This study introduces an image processing method capable of performing real-time detection of two kinds of weeds in the rice fields of the Vietnamese Mekong Delta (VMD). Two image processing methods were applied and compared in this research: Faster region-based convolutional neural network (R-CNN) and bounding blob analysis. The input images were recorded using a red, green, and blue (RGB) camera. The weeds detection accuracy and processing time were estimated for each method using the same image source data from Vietnam. Both methods were able to detect narrow-leaf and broadleaf weeds on the weed post-emergence stage under uncontrolled light conditions in the rice fields. The results show that bounding blob analysis is simple but effective, with a shorter processing time and higher accuracy than Faster R-CNN.

This study offers knowledge and techniques to resolve the problem of labor shortage in grafted seedling production during the busy season. The success of the most marketed grafting machine depends on the size and joining ability of the seedlings used for grafting. Therefore, we focused here, on developing coherent devices that can be used from the seeding to curing stages. We propose a method to cut a stem without its refuge using a clamp. In addition, we developed a nursery chamber for artificial environment control. Through static system identification, temperature and humidity could be controlled independently using an interference system. Therefore, the seedlings for grafting were obtained within the nursery chamber itself. Subsequently, the seedlings were cut and joined for processing. However, a gap was observed at the center of the cut stems. It is essential to bring about improvements in both the nursery and sorting techniques to increase the success of grafting, and we believe our method contributes to this goal.

A rubber crawler system of combine harvester works well in wet paddy fields, and designers have taken mobility, safety, and comfort into consideration while developing the machine. The track roller arrangement requires smooth turnability, especially with regard to mobility. In this study, a turning dynamic model for a combine harvester with four degrees of freedom (vertical, pitch, roll, and anteroposterior direction) was developed. In addition, the validity of the model was verified through experiment, and simulation of the turning behavior of various track roller arrangements was done. As a result, the turning performance can be evaluated by this method when traveling on a rigid flat road. Furthermore, the greatest mobility was achieved when the track roller arrangement was concentrated near the center of gravity.

In this study, the terrain images captured in front of a tractor using a stereo-vision camera were reconstructed in three dimensions (3D). A stereo-vision camera was installed in various arrangements to verify the influence of its position and angle on accuracy of 3D-reconstruction. The obtained images were converted into 3D space information through image processing methods in using Matlab. The accuracy of the reconstructed ground was evaluated by comparison between actual and reconstructed ground height onto which left and right tractor wheels passed every 0.5 m. The root mean square error (RMSE) of the extracted tractor path’s height (between the reconstructed ground and the actual ground) was approximately 1.3-2.1 cm. The overall RMSE of the ground captured by the stereo-vision camera, which was tilted at 20° and mounted onto the upper side of the tractor weight, had the highest accuracy.

Electrification technologies that are prevalent in HEVs, EVs, and FCEVs are not common in the case of farm machinery. The purpose of this study is to investigate the power consumption and energy efficiency of motor-driven farm machinery to clarify the advantages of their electrification. Therefore, a motor-driven rotary tiller was developed and examined in field and motor bench tests.

The results of the tests showed that the motor-driven rotary tiller hardly stalled because the load adjustment was quick and motor rotation speed was stable. Moreover, it instantly achieved high torque at low speeds. The energy efficiency exceeded 80 % in the field test, and the use of an electric motor reduced energy costs by 43 % compared to using diesel.