Muddy irrigation ditch understanding for agriculture environmental monitoring

Abstract

Understanding an irrigation ditch plays an important role in intelligent agriculture environmental monitoring, especially in field environments where large chunks of ditches are particularly covered by various types of natural unstructured soil, vegetation and weeds. However, due to the diverse and unstructured muddy ditches, understanding them remains a challenge. Traditional approaches of understanding a scene from three-dimensional (3D) point clouds or multi-sensor fusion are energy intensive and computationally complex, making them quite laborious in application on a resource-constrained system. In this study, we propose a methodology to understand irrigation ditches and reconstruct them in a 3D scene, using only a resource-constrained monocular camera, without prior training. Spatial similar textures projections are extracted and clustered. Through geometric constraints of distribution and orientation, similar texture projections are refined and their corresponding surfaces are shaped. By contours and evidence lines, the ditch bottom surfaces are represented. Thus an irrigation ditch can be understood and reconstructed in a 3D environment, which can be used in agricultural automatic control system, agricultural robots, and precise agriculture. Unlike machine learning-based algorithms, the proposed method requires no prior training nor knowledge of the camera’s internal parameters such as focal length, field angle, and aperture. Additionally, pure geometric features make the presented method robust to varying illumination and colour. The percentage of incorrectly classified pixels was compared to the ground truth. Experimental results demonstrated that the approach can successfully elucidate irrigation ditches, meeting requirements in safety monitoring in an agriculture environment.