In this paper, a three-dimensional reconstruction method, which is based on point clouds and texture images, is used to realize the visualization of leaves of greenhouse crops. We take Epipremnum aureum as the object for study and focus on applying the triangular meshing method to organize and categorize scattered point cloud input data of leaves, and then construct a triangulated surface with interconnection topology to simulate the real surface of the object. At last we texture-map the leaf surface with real images to present a life-like 3D model which can be used to simulate the growth of greenhouse plants.
The digitization of greenhouse plants is an important aspect of digital agriculture. Its ultimate aim is to reconstruct a
visible and interoperable virtual plant model on the computer by using state-of-the-art image process and computer
graphics technologies. The most prominent difficulties of the digitization of greenhouse plants include how to acquire
the three-dimensional shape data of greenhouse plants and how to carry out its realistic stereo reconstruction. Concerning
these issues an effective method for the digitization of greenhouse plants is proposed by using a binocular stereo vision
system in this paper. Stereo vision is a technique aiming at inferring depth information from two or more cameras; it
consists of four parts: calibration of the cameras, stereo rectification, search of stereo correspondence and triangulation.
Through the final triangulation procedure, the 3D point cloud of the plant can be achieved. The proposed stereo vision
system can facilitate further segmentation of plant organs such as stems and leaves; moreover, it can provide reliable
digital samples for the visualization of greenhouse tomato plants.