic model (R2 > 0.99), and the adsorption mechanisms could be a combination of hydrogen bonding, π-π conjugation, electrostatic attraction, and physical adsorption. Additionally, E-AC exhibited good reusability, with a consistent MB removal rate of 91.14 % even after five cycles. This study offered an approach for obtaining high-quality activated carbon from COS and contributed to sustainable development strategies.

Drying kinetics of camellia oleifera seeds under hot air drying with ultrasonic pretreatment

Camellia oleifera seeds with high moisture content are prone to decay, leading to oil rancidity and seriously affecting subsequent processing and tea oil quality. Thus, an efficient drying method is needed. Hot air drying with ultrasonic pretreatment is a potential drying method for camellia oleifera seeds. In this paper, the effects of key parameters such as ultrasound power, ultrasound pretreatment time, and hot air drying temperature on the moisture ratio of camellia oleifera seeds, as well as the changes in microstructure of both seed shell and seed kernel, and the main quality parameters such as peroxide value and acid value of tea oil were explored. Results showed that the shorter the ultrasound pretreatment time, the greater the ultrasound power, the higher the temperature, the faster the drying rate, and the shorter the drying time. The drying time and specific energy consumption was reduced by up to 26.7 % and 16.8 % with the ultrasonic pretreatment, respectively. The optimal ultrasonic pretreatment time is 2 min, and the ultrasonic power is 300 W. A Genetic Algorithm Optimized Backpropagation Artificial Neural Network (GA-BP-ANN) drying model was proposed to predict the changes in moisture ratio during the drying process of camellia oleifera seeds to provide guidance for the development of intelligent drying system. The experimental results showed that the proposed drying model had a good predictive performance, with an RMSE of 0.0076969 and an R2 of 99.909 %, which can accurately estimate the effect of ultrasonic pretreatment on hot air drying. The research results of this study are expected to reduce post-harvest losses of camellia oleifera fruits and provide theoretical support for the development of drying systems of camellia oleifera seeds and similar agricultural products.

CTDUNet: A Multimodal CNN-Transformer Dual U-Shaped Network with Coordinate Space Attention for Camellia oleifera Pests and Diseases Segmentation in Complex Environments.

Camellia oleifera is a crop of high economic value, yet it is particularly susceptible to various diseases and pests that significantly reduce its yield and quality. Consequently, the precise segmentation and classification of diseased Camellia leaves are vital for managing pests and diseases effectively. Deep learning exhibits significant advantages in the segmentation of plant diseases and pests, particularly in complex image processing and automated feature extraction. However, when employing single-modal models to segment Camellia oleifera diseases, three critical challenges arise: (A) lesions may closely resemble the colors of the complex background; (B) small sections of diseased leaves overlap; (C) the presence of multiple diseases on a single leaf. These factors considerably hinder segmentation accuracy. A novel multimodal model, CNN-Transformer Dual U-shaped Network (CTDUNet), based on a CNN-Transformer architecture, has been proposed to integrate image and text information. This model first utilizes text data to address the shortcomings of single-modal image features, enhancing its ability to distinguish lesions from environmental characteristics, even under conditions where they closely resemble one another. Additionally, we introduce Coordinate Space Attention (CSA), which focuses on the positional relationships between targets, thereby improving the segmentation of overlapping leaf edges. Furthermore, cross-attention (CA) is employed to align image and text features effectively, preserving local information and enhancing the perception and differentiation of various diseases. The CTDUNet model was evaluated on a self-made multimodal dataset compared against several models, including DeeplabV3+, UNet, PSPNet, Segformer, HrNet, and Language meets Vision Transformer (LViT). The experimental results demonstrate that CTDUNet achieved an mean Intersection over Union (mIoU) of 86.14%, surpassing both multimodal models and the best single-modal model by 3.91% and 5.84%, respectively. Additionally, CTDUNet exhibits high balance in the multi-class segmentation of Camellia oleifera diseases and pests. These results indicate the successful application of fused image and text multimodal information in the segmentation of Camellia disease, achieving outstanding performance.