Towards In-Field Phenotyping Exploiting Differentiable Rendering with Self-Consistency Loss. Magistri, F., Chebrolu, N., Behley, J., & Stachniss, C. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 13960–13966, May, 2021. ISSN: 2577-087Xdoi abstract bibtex In modern agriculture, measuring phenotypic traits helps breeders monitor plant growth, increase yield, and provide food, feed, and fiber. Traditional phenotyping requires intensive manual work, partially being intrusive. In this paper, we investigate the challenge of measuring phenotypic traits in an automated fashion through mobile robots operating in field environments. In particular, we want to measure plants from images acquired by mobile robots instead of using data from a static scanning environment. We propose to use a differentiable rendering approach to deform a generic 3D template of a plant to fit the observation recorded by a robot while ensuring a coherent deformation of the plant template. The experiments presented in this paper suggest that our approach allows for 3D reconstruction of different plant species at different growth stages using single images. From that model, we can compute important phenotypic traits, such as the leaf area index.
@inproceedings{magistri_towards_2021,
title = {Towards {In}-{Field} {Phenotyping} {Exploiting} {Differentiable} {Rendering} with {Self}-{Consistency} {Loss}},
doi = {10.1109/ICRA48506.2021.9561356},
abstract = {In modern agriculture, measuring phenotypic traits helps breeders monitor plant growth, increase yield, and provide food, feed, and fiber. Traditional phenotyping requires intensive manual work, partially being intrusive. In this paper, we investigate the challenge of measuring phenotypic traits in an automated fashion through mobile robots operating in field environments. In particular, we want to measure plants from images acquired by mobile robots instead of using data from a static scanning environment. We propose to use a differentiable rendering approach to deform a generic 3D template of a plant to fit the observation recorded by a robot while ensuring a coherent deformation of the plant template. The experiments presented in this paper suggest that our approach allows for 3D reconstruction of different plant species at different growth stages using single images. From that model, we can compute important phenotypic traits, such as the leaf area index.},
booktitle = {2021 {IEEE} {International} {Conference} on {Robotics} and {Automation} ({ICRA})},
author = {Magistri, Federico and Chebrolu, Nived and Behley, Jens and Stachniss, Cyrill},
month = may,
year = {2021},
note = {ISSN: 2577-087X},
keywords = {Atmospheric measurements, Loss measurement, Particle measurements, Performance evaluation, Plants (biology), Rendering (computer graphics), Three-dimensional displays},
pages = {13960--13966},
}
Downloads: 0
{"_id":"FPZsC82SoYdN7ZTnd","bibbaseid":"magistri-chebrolu-behley-stachniss-towardsinfieldphenotypingexploitingdifferentiablerenderingwithselfconsistencyloss-2021","author_short":["Magistri, F.","Chebrolu, N.","Behley, J.","Stachniss, C."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Towards In-Field Phenotyping Exploiting Differentiable Rendering with Self-Consistency Loss","doi":"10.1109/ICRA48506.2021.9561356","abstract":"In modern agriculture, measuring phenotypic traits helps breeders monitor plant growth, increase yield, and provide food, feed, and fiber. Traditional phenotyping requires intensive manual work, partially being intrusive. In this paper, we investigate the challenge of measuring phenotypic traits in an automated fashion through mobile robots operating in field environments. In particular, we want to measure plants from images acquired by mobile robots instead of using data from a static scanning environment. We propose to use a differentiable rendering approach to deform a generic 3D template of a plant to fit the observation recorded by a robot while ensuring a coherent deformation of the plant template. The experiments presented in this paper suggest that our approach allows for 3D reconstruction of different plant species at different growth stages using single images. From that model, we can compute important phenotypic traits, such as the leaf area index.","booktitle":"2021 IEEE International Conference on Robotics and Automation (ICRA)","author":[{"propositions":[],"lastnames":["Magistri"],"firstnames":["Federico"],"suffixes":[]},{"propositions":[],"lastnames":["Chebrolu"],"firstnames":["Nived"],"suffixes":[]},{"propositions":[],"lastnames":["Behley"],"firstnames":["Jens"],"suffixes":[]},{"propositions":[],"lastnames":["Stachniss"],"firstnames":["Cyrill"],"suffixes":[]}],"month":"May","year":"2021","note":"ISSN: 2577-087X","keywords":"Atmospheric measurements, Loss measurement, Particle measurements, Performance evaluation, Plants (biology), Rendering (computer graphics), Three-dimensional displays","pages":"13960–13966","bibtex":"@inproceedings{magistri_towards_2021,\n\ttitle = {Towards {In}-{Field} {Phenotyping} {Exploiting} {Differentiable} {Rendering} with {Self}-{Consistency} {Loss}},\n\tdoi = {10.1109/ICRA48506.2021.9561356},\n\tabstract = {In modern agriculture, measuring phenotypic traits helps breeders monitor plant growth, increase yield, and provide food, feed, and fiber. Traditional phenotyping requires intensive manual work, partially being intrusive. In this paper, we investigate the challenge of measuring phenotypic traits in an automated fashion through mobile robots operating in field environments. In particular, we want to measure plants from images acquired by mobile robots instead of using data from a static scanning environment. We propose to use a differentiable rendering approach to deform a generic 3D template of a plant to fit the observation recorded by a robot while ensuring a coherent deformation of the plant template. The experiments presented in this paper suggest that our approach allows for 3D reconstruction of different plant species at different growth stages using single images. From that model, we can compute important phenotypic traits, such as the leaf area index.},\n\tbooktitle = {2021 {IEEE} {International} {Conference} on {Robotics} and {Automation} ({ICRA})},\n\tauthor = {Magistri, Federico and Chebrolu, Nived and Behley, Jens and Stachniss, Cyrill},\n\tmonth = may,\n\tyear = {2021},\n\tnote = {ISSN: 2577-087X},\n\tkeywords = {Atmospheric measurements, Loss measurement, Particle measurements, Performance evaluation, Plants (biology), Rendering (computer graphics), Three-dimensional displays},\n\tpages = {13960--13966},\n}\n\n","author_short":["Magistri, F.","Chebrolu, N.","Behley, J.","Stachniss, C."],"key":"magistri_towards_2021","id":"magistri_towards_2021","bibbaseid":"magistri-chebrolu-behley-stachniss-towardsinfieldphenotypingexploitingdifferentiablerenderingwithselfconsistencyloss-2021","role":"author","urls":{},"keyword":["Atmospheric measurements","Loss measurement","Particle measurements","Performance evaluation","Plants (biology)","Rendering (computer graphics)","Three-dimensional displays"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mcrimaldi","dataSources":["dq7oSdLvMkrCCarLK"],"keywords":["atmospheric measurements","loss measurement","particle measurements","performance evaluation","plants (biology)","rendering (computer graphics)","three-dimensional displays"],"search_terms":["towards","field","phenotyping","exploiting","differentiable","rendering","self","consistency","loss","magistri","chebrolu","behley","stachniss"],"title":"Towards In-Field Phenotyping Exploiting Differentiable Rendering with Self-Consistency Loss","year":2021}