With massive green fields. You can find two false SB-480848 Autophagy positives around the overpass. Figure 13 shows the using a low mean IoU. These with significant green fields. approach performed worse for the sparse Figure urban region outcomes show that our You will find two false positives around the overpass. the two false positives together with the nDSM; the overpass. Figure urban area withcomparison ofcomparison of thetwo false positives together with the height of your false positives on big green fields. There are two false positives around the nDSM; the height of the false 13 shows the the overpass is greater than its surroundings. We may possibly deduce that the nDSM results in the 13 shows the comparison in the two falseis higher than its the nDSM; the heightdeduce falsethe nDSM positives on the overpass positives with surroundings. We may perhaps in the that false positives for the overpass. benefits in the false than its surroundings. positives around the overpass is higherpositives for the overpass.We may deduce that the nDSM benefits in the false positives for the overpass.Figure 11 shows the predicted polygons obtained on composite image 1 (RGB + nDSM)(a)(b)(c)(d)Figure Benefits obtained on the urban area test dataset (RGB + nDSM) with high mean The The predicted polygons Figure 11.11. Outcomes obtainedon the urban region test dataset (RGB + nDSM) with higher mean IoU. IoU.predicted polygons are created with 1 pixel for the tolerance parameter from the polygonization approach. (a) Predicted (d) polygons with imply IoU (b) (c) are DNQX disodium salt Protocol developed with 1 pixel for the tolerance parameter in the polygonization approach. (a) Predicted polygons with mean 1; (b) predicted polygons with mean IoU 0.955; (c) predicted polygons with imply IoU 0.951; (d) predicted polygons with IoU 1; (b) predicted polygons with imply IoU + nDSM) with higher mean IoU. The predicted polygons are re 11. Results obtained IoUthe urban area test dataset (RGB 0.955; (c) predicted polygons with mean IoU 0.951; (d) predicted polygons mean on 0.937. withfor the IoU 0.937. parameter with the polygonization process. (a) Predicted polygons with mean IoU uced with 1 pixel mean tolerance(a)predicted polygons with imply IoU 0.955; (c) predicted polygons with imply IoU 0.951; (d) predicted polygons with n IoU 0.937.Remote Sens. 2021, 13, x FOR PEER REVIEWRemote Sens. 2021, 13, 4700 Remote Sens. 2021, 13, x FOR PEER Evaluation 16 of17 of(a) (a)(b) (b)(c)(c)(d)(d)Figure 12. Results obtained on the urban location test dataset (RGB + with low mean IoU. The predicted predicted obtained Figure 12. Benefits 1 pixel foron the urban region test dataset (RGB + nDSM)nDSM) with low imply IoU.withpolygons are polygons are Themean IoU produced together with the tolerance parameter in the polygonization method. (a) Predicted polygons producedwith 1 pixel for the tolerance parameter of your from the polygonization (a) Predicted polygons with mean IoUwith mean IoU with 1 pixel for the tolerance parameter polygonization method. process. (a) Predicted polygons 0; developed predicted polygons with mean IoU 0.195; (c) predicted polygons with imply IoU 0.257; (d) predicted polygons with 0; (b) (b) predicted 0.345. 0; (b)imply IoU polygons withwith mean IoU(c) predicted polygons with imply IoU 0.257; (d) predicted polygons with mean predicted polygons imply IoU 0.195; 0.195; (c) predicted polygons with mean IoU 0.257; (d) predicted polygons with IoU IoU 0.345. mean 0.345.Figure 12. Results obtained on the urban location test dataset (RGB + nDSM) with low mean IoU. The predicted polygons arenDSMnDSMnDSM+Prediction nDSM+Prediction(a)(b).