TY - JOUR
T1 - Evaluation of low-cost depth cameras for agricultural applications
AU - Condotta, Isabella C.F.S.
AU - Brown-Brandl, Tami M.
AU - Pitla, Santosh K.
AU - Stinn, John P.
AU - Silva-Miranda, Késia O.
N1 - Funding Information:
This work was funded in part by the USDA , Agricultural Research Service – United States; the São Paulo Research Foundation ( FAPESP ) - Brazil [grants number 2015/06414-7 and 2017/09893-9 ]; the Coordination of Improvement of Higher Education Personnel ( CAPES ) – Brazil, and by the National Council for Scientific and Technological Development ( CNPq ) – Brazil [grant number 141897/2017-1 ].
Funding Information:
All animal procedures were approved by the USMARC IACUC and followed recognized guidelines for animal use and care (, 2010). Mention of trade names or commercial products in this article is solely for the purpose of providing specific information and does not imply recommendation or endorsement by the authors. The authors would like to thank James C. Schnable for providing access to the experimental corn field, the Meat Animal Research Center for providing access to their facilities; and John Holman, Nathan Olsufka, Brooke Compton, and Hessan Sedaghat for helping with data acquisition. This work was funded in part by the USDA, Agricultural Research Service ? United States; the S?o Paulo Research Foundation (FAPESP) - Brazil [grants number 2015/06414-7 and 2017/09893-9]; the Coordination of Improvement of Higher Education Personnel (CAPES) ? Brazil, and by the National Council for Scientific and Technological Development (CNPq) ? Brazil [grant number 141897/2017-1].
Publisher Copyright:
© 2020 Elsevier B.V.
PY - 2020/6
Y1 - 2020/6
N2 - 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® RealSense™ 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.
AB - 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® RealSense™ 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.
KW - Depth image
KW - Stereoscopy
KW - Structured light
KW - Time-of-flight
UR - http://www.scopus.com/inward/record.url?scp=85083815276&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85083815276&partnerID=8YFLogxK
U2 - 10.1016/j.compag.2020.105394
DO - 10.1016/j.compag.2020.105394
M3 - Article
AN - SCOPUS:85083815276
SN - 0168-1699
VL - 173
JO - Computers and Electronics in Agriculture
JF - Computers and Electronics in Agriculture
M1 - 105394
ER -