Kinect v2 sensor-based mobile terrestrial laser scanner for agricultural outdoor applications
MetadataShow full item record
Mobile terrestrial laser scanners (MTLS), based on light detection and ranging (LiDAR) sensors, are used worldwide in agricultural applications. MTLS are applied to characterize the geometry and the structure of plants and crops for technical and scientific purposes. Although MTLS exhibit outstanding performance, their high cost is still a drawback for most agricultural applications. This paper presents a low-cost alternative to MTLS based on the combination of a Kinect v2 depth sensor and a Real Time Kinematic (RTK) global navigation satellite system (GNSS) with extended color information capability. The theoretical foundations of this system are exposed along with some experimental results illustrating their performance and limitations. This work is focused on open-field agricultural applications, although most conclusions can also be extrapolated to similar outdoor uses. The developed Kinect-based MTLS (K2-MTLS) system allows to select different acquisition frequencies and fields of view (FOV), from one to 512 vertical slices. The authors conclude that the better performance is obtained when a FOV of a single slice is used, but at the price of a very low measuring speed. With that particular configuration, plants, crops, and objects are reproduced accurately. Future efforts will be directed to increase the scanning efficiency by improving both the hardware and software components and to make it feasible using both partial and full FOV.
Is part ofIEEE-Asme Transactions on Mechatronics, 2017, vol. 22, núm. 6, p. 2420 - 2427
European research projects
Showing items related by title, author, creator and subject.
Sanz Cortiella, Ricardo; Llorens Calveras, Jordi; Escolà i Agustí, Alexandre; Arnó Satorra, Jaume; Ribes Dasi, Manuel; Masip Vilalta, Joan; Camp, Ferran; Gràcia Aguilà, Felipe José; Solanelles Batlle, Francesc; Planas de Martí, Santiago; Pallejà Cabrè, Tomàs; Palacín Roca, Jordi; Gregorio López, Eduard; Del Moral Martínez, Ignacio; Rosell Polo, Joan Ramon (Molecular Diversity Preservation International (MDPI), 2011)In this work, a LIDAR-based 3D Dynamic Measurement System is presented and evaluated for the geometric characterization of tree crops. Using this measurement system, trees were scanned from two opposing sides to obtain two ...
Gené Mola, Jordi; Llorens Calveras, Jordi; Rosell Polo, Joan Ramon; Gregorio López, Eduard; Arnó Satorra, Jaume; Solanelles Batlle, Francesc; Martínez Casasnovas, José Antonio; Escolà i Agustí, Alexandre (Universitat de Lleida, 2020-11)The Kinect Evaluation in Orchard conditions (KEvOr) dataset is comprised of a set of RGB-D captures carried out with the Microsoft Kinect v2 to evaluate the performance of this sensor at different lighting conditions in ...
Assessing the Performance of RGB-D Sensors for 3D Fruit Crop Canopy Characterization under Different Operating and Lighting Conditions Gené Mola, Jordi; Llorens Calveras, Jordi; Rosell Polo, Joan Ramon; Gregorio López, Eduard; Arnó Satorra, Jaume; Solanelles Batlle, Francesc; Martínez Casasnovas, José Antonio; Escolà i Agustí, Alexandre (MDPI, 2020-12-10)The use of 3D sensors combined with appropriate data processing and analysis has provided tools to optimise agricultural management through the application of precision agriculture. The recent development of low-cost ...