No abstract

No abstract

In this paper is described the starting of a research activity to define measurement tecniques and instruments for analyzing the shape of an olive tree in order to obtain the most interesting geometric characteristics, such as stem diameter, branch direction and crown volume. After an introduction to possible non-contact measurement systems applied till now to trees, we have choose two of them: one based on laser scanner and the other based on structured light. Both as been used to performed measurements on a test case: an olive tree. Data processing and comparision is illustrated.

This paper presents a comparison of different methodologies for monitoring the plants growth in a greenhouse. A 2D measurement based on Computer Vision algorithms and 3D shape measurements techniques (Structured light, LIDAR and photogrammetry) are compared. From the joined 2D and 3D data, an analysis was performed considering health plant indicators. The methodologies are compared among each other. The acquired data are then fed into Deep Learning algorithms in order to detect anomalies in plant growth. The final aim is to give an assessment on the image acquisition methodologies, selecting the most suitable to be used to create the Deep Learning model inputs saving time and resources.

<p>In this work the performances of three different techniques for 3D scanning have been investigated. In particular two commercial tools (smartphone camera and iPad Pro LiDAR) and a structured light scanner (Go!SCAN 50) have been used for the analysis. First of all, two different subjects have been scanned with the three different techniques and the obtained 3D model were analysed in order to evaluate the respective reconstruction accuracy. A case study involving a child was then considered, with the main aim of providing useful information on performances of scanning techniques for clinical applications, where boundary conditions are often challenging (i.e., non-collaborative patient). Finally, a full procedure for the 3D reconstruction of a human shape is proposed, in order to setup a helpful workflow for clinical applications.</p>