Due to their rapid development and wide application in modern agriculture, robots, mobile terminals, and intelligent devices have become vital technologies and fundamental research topics for the development of intelligent and precision agriculture. Accurate and efficient target detection technology is required for mobile inspection terminals, picking robots, and intelligent sorting equipment in tomato production and management in plant factories. However, due to the limitations of computer power, storage capacity, and the complexity of the plant factory (PF) environment, the precision of small-target detection for tomatoes in real-world applications is inadequate. Therefore, we propose an improved Small MobileNet YOLOv5 (SM-YOLOv5) detection algorithm and model based on YOLOv5 for target detection by tomato-picking robots in plant factories. Firstly, MobileNetV3-Large was used as the backbone network to make the model structure lightweight and improve its running performance. Secondly, a small-target detection layer was added to improve the accuracy of small-target detection for tomatoes. The constructed PF tomato dataset was used for training. Compared with the YOLOv5 baseline model, the mAP of the improved SM-YOLOv5 model was increased by 1.4%, reaching 98.8%. The model size was only 6.33 MB, which was 42.48% that of YOLOv5, and it required only 7.6 GFLOPs, which was half that required by YOLOv5. The experiment showed that the improved SM-YOLOv5 model had a precision of 97.8% and a recall rate of 96.7%. The model is lightweight and has excellent detection performance, and so it can meet the real-time detection requirements of tomato-picking robots in plant factories.

In order to realize the intelligent online yield estimation of tomato in the plant factory with artificial lighting (PFAL), a recognition method of tomato red fruit and green fruit based on improved yolov3 deep learning model was proposed to count and estimate tomato fruit yield under natural growth state. According to the planting environment and facility conditions of tomato plants, a computer vision system for fruit counting and yield estimation was designed and the new position loss function was based on the generalized intersection over union (GIoU), which improved the traditional YOLO algorithm loss function. Meanwhile, the scale invariant feature could promote the description precision of the different shapes of fruits. Based on the construction and labeling of the sample image data, the K-means clustering algorithm was used to obtain nine prior boxes of different specifications which were assigned according to the hierarchical level of the feature map. The experimental results of model training and evaluation showed that the mean average precision (mAP) of the improved detection model reached 99.3%, which was 2.7% higher than that of the traditional YOLOv3 model, and the processing time for a single image declined to 15 ms. Moreover, the improved YOLOv3 model had better identification effects for dense and shaded fruits. The research results can provide yield estimation methods and technical support for the research and development of intelligent control system for planting fruits and vegetables in plant factories, greenhouses and fields.

Accurate, fast and lightweight dense target detection methods are highly important for precision agriculture. To detect dense apricot flowers using drones, we propose an improved dense target detection method based on YOLOv8, named D-YOLOv8. First, we introduce the Dense Feature Pyramid Networks (D-FPN) to enhance the model’s ability to extract dense features and Dense Attention Layer (DAL) to focus on dense target areas, which enhances the feature extraction ability of dense areas, suppresses features in irrelevant areas, and improves dense target detection accuracy. Finally, RAW data are used to enhance the dataset, which introduces additional original data into RAW images, further enriching the feature input of dense objects. We perform validation on the CARPK challenge dataset and constructed a dataset. The experimental results show that our proposed D-YOLOv8m achieved 98.37% AP, while the model parameters were only 13.2 million. The improved network can effectively support any task of dense target detection.

Introduction: In recent years, innovative sustainable agricultural production technologies, including vertical farms and plant factories, have been developing rapidly around the world. The development of plant factories and vertical farms is currently receiving a lot of attention from Chinese academia and industry. However, the recognition and satisfaction of the government, producers, sales companies, and consumers are low, and their attitudes are mixed, mainly due to high pre-construction and post-operation costs, low comprehensive utilization of resources, low product diversity, low market share, high prices, and low core competitiveness, which limit its healthy and sustainable development. This paper designed a questionnaire from the perspectives of industrialization, commercialization, and sustainability in order to understand the respondents' level of awareness, doubts and concerns, purchase intentions and consumption expectations, as well as their trust and recognition of branded products in this new agricultural production system.Method: To determine the diversity of respondents, this paper examines the group structure of participants from management, research and development, manufacturing, sales, consumers, regional development, and other industrial sectors. The survey was conducted using both face-to-face interviews and electronic questionnaires. As an online survey, the questionnaire was distributed to social groups through social media platforms. A total of 729 valid questionnaires were submitted. For the purposes of categorizing, enumerating, compiling statistics, and analyzing the questionnaires used in this study, descriptive statistics, multi-factor cross-analysis, and other statistical methods were employed. The social roles, functions, and interaction styles of various plant factory practitioners are examined from the perspective of social relationships, and pertinent development concepts and suggestions are proposed based on the survey results.Results and conclusions: The study found that an increasing number of consumers are understanding and accepting this new form of plant production and are willing to purchase plant products from plant factories and vertical farming. Plant factories and vertical farms are widely regarded as one of the most important methods of future urban agricultural production. Awareness, purchase intent, price expectations, brand awareness, and price expectations of plant factories and vertical farms varied significantly by gender, age, education level, occupation, and income. In addition, there are numerous findings that provide governments, producers, marketers, managers, and consumers with great value and assistance.Development recommendations: We should take the opportunity of developing plant factories to adjust the structure of the plant industry, enrich the “vegetable basket” of urban residents, increase the supply capacity of the market, enhance agricultural modernization and technological innovation, improve the quality of agricultural products from plant factories, strengthen the brand sales of plant products, and develop more functional plant products with high added value. Through the development of plant factories and vertical farms, we can improve the nutrition and healthy diet structure of citizens' diets, increase the modern plant industry's contribution to the national economy, and promote the comprehensive and sustainable development of the urban productive plant industry.

Plant factories are an advanced form of facility agriculture that enable efficient plant cultivation through controllable environmental conditions, making them highly suitable for the automation and intelligent application of machinery. Tomato cultivation in plant factories has significant economic and agricultural value and can be utilized for various applications such as seedling cultivation, breeding, and genetic engineering. However, manual completion is still required for operations such as detection, counting, and classification of tomato fruits, and the application of machine detection is currently inefficient. Furthermore, research on the automation of tomato harvesting in plant factory environments is limited due to the lack of a suitable dataset. To address this issue, a tomato fruit dataset was constructed for plant factory environments, named as TomatoPlantfactoryDataset, which can be quickly applied to multiple tasks, including the detection of control systems, harvesting robots, yield estimation, and rapid classification and statistics. This dataset features a micro tomato variety and was captured under different artificial lighting conditions, including changes in tomato fruit, complex lighting environment changes, distance changes, occlusion, and blurring. By facilitating the intelligent application of plant factories and the widespread adoption of tomato planting machinery, this dataset can contribute to the detection of intelligent control systems, operation robots, and fruit maturity and yield estimation. The dataset is publicly available for free and can be utilized for research and communication purposes.

Accurate identification of tomato ripeness and precise detection of picking points is the key to realizing automated picking. Aiming at the problems faced in practical applications, such as low accuracy of tomato ripeness and picking points detection in complex greenhouse environments, which leads to wrong picking, missed picking, and fruit damage by robots, this study proposes the YOLO-TMPPD (Tomato Maturity and Picking Point Detection) model. YOLO-TMPPD is structurally improved and algorithmically optimized based on the YOLOv8 baseline architecture. Firstly, the Depthwise Convolution (DWConv) module is utilized to substitute the C2f module within the backbone network. This substitution not only cuts down the model’s computational load but also simultaneously enhances the detection precision. Secondly, the Content-Aware ReAssembly of FEatures (CARAFE) operator is utilized to enhance the up-sampling operation, enabling precise content-aware processing of tomatoes and picking keypoints to improve accuracy and recall. Finally, the Convolutional Attention Mechanism (CBAM) module is incorporated to enhance the model’s ability to detect tomato-picking key regions in a large field of view in both channel and spatial dimensions. Ablation experiments were conducted to validate the effectiveness of each proposed module (DWConv, CARAFE, CBAM), and the architecture was compared with YOLOv3, v5, v6, v8, v9, and v10. The experimental results reveal that, when juxtaposed with the original network model, the YOLO-TMPPD model brings about remarkable improvements. Specifically, it improves the object detection F1 score by 4.48% and enhances the keypoint detection accuracy by 4.43%. Furthermore, the model’s size is reduced by 8.6%. This study holds substantial theoretical and practical value. In the complex environment of a greenhouse, it contributes significantly to computer-vision-enabled detection of tomato ripening. It can also help robots accurately locate picking points and estimate posture, which is crucial for efficient and precise tomato-picking operations without damage.