The Editorial Office of
Remote Sensing wish to report an error in the published paper [
1];
Table 6,
Table 7 and
Table 8 were incorrect. The correct tables are as follows:
Table 6.
Confusion matrix for the best performing model (features used are: , , , , , , ).
Table 7.
Confusion matrix for the model created by using only the spectral feature subset from the feature set resulting in the best performing model (features used are: , , , , and ).
Table 8.
Confusion matrix for the model created by using only the structural feature subset from the feature set resulting in the best performing model (features used are: , , and ).
We apologize for any inconvenience caused to the readers by this change. The change does not affect the scientific results. The manuscript will be updated and the original will remain available on the article webpage.
Reference
- Axelsson, A.; Lindberg, E.; Olsson, H. Exploring Multispectral ALS Data for Tree Species Classification. Remote Sens. 2018, 10, 183. [Google Scholar] [CrossRef]
Table 6.
Confusion matrix for the best performing model (features used are: , , , , , , ).
| Classification † (Number of Trees) | Reference † (Number of Trees) | User’s (%) |
|---|
| AL | M | B | AS | S | C | P | O | L |
|---|
| AL | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 50 |
| M | 0 | 12 | 0 | 0 | 0 | 0 | 0 | 1 | 2 | 80 |
| B | 0 | 0 | 24 | 0 | 0 | 2 | 0 | 0 | 5 | 77 |
| AS | 1 | 0 | 0 | 15 | 0 | 1 | 0 | 3 | 2 | 68 |
| S | 0 | 0 | 0 | 0 | 14 | 0 | 0 | 0 | 0 | 100 |
| C | 0 | 0 | 0 | 2 | 0 | 2 | 0 | 0 | 0 | 50 |
| P | 0 | 0 | 0 | 0 | 1 | 0 | 29 | 0 | 0 | 97 |
| O | 2 | 0 | 0 | 5 | 0 | 0 | 0 | 31 | 4 | 74 |
| L | 3 | 1 | 2 | 1 | 0 | 0 | 0 | 3 | 9 | 47 |
| Producer’s (%) | 14 | 92 | 92 | 65 | 93 | 40 | 100 | 82 | 39 | Overall: 76.5 |
Table 7.
Confusion matrix for the model created by using only the spectral feature subset from the feature set resulting in the best performing model (features used are: , , , , and ).
| Classification † (Number of Trees) | Reference † (Number of Trees) | User’s (%) |
|---|
| AL | M | B | AS | S | C | P | O | L |
|---|
| AL | 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 50 |
| M | 0 | 12 | 0 | 0 | 0 | 0 | 0 | 1 | 2 | 80 |
| B | 0 | 0 | 24 | 0 | 0 | 4 | 0 | 0 | 5 | 73 |
| AS | 0 | 0 | 0 | 16 | 0 | 1 | 0 | 3 | 2 | 73 |
| S | 0 | 0 | 0 | 0 | 14 | 0 | 0 | 0 | 0 | 100 |
| C | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 |
| P | 0 | 0 | 0 | 0 | 1 | 0 | 29 | 0 | 0 | 97 |
| O | 2 | 0 | 0 | 5 | 0 | 0 | 0 | 31 | 4 | 74 |
| L | 4 | 1 | 2 | 1 | 0 | 0 | 0 | 3 | 9 | 45 |
| Producer’s (%) | 14 | 92 | 92 | 70 | 93 | 0 | 100 | 82 | 39 | Overall: 76.0 |
Table 8.
Confusion matrix for the model created by using only the structural feature subset from the feature set resulting in the best performing model (features used are: , , and ).
| Classification † (Number of Trees) | Reference † (Number of Trees) | User’s (%) |
|---|
| AL | M | B | AS | S | C | P | O | L |
|---|
| AL | 0 | 1 | 0 | 1 | 1 | 1 | 0 | 0 | 2 | 0 |
| M | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| B | 0 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 | 0 |
| AS | 0 | 5 | 4 | 11 | 7 | 0 | 0 | 5 | 1 | 33 |
| S | 0 | 0 | 1 | 2 | 4 | 0 | 0 | 1 | 0 | 50 |
| C | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| P | 0 | 0 | 2 | 3 | 0 | 0 | 26 | 2 | 0 | 79 |
| O | 5 | 7 | 12 | 4 | 2 | 4 | 3 | 26 | 13 | 34 |
| L | 2 | 0 | 7 | 1 | 1 | 0 | 0 | 4 | 7 | 32 |
| Producer’s (%) | 0 | 0 | 0 | 48 | 27 | 0 | 90 | 68 | 30 | Overall: 41.3 |
© 2018 by the author. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).