Chinese Journal of Lasers, Volume. 49, Issue 23, 2310001(2022)
Tree Branch and Leaf Separation Using Terrestrial Laser Point Clouds
Figures & Tables(21)
Fig. 2. Schematics of constructing shortest path. (a) Constructing shortest path with point spacing as weight; (b) constructing shortest path with square of point spacing as weight
Fig. 3. Constructed undirected graph structure and trimmed graphs. (a) Constructed undirected graph; (b) result of graph segmentation
Fig. 4. Skeletons of branches and trunks extracted by shortest path algorithm. (a) Original point cloud of branches and trunks; (b) skeleton of branches and trunks extracted with distance between points as weight; (c) skeleton of branches and trunks extracted with square of distance between points as weight
Fig. 5. Point cloud of tree branches and trunks extracted by shortest path analysis algorithm. (a) Original point cloud of branches and trunks; (b) extracted point cloud of branches and trunks
Fig. 6. Point cloud of tree branches and trunks extracted by graph-based segmentation algorithm. (a) Original point cloud of branches and trunks; (b) extracted point cloud of branches and trunks
Fig. 8. Single tree point clouds with different average point spacings. (a) Tree 1; (b) Tree 2; (c) Tree 3
Fig. 9. Single-tree point clouds for different data quality or different tree species. (a) Tree 4; (b) Tree 5; (c) Tree 6; (d) Tree 7; (e) Tree 8; (f) Tree 9; (g) Tree 10; (h) Tree 11; (i) Tree 12; (j) Tree 13; (k) Tree 14; (l) Tree 15; (m) Tree 16; (n) Tree 17; (o) Tree 18; (p) Tree 19
Fig. 11. Separation results for branches and leaves of Tree 3 and reference values in open source data set. (a) Separation result for branches and leaves by proposed method; (b) reference value for branch and leaf separation in open source data set
Fig. 12. Separation results for branches and leaves by proposed method . (a) Tree 1; (b) Tree 2; (c) Tree 3
Fig. 13. Separation results for branches and leaves by TLSeparation method. (a) Tree 1; (b) Tree 2; (c) Tree 3
Fig. 14. Separation results for branches and leaves by LeWos method. (a) Tree 1; (b) Tree 2; (c) Tree 3
Table 1. Tree point cloud data
View tableTable 1. Tree point cloud data
Tree No. Number of points Tree height /m Average point spacing /m Tree 1 982636 52 0.12 Tree 2 947942 42 0.06 Tree 3 301615 36 0.04
Table 2. Pseudo-randomly selected input parameter values for verification testing
View tableTable 2. Pseudo-randomly selected input parameter values for verification testing
Parameter Possible value R 40，45，50 k 10，12，14，16，18，10，22，24，26，28 H 0.080，0.085，0.090，0.095，0.100，0.105，0.110 L [0.55，0.95] S′ [80，200]
Table 3. Separation result for branches and leaves of each tree
View tableTable 3. Separation result for branches and leaves of each tree
Tree No. Accuracy F(wood) F(leaf) κ M SD M SD M SD M SD Tree 1 0.9612 0.0012 0.8454 0.0041 0.9783 0.0007 0.8183 0.0046 Tree 2 0.9445 0.0011 0.8278 0.0033 0.9504 0.0006 0.8223 0.0039 Tree 3 0.9264 0.0034 0.8024 0.0056 0.9547 0.0023 0.7572 0.0078
Table 4. Separation results for branches and leaves from different trees
View tableTable 4. Separation results for branches and leaves from different trees
Tree No. Accuracy F(wood) F(leaf) κ Tree 4 0.9689 0.9055 0.9814 0.8869 Tree 5 0.9854 0.8967 0.9921 0.8887 Tree 6 0.9431 0.8722 0.9631 0.8383 Tree 7 0.9315 0.8664 0.9522 0.8122 Tree 8 0.9589 0.8352 0.9765 0.8118 Tree 9 0.9309 0.7973 0.9538 0.7799 Tree 10 0.9335 0.8395 0.9581 0.7977 Tree 11 0.9519 0.8800 0.9699 0.8500 Tree 12 0.9548 0.8291 0.9739 0.8030 Tree 13 0.9861 0.8658 0.9814 0.8586 Tree 14 0.9342 0.8182 0.9598 0.7781 Tree 15 0.9346 0.9545 0.8831 0.8376 Tree 16 0.9491 0.8722 0.9682 0.8405 Tree 17 0.9773 0.9244 0.9867 0.9111 Tree 18 0.9641 0.8956 0.9784 0.8740 Tree 19 0.9090 0.7650 0.9525 0.7077
Table 5. Evaluation indexes for TLSeparation method in separation of branches and leaves from 19 trees
View tableTable 5. Evaluation indexes for TLSeparation method in separation of branches and leaves from 19 trees
Tree No. Accuracy F(wood) F(leaf) κ Tree 1 0.9527 0.8035 0.9731 0.8338 Tree 2 0.8750 0.7780 0.9130 0.7690 Tree 3 0.6667 0.5131 0.7467 0.3327 Tree 4 0.9445 0.8218 0.9428 0.8046 Tree 5 0.9557 0.8000 0.9471 0.7875 Tree 6 0.9225 0.8136 0.9623 0.8062 Tree 7 0.9135 0.8832 0.9138 0.8271 Tree 8 0.8974 0.6500 0.9399 0.5918 Tree 9 0.9153 0.7472 0.9493 0.7186 Tree 10 0.9367 0.8530 0.9507 0.8127 Tree 11 0.9213 0.7769 0.9523 0.7303 Tree 12 0.9344 0.8148 0.9638 0.7986 Tree 13 0.9610 0.6877 0.9792 0.6681 Tree 14 0.8830 0.6493 0.9298 0.5792 Tree 15 0.8513 0.8855 0.7880 0.6788 Tree 16 0.9139 0.7967 0.9454 0.7424 Tree 17 0.9242 0.7232 0.9561 0.6799 Tree 18 0.9208 0.7840 0.9515 0.7359 Tree 19 0.9020 0.6949 0.9353 0.6527
Table 6. Evaluation indexes for LeWos method in separation of branches and leaves from 19 trees
View tableTable 6. Evaluation indexes for LeWos method in separation of branches and leaves from 19 trees
Tree No. Accuracy F(wood) F(leaf) κ Tree 1 0.9605 0.7899 0.9782 0.8405 Tree 2 0.9326 0.8645 0.9420 0.8337 Tree 3 0.9075 0.7902 0.9344 0.7365 Tree 4 0.9589 0.8818 0.9815 0.8634 Tree 5 0.9612 0.8611 0.9800 0.6087 Tree 6 0.9200 0.6263 0.9467 0.8080 Tree 7 0.9249 0.9052 0.9146 0.8898 Tree 8 0.9446 0.8287 0.9671 0.8020 Tree 9 0.9254 0.7069 0.9455 0.6756 Tree 10 0.9314 0.8391 0.9536 0.8133 Tree 11 0.9367 0.8319 0.9610 0.7932 Tree 12 0.9555 0.8582 0.9761 0.8644 Tree 13 0.9665 0.8526 0.9629 0.8456 Tree 14 0.9204 0.7650 0.9521 0.7171 Tree 15 0.9318 0.9532 0.8934 0.8867 Tree 16 0.9307 0.8301 0.9565 0.7866 Tree 17 0.9471 0.8315 0.9686 0.8002 Tree 18 0.9402 0.8214 0.9641 0.7855 Tree 19 0.9025 0.6634 0.9397 0.6155
Table 7. Evaluation indexes for proposed method in separation of branches and leaves from 19 trees
View tableTable 7. Evaluation indexes for proposed method in separation of branches and leaves from 19 trees
Tree No. Accuracy F(wood) F(leaf) κ Tree 1 0.9697 0.8674 0.9829 0.8475 Tree 2 0.9469 0.8863 0.9655 0.8547 Tree 3 0.9314 0.8110 0.9581 0.7691 Tree 4 0.9689 0.9055 0.9814 0.8869 Tree 5 0.9854 0.8967 0.9921 0.8887 Tree 6 0.9431 0.8722 0.9631 0.8383 Tree 7 0.9315 0.8664 0.9522 0.8122 Tree 8 0.9589 0.8352 0.9765 0.8118 Tree 9 0.9309 0.7973 0.9538 0.7799 Tree 10 0.9335 0.8395 0.9581 0.7977 Tree 11 0.9519 0.8800 0.9699 0.8500 Tree 12 0.9548 0.8291 0.9739 0.8030 Tree 13 0.9861 0.8658 0.9814 0.8586 Tree 14 0.9342 0.8182 0.9598 0.7781 Tree 15 0.9346 0.9545 0.8831 0.8376 Tree 16 0.9491 0.8722 0.9682 0.8405 Tree 17 0.9773 0.9244 0.9867 0.9111 Tree 18 0.9641 0.8956 0.9784 0.8740 Tree 19 0.9090 0.7650 0.9525 0.7077
Tools
Get Citation
Copy Citation Text
Huaqing Lu, Jicang Wu, Zijian Zhang. Tree Branch and Leaf Separation Using Terrestrial Laser Point Clouds[J]. Chinese Journal of Lasers, 2022, 49(23): 2310001
Paper Information
Category: remote sensing and sensor
Received: Dec. 28, 2021
Accepted: Mar. 24, 2022
Published Online: Oct. 31, 2022
The Author Email: Lu Huaqing (2033690@tongji.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20