Method for the navigation line recognition of the ridge without crops via machine vision

Some agriculture machinery like the transplanter,needs to operate by following the crop-free ridges.In order to improve working efficiency and quality,some autonomous navigation systems were developed and applied to ridge-following machinery.At present,agricultural navigation systems are mainly the satellite navigation system and the machine vision system.The satellite navigation system is difficult to apply to the machinery that needs to work by following the ridge because it cannot distinguish the shape of the navigated ridge and guide the machinery working along the ridge.In this study,697 cloudy ridge images and 235 sunny ridge images were taken in the field,and these images were used as the dataset.Moreover,a machine vision navigation method based on the color of ridges was proposed.Firstly,the regions of interest(ROI)in the ridge image were extracted according to the reaction time and the forward speed of the machine.Then,a gray reconstruction method was used to enlarge the color difference between the ridge and the furrow.The optimal threshold for the gray image segmenting was calculated real-timely by using the threshold segmentation method.Then,based on the contour detection method,the ridge contour which was not surrounded by holes was extracted.Finally,the approximate quadrilateral method was proposed to recognize the ridge center line as the navigation line.The method proposed in this study was verified by four types of ridges with different colors and textures.The experimental results showed that the recognition success rates of the light ridge,the dark ridge,the film-covered ridge,and the sunny ridge were 100%,97.5%,100%,and 98.7%,respectively.The recognition success rate of the proposed method was at least 8%higher than that of the existing ridge-furrow recognition methods.The results indicate that this method can effectively realize navigation line recognition.This method can provide technical support for the autonomous navigation of agricultural machinery,such as transplanters,seeders,etc.,operating on the ridge without crops.

Navigation algorithm based on semantic segmentation in wheat fields using an RGB-D camera

Determining the navigation line is critical for the automatic navigation of agricultural robots in the farmland.In this research,considering a wheat field as the typical scenario,a novel navigation line extraction algorithm based on semantic segmentation is proposed.The data containing horizontal parallax,height,and grayscale information(HHG)is constructed by combining re-encoded depth data and red-green-blue(RGB)data.The HHG,RGB,and depth data are used to achieve scene recognition and navigation line extraction for a wheat field.The method includes two main steps.First,the semantic segmentation of the wheat,ground,and background are performed using a fully convolutional network(FCN).Second,the navigation line is fitted in the camera coordinate system on the basis of the semantic segmentation result and the principle of camera pinhole imaging.Our segmentation model is trained using 508 randomly selected images from a data set,and the model is tested on 199 images.When labelled data are used as the reference benchmark,the mean intersection over union(mIoU)of the HHG data is greater than 95%,which is the highest among the three types of data.The semantic segmentation methods based on the RGB and HHG data show higher navigation line extraction accuracy rates(with the absolute value of the angle deviation less than 5)than the compared methods.The mean and standard deviation of the angle deviation of the two methods are within 0.1and 2.0,while the mean and standard deviation of the distance deviation are less than 30 mm and 60 mm,respectively.These values meet the basic requirements of agricultural machinery field navigation.The novelty of this work is the proposal of a navigation line extraction algorithm based on semantic segmentation in wheat fields.This method is high in accuracy and robustness to interference from crop occlusion.

Ideal proportional navigation for exoatmospheric interception

Ideal proportional navigation （IPN） is a natural choice for exoatmospheric interception for its mighty capture capability and ease of implementation. The closed-form solution of two- dimensional ideal proportional navigation was conducted in previous public literature, whereas the practical interception happens in the three-dimensional space. A novel set of relative dynamic equations is adopted in this paper, which is with the advantage of decoupling relative motion in the instantaneous rotation plane of the line of sight from the rotation of this plane. The dimension-reduced IPN is constructed in this instantaneous plane, which functions as a three-dimensional guidance law. The trajectory features of dimension-reduced IPN are explored, and the capture regions of dimension-reduced IPN with limited acceleration against nonmaneuvering and maneuvering targets are analyzed by using phase plane method. It is proved that the capture capability of IPN is much stronger than true proportional navigation （TPN）, no matter the target maneuvers or not. Finally, simulation results indicate that IPN is more effective than TPN in exoatmospheric interception scenarios.