Search

To meet the needs of precision agriculture for crop location information, to achieve accurate plant position of crops, and to solve the problem of low resource utilization rate and high operation cost caused by repeated identification and positioning of plants in each part of field management, a seed positioning method was proposed by using maize planting as research object. A 4-row precision planter was used, all seed tubes were replaced with optoelectronic sensor (OE-sensor) equipped tubes to monitor seeds dropping. An RTK satellite receiver mounted on seeder frame girder provided global position. Furthermore, time and distance compensation model of seed from OE-sensor to implantation process was established based on EDEM numerical simulation. Seeds implantation location prediction and actual position measurement data acquisition programs were developed. Field test results showed that the mean, range and standard deviations (SD) of the longitudinal deviation between prediction location and actual position in operation direction were greater than vertical deviation which is perpendicular to operation direction. 87.7% of corn seeds dropped within 50mm from prediction location at operating speed of 3.2 km/h. This method can provide theoretical reference for synchronous generation of seed map in seeding process.

In this paper, a path recognition method for agricultural robot vision navigation under weed environment is proposed. The vision navigation is based on color images sampled by a high speed camera. First, the crop and weed information is extracted using an appropriate color feature model to separate the green crop from background; then the image is thresholded, and the noise caused by weed is filtered by deleting small-area objects in the image; the navigation path is extracted through Hough transformation. Experiments are carried out in corn seedling field, and results show that the method can recognize navigation path correctly under weed environment.