Autonomous detection of crop rows based on adaptive multi-ROI in maize fields

Crop rows detection in maize fields remains a challenging problem due to variation in illumination and weeds interference under field conditions.This study proposed an algorithm for detecting crop rows based on adaptive multi-region of interest(multi-ROI).First,the image was segmented into crop and soil and divided into several horizontally labeled strips.Feature points were located in the first image strip and initial ROI was determined.Then,the ROI window was shifted upward.For the next image strip,the operations for the previous strip were repeated until multiple ROIs were obtained.Finally,the least square method was carried out to extract navigation lines and detection lines in multi-ROI.The detection accuracy of the method was 95.3%.The average computation time was 240.8 ms.The results suggest that the proposed method has generally favorable performance and can meet the real-time and accuracy requirements for field navigation.

Accurate crop row recognition of maize at the seedling stage using lightweight network

Accurate extraction of crop row is very important for automation of agricultural production.Crop rows are required for accurate machine guidance in agricultural production such as fertilization,plant protection,weeding and harvesting.In this study,an efficient crop row detection algorithm called Crop-BiSeNet V2 was proposed,which combined BiSeNet V2 with a spatial convolutional neural network.The proposed Crop-BiSeNet V2 detected crop rows in color images without the use of threshold and other pre-information such as number of rows.A data set had 2697 maize crop images was constructed in challenging field trial conditions such as variable light,shadows,presence of weeds,and irregular crop shape.The proposed system was experimentally determined to overcome the interference of different complex scenes.And it can be applied to crop rows of different numbers,straight lines and curves.Different analyses were performed to check the robustness of the algorithm.Comparing this algorithm with the Fully Convolutional Networks(FCN)algorithm,it exhibited superior performance and saved 84.85 ms.The accuracy rate reached 0.9811,and the detection speed reached 65.54 ms/frame.The Crop-BiSeNet V2 algorithm proposed in this study show strong generalization performance for seedling crop row recognition.It provides high-reliability technical support for crop row detection research and assists in the study of intelligent field operation machinery navigation.

Natural and anthropogenic rates of soil erosion

Regions of land that are brought into crop production from native vegetation typically undergo a period of soil erosion instability,and long term erosion rates are greater than for natural lands as long as the land continues being used for crop production.Average rates of soil erosion under natural,non-cropped conditions have been documented to be less than 2 Mg ha^(-1) yr^(-1).On-site rates of erosion of lands under cultivation over large cropland areas,such as in the United States,have been documented to be on the order of6 Mg ha^(-1) yr^(-1)or more.In northeastern China,lands that were brought into production during the last century are thought to have average rates of erosion over this large area of as much as 15 Mg ha^(-1) yr^(-1) or more.Broadly applied soil conservation practices,and in particular conservation tillage and no-till cropping,have been found to be effective in reducing rates of erosion,as was seen in the United States when the average rates of erosion on cropped lands decreased from on the order of 9Mg ha^(-1) yr^(-1) to 6 or 7Mg ha^(-1) yr^(-1) between 1982 and 2002,coincident with the widespread adoption of new conservation tillage and residue management practices.Taking cropped lands out of production and restoring them to perennial plant cover,as was done in areas of the United States under the Conservation Reserve Program,is thought to reduce average erosion rates to approximately 1 Mg ha^(-1) yr^(-1) or less on those lands.