Tree instance segmentation and traits estimation for forestry environments exploiting LiDAR data collected by mobile robots
Forests play a crucial role in our ecosystems, functioning as carbon sinks, climate stabilizers, biodiversity hubs, and sources of wood. By the very nature of their scale, monitoring and maintaining forests is a challenging task. Robotics in forestry can have the potential for substantial automation...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2024
|
| _version_ | 1826314960020439040 |
|---|---|
| author | Malladi, MVR Guadagnino, T Lobefaro, L Mattamala, M Griess, H Schweier, J Chebrolu, N Fallon, M Behley, J Stachniss, C |
| author_facet | Malladi, MVR Guadagnino, T Lobefaro, L Mattamala, M Griess, H Schweier, J Chebrolu, N Fallon, M Behley, J Stachniss, C |
| author_sort | Malladi, MVR |
| collection | OXFORD |
| description | Forests play a crucial role in our ecosystems, functioning as carbon sinks, climate stabilizers, biodiversity hubs, and sources of wood. By the very nature of their scale, monitoring and maintaining forests is a challenging task. Robotics in forestry can have the potential for substantial automation toward efficient and sustainable foresting practices. In this paper, we address the problem of automatically producing a forest inventory by exploiting LiDAR data collected by a mobile platform. To construct an inventory, we first extract tree instances from point clouds. Then, we process each instance to extract forestry inventory information. Our approach provides the per-tree geometric trait of "diameter at breast height" together with the individual tree locations in a plot. We validate our results against manual measurements collected by foresters during field trials. Our experiments show strong segmentation and tree trait estimation performance, underlining the potential for automating forestry services. Results furthermore show a superior performance compared to the popular baseline methods used in this domain. |
| first_indexed | 2024-04-09T03:55:23Z |
| format | Conference item |
| id | oxford-uuid:d29224bc-f133-484f-b8eb-f99fb34b6eb3 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:17:29Z |
| publishDate | 2024 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:d29224bc-f133-484f-b8eb-f99fb34b6eb32024-10-21T11:16:39ZTree instance segmentation and traits estimation for forestry environments exploiting LiDAR data collected by mobile robotsConference itemhttp://purl.org/coar/resource_type/c_5794uuid:d29224bc-f133-484f-b8eb-f99fb34b6eb3EnglishSymplectic ElementsIEEE2024Malladi, MVRGuadagnino, TLobefaro, LMattamala, MGriess, HSchweier, JChebrolu, NFallon, MBehley, JStachniss, CForests play a crucial role in our ecosystems, functioning as carbon sinks, climate stabilizers, biodiversity hubs, and sources of wood. By the very nature of their scale, monitoring and maintaining forests is a challenging task. Robotics in forestry can have the potential for substantial automation toward efficient and sustainable foresting practices. In this paper, we address the problem of automatically producing a forest inventory by exploiting LiDAR data collected by a mobile platform. To construct an inventory, we first extract tree instances from point clouds. Then, we process each instance to extract forestry inventory information. Our approach provides the per-tree geometric trait of "diameter at breast height" together with the individual tree locations in a plot. We validate our results against manual measurements collected by foresters during field trials. Our experiments show strong segmentation and tree trait estimation performance, underlining the potential for automating forestry services. Results furthermore show a superior performance compared to the popular baseline methods used in this domain. |
| spellingShingle | Malladi, MVR Guadagnino, T Lobefaro, L Mattamala, M Griess, H Schweier, J Chebrolu, N Fallon, M Behley, J Stachniss, C Tree instance segmentation and traits estimation for forestry environments exploiting LiDAR data collected by mobile robots |
| title | Tree instance segmentation and traits estimation for forestry environments exploiting LiDAR data collected by mobile robots |
| title_full | Tree instance segmentation and traits estimation for forestry environments exploiting LiDAR data collected by mobile robots |
| title_fullStr | Tree instance segmentation and traits estimation for forestry environments exploiting LiDAR data collected by mobile robots |
| title_full_unstemmed | Tree instance segmentation and traits estimation for forestry environments exploiting LiDAR data collected by mobile robots |
| title_short | Tree instance segmentation and traits estimation for forestry environments exploiting LiDAR data collected by mobile robots |
| title_sort | tree instance segmentation and traits estimation for forestry environments exploiting lidar data collected by mobile robots |
| work_keys_str_mv | AT malladimvr treeinstancesegmentationandtraitsestimationforforestryenvironmentsexploitinglidardatacollectedbymobilerobots AT guadagninot treeinstancesegmentationandtraitsestimationforforestryenvironmentsexploitinglidardatacollectedbymobilerobots AT lobefarol treeinstancesegmentationandtraitsestimationforforestryenvironmentsexploitinglidardatacollectedbymobilerobots AT mattamalam treeinstancesegmentationandtraitsestimationforforestryenvironmentsexploitinglidardatacollectedbymobilerobots AT griessh treeinstancesegmentationandtraitsestimationforforestryenvironmentsexploitinglidardatacollectedbymobilerobots AT schweierj treeinstancesegmentationandtraitsestimationforforestryenvironmentsexploitinglidardatacollectedbymobilerobots AT chebrolun treeinstancesegmentationandtraitsestimationforforestryenvironmentsexploitinglidardatacollectedbymobilerobots AT fallonm treeinstancesegmentationandtraitsestimationforforestryenvironmentsexploitinglidardatacollectedbymobilerobots AT behleyj treeinstancesegmentationandtraitsestimationforforestryenvironmentsexploitinglidardatacollectedbymobilerobots AT stachnissc treeinstancesegmentationandtraitsestimationforforestryenvironmentsexploitinglidardatacollectedbymobilerobots |