Evaluation of low-cost depth cameras for agricultural applications

Autor(es)

Condotta, Isabella C. F. S. ^{[1, 2, 3]} ; Brown-Brandl, Tami M. ^{[4, 1]} ; Pitla, Santosh K. ^[1] ; Stinn, John P. ^[5] ; Silva-Miranda, Kesia O. ^[2]

Afiliação do(s) autor(es)

^[1] Univ Nebraska, Biol Syst Engn Dept, 3605 Fair St, Lincoln, NE 68503 - USA

^[2] Univ Sao Paulo, Luiz de Queiroz Coll Agr, Biosyst Engn Dept, Av Padua Dias 11, Piracicaba 13418900, SP - Brazil

^[3] Univ Illinois, Anim Sci Dept, 1207 West Gregory Dr, Urbana, IL 61801 - USA

^[4] ARS, USDA, US Meat Anim Res Ctr, PO 166, Clay Ctr, NE 68933 - USA

^[5] Iowa Select Farms, 811 South Oak, Iowa Falls, IA 50126 - USA

• Tipo de documento: Artigo Científico
• Fonte: COMPUTERS AND ELECTRONICS IN AGRICULTURE; v. 173, JUN 2020.
• Citações Web of Science: 0

Resumo

Low-cost depth-cameras have been used in many agricultural applications with reported advantages of low cost, reliability and speed of measurement. However, some problems were also reported and seem to be technology-related, so understanding the limitations of each type of depth camera technology could provide a basis for technology selection and the development of research involving its use. The cameras use one or a combination of two of the three available technologies: structured light, time-of-flight (ToF), and stereoscopy. The objectives were to evaluate these different technologies for depth sensing, including measuring accuracy and repeatability of distance data and measurements at different positions within the image, and cameras usefulness in indoor and outdoor settings. Then, cameras were tested in a swine facility and in a corn field. Five different cameras were used: (1) Microsoft Kinect v.1, (2) Microsoft Kinect v.2, (3) Intel (R) RealSense (TM) Depth Camera D435, (4) ZED Stereo Camera (StereoLabs), and (5) CamBoard Pico Flexx (PMD Technologies). Results indicate that there were significant camera to camera differences for ZED Stereo Camera and Kinect v.1 camera (p < 0.05). All cameras showed an increase in the standard deviation as the distance between camera and object increased; however, the Intel RealSense camera had a larger increase. Time-of-flight cameras had the smallest error between different sizes of objects. Time-of-flight cameras had non-readable zones on the corners of the images. The results indicate that the ToF technology is the best to be used for indoor applications and stereoscopy is the best technology for outdoor applications. (AU)

• Processo FAPESP: 17/09893-9 - Melhorando o desempenho de matrizes suínas por meio da detecção precoce de claudicação e de alterações no escore de condição corporal
• Beneficiário: Isabella Cardoso Ferreira da Silva Condotta
• Modalidade de apoio: Bolsas no Brasil - Doutorado