Impact of Camera Viewing Angle for Estimating Leaf Parameters of Wheat Plants from 3D Point Clouds

Estimation of plant canopy using low-altitude imagery can help monitor the normal growth status crops and is highly beneficial for various digital farming applications such as precision crop protection. However, extracting 3D information from raw images requires studying effect sensor viewing angle by taking into accounts limitations mobile platform routes inside field. The main objective this research was to estimate wheat (Triticum aestivum L.) leaf parameters, including length width, model representation plants. For purpose, experiments with different camera angles were conducted find optimum setup a mono-camera system that would result in best point clouds. angle-control analytical study on four-row plot row spacing 0.17 m two seeding densities stages factors. Nadir six oblique view image datasets acquired 88% overlapping then reconstructed clouds Structure Motion (SfM) Multi-View Stereo (MVS) methods. Point first categorized three classes canopy, soil background, experimental plot. class used extract which compared those values manual measurements. comparison between results showed (i) multiple-view dataset provided estimation (ii) among single-view dataset, parameters modeled vertically at ?45° horizontally 0° (VA ?45, HA 0), while (iii) nadir view, fewer underlying points obtained missing rate 70%. It concluded promising approach effectively SfM-MVS single monitoring. This contributes improvement proximal sensing health assessment.