To reduce the cost of production and the pollution of the environment that is due to the overapplication of herbicide in paddy fields, the location information of rice seedlings and weeds must be detected in site-specific weed management (SSWM). With the development of deep learning, a semantic segmentation method with the SegNet that is based on fully convolutional network (FCN) was proposed. In this paper, RGB color images of seedling rice were captured in paddy field, and ground truth (GT) images were obtained by manually labeled the pixels in the RGB images with three separate categories, namely, rice seedlings, background, and weeds. The class weight coefficients were calculated to solve the problem of the unbalance of the number of the classification category. GT images and RGB images were used for data training and data testing. Eighty percent of the samples were randomly selected as the training dataset and 20% of samples were used as the test dataset. The proposed method was compared with a classical semantic segmentation model, namely, FCN, and U-Net models. The average accuracy rate of the SegNet method was 92.7%, whereas the average accuracy rates of the FCN and U-Net methods were 89.5% and 70.8%, respectively. The proposed SegNet method realized higher classification accuracy and could effectively classify the pixels of rice seedlings, background, and weeds in the paddy field images and acquire the positions of their regions.

Recognizing rice seedling growth stages to timely do field operations, such as temperature control, fertilizer, irrigation, cultivation, and disease control, is of great significance of crop management, provision of standard and well-nourished seedlings for mechanical transplanting, and increase of yield. Conventionally, rice seedling growth stage is performed manually by means of visual inspection, which is not only labor-intensive and time-consuming, but also subjective and inefficient on a large-scale field. The application of machine learning algorithms on UAV images offers a high-throughput and non-invasive alternative to manual observations and its applications in agriculture and high-throughput phenotyping are increasing. This paper presented automatic approaches to detect rice seedling of three critical stages, BBCH11, BBCH12, and BBCH13. Both traditional machine learning algorithms and deep learning algorithms were investigated the discriminative ability of the three growth stages. UAV images were captured vertically downward at 3-m height from the field. A dataset consisted of images of three growth stages of rice seedlings for three cultivars, five nursing seedling densities, and different sowing dates. In the traditional machine learning algorithm, histograms of oriented gradients (HOGs) were selected as texture features and combined with the support vector machine (SVM) classifier to recognize and classify three growth stages. The best HOG-SVM model obtained the performance with 84.9, 85.9, 84.9, and 85.4% in accuracy, average precision, average recall, and F1 score, respectively. In the deep learning algorithm, the Efficientnet family and other state-of-art CNN models (VGG16, Resnet50, and Densenet121) were adopted and investigated the performance of three growth stage classifications. EfficientnetB4 achieved the best performance among other CNN models, with 99.47, 99.53, 99.39, and 99.46% in accuracy, average precision, average recall, and F1 score, respectively. Thus, the proposed method could be effective and efficient tool to detect rice seedling growth stages.

High amount of corn (Zea mays L.) residue left in the field interferes with seeding operations, which hinders the viability of conservation agriculture. Vertical tillage is a promising practice in dealing with heavy crop residue, but its effectiveness largely depends on the design and use of tillage machines. In this study, three vertical tillage discs with different shapes, namely notched, plain, and rippled, were tested in a soil bin at two different working depths, shallow (63.5 mm) and deep (127 mm). Corn residues were spread on top of the soil as surface residue. soil cutting forces, soil displacement, and residue mixing with soil, as well as residue cutting were measured. The results showed that the working depth had a stronger effect on the performance of discs as compared to the disc type. No difference in residue cutting was found between the treatments. The deep working depth resulted in 5.1% higher residue mixing, 53.4% greater soil cutting forces, and 34.9% larger soil displacements, as compared to the shallow depth. The rippled disc resulted in the largest soil displacements with the greatest demand in soil cutting forces. Overall, the rippled disc was the most aggressive among the three discs with regard to the performance indicators measured. The results suggested that varying working depth would be an effective approach in changing the soil dynamics and residue cutting performance of the discs for vertical tillage.

The discrete element method (DEM) for modeling the behavior of particulate material is highly dependent on the use of appropriate and accurate parameters. In this study, a seed metering DEM simulation was used to measure, calibrate, and verify the physical and interactional parameters of rapeseed. The coefficients of restitution and static friction between rapeseeds and three common materials (aluminum alloy, acrylic, and high-density polyethylene) were measured using free drop and sliding ramp tests, respectively. The angle of repose was determined using a hollow cylinder experiment, which was duplicated using a DEM simulation, to examine the effects of static and rolling friction coefficients on the angle of repose. Response surface optimization was performed to determine the optimized model parameters using a Box–Behnken design test. A metering device was made with three materials, and rapeseed seeding was simulated at different working speeds to verify the calibrated parameters. The validation results showed that the relative errors between the seed metering model and experiments for the single qualified seeding, missed seeding, and multiple seeding rates were −0.15%, 3.29%, and 5.37%, respectively. The results suggest that the determined physical and interactional parameters of rapeseed can be used as references for future DEM simulations.

Automatic and efficient plant leaf geometry parameter measurement offers useful information for plant management. The objective of this study was to develop an efficient and effective leaf geometry parameter measurement system based on the Android phone platform. The Android mobile phone was used to process and measure geometric parameters of the leaf, such as length, width, perimeter, and area. First, initial leaf images were pre-processed by some image algorithms, then distortion calibration was proposed to eliminate image distortion. Next, a method for calculating leaf parameters by using the positive circumscribed rectangle of the leaf as a reference object was proposed to improve the measurement accuracy. The results demonstrated that the test distances from 235 to 260 mm and angles from 0 to 45 degrees had little influence on the leafs’ geometric parameters. Both lab and outdoor measurements of leaf parameters showed that the developed method and the standard method were highly correlated. In addition, for the same leaf, the results of different mobile phone measurements were not significantly different. The leaf geometry parameter measurement system based on the Android phone platform used for this study could produce high accuracy measurements for leaf geometry parameters.