Plant phenotypic image recognition (PPIR) is an important branch of smart agriculture. In recent years, deep learning has achieved significant breakthroughs in image recognition. Consequently, PPIR technology that is based on deep learning is becoming increasingly popular. First, this paper introduces the development and application of PPIR technology, followed by its classification and analysis. Second, it presents the theory of four types of deep learning methods and their applications in PPIR. These methods include the convolutional neural network, deep belief network, recurrent neural network, and stacked autoencoder, and they are applied to identify plant species, diagnose plant diseases, etc. Finally, the difficulties and challenges of deep learning in PPIR are discussed.

Food Science of Animal Resources (Food Sci. Anim. Resour.) is an international, peer-reviewed bimonthly journal publishing original research and reviews on basic and applied aspects of the use of animal resources including the meat, egg, dairy, and edible insect/worm products. Food Sci. Anim. Resour. is published and distributed by the Korean Society for Food Science of Animal Resources.

Background: Variable-rate fertilization is crucial in the implementation of precision agriculture and for ensuring reasonable and efficient fertilizer application and nutrient management that is tailored to local conditions. The overall goal of these technologies is to maximize grain output and minimize fertilizer input and, thus, achieve the optimal input–output production ratio. As the main form of variable-rate fertilization, real-time variable-rate control technology adjusts fertilizer application according to the growth status and nutrient information of crops and, as such, its effective application relies on the stable and accurate acquisition of crop phenotypic information. Results: Due to the relationship between crop phenotype and real-time fertilizer demand, phenotypic information has been increasingly applied in these contexts in recent years. Here, the establishment and characteristics of inversion models between crop phenotypic information and nutritional status are reviewed. The principles of real-time monitoring applications, the key technologies relating to crop phenotypic biological parameters, and the existing challenges for real-time variable-rate fertilization technology are also evaluated. Future research directions are then discussed in the specific context of the need for sustainable development of modern agriculture in China. Conclusion: This paper provides a theoretical reference for the construction of scientific management technology systems aimed at reducing fertilizer application and maximizing output, and for the development of relevant technologies in the specific context of China.

Plant morphological data are an important basis for precision agriculture and plant phenomics. The three-dimensional (3D) geometric shape of plants is complex, and the 3D morphology of a plant changes relatively significantly during the full growth cycle. In order to make high-throughput measurements of the 3D morphological data of greenhouse plants, it is necessary to frequently adjust the relative position between the sensor and the plant. Therefore, it is necessary to frequently adjust the Kinect sensor position and consequently recalibrate the Kinect sensor during the full growth cycle of the plant, which significantly increases the tedium of the multiview 3D point cloud reconstruction process. A high-throughput 3D rapid greenhouse plant point cloud reconstruction method based on autonomous Kinect v2 sensor position calibration is proposed for 3D phenotyping greenhouse plants. Two red–green–blue–depth (RGB-D) images of the turntable surface are acquired by the Kinect v2 sensor. The central point and normal vector of the axis of rotation of the turntable are calculated automatically. The coordinate systems of RGB-D images captured at various view angles are unified based on the central point and normal vector of the axis of the turntable to achieve coarse registration. Then, the iterative closest point algorithm is used to perform multiview point cloud precise registration, thereby achieving rapid 3D point cloud reconstruction of the greenhouse plant. The greenhouse tomato plants were selected as measurement objects in this study. Research results show that the proposed 3D point cloud reconstruction method was highly accurate and stable in performance, and can be used to reconstruct 3D point clouds for high-throughput plant phenotyping analysis and to extract the morphological parameters of plants.

Measurement of plant nitrogen (N), phosphorus (P), and potassium (K) levels are important for determining precise fertilization management approaches for crops cultivated in greenhouses. To accurately, rapidly, stably, and nondestructively measure the NPK levels in tomato plants, a nondestructive determination method based on multispectral three-dimensional (3D) imaging was proposed. Multiview RGB-D images and multispectral images were synchronously collected, and the plant multispectral reflectance was registered to the depth coordinates according to Fourier transform principles. Based on the Kinect sensor pose estimation and self-calibration, the unified transformation of the multiview point cloud coordinate system was realized. Finally, the iterative closest point (ICP) algorithm was used for the precise registration of multiview point clouds and the reconstruction of plant multispectral 3D point cloud models. Using the normalized grayscale similarity coefficient, the degree of spectral overlap, and the Hausdorff distance set, the accuracy of the reconstructed multispectral 3D point clouds was quantitatively evaluated, the average value was 0.9116, 0.9343 and 0.41 cm, respectively. The results indicated that the multispectral reflectance could be registered to the Kinect depth coordinates accurately based on the Fourier transform principles, the reconstruction accuracy of the multispectral 3D point cloud model met the model reconstruction needs of tomato plants. Using back-propagation artificial neural network (BPANN), support vector machine regression (SVMR), and gaussian process regression (GPR) methods, determination models for the NPK contents in tomato plants based on the reflectance characteristics of plant multispectral 3D point cloud models were separately constructed. The relative error (RE) of the N content by BPANN, SVMR and GPR prediction models were 2.27%, 7.46% and 4.03%, respectively. The RE of the P content by BPANN, SVMR and GPR prediction models were 3.32%, 8.92% and 8.41%, respectively. The RE of the K content by BPANN, SVMR and GPR prediction models were 3.27%, 5.73% and 3.32%, respectively. These models provided highly efficient and accurate measurements of the NPK contents in tomato plants. The NPK contents determination performance of these models were more stable than those of single-view models.