Segmentation of LiDAR Intensity Using CNN Feature Based on Weighted Voting
We propose an image labeling method for LiDAR intensity image obtained by Mobile Mapping System (MMS). Conventional segmentation method using CNN and KNN could give high accuracy but the accuracies of objects with small area are much lower than other classes with large area. We solve this issue by using voting cost. The first cost is determined from a local region. Another cost is determined from surrounding regions of the local region. Those costs become large when labeling result corresponds to class label of the region. In experiments, we use 36 LIDAR intensity images with ground truth labels. We divide 36 images into training (28 images) and test sets (8 images). We use class average accuracy as evaluation measures. Our proposed method gain 84.75% on class average accuracy, and it is 9.22% higher than our conventional method. We demonstrated that the proposed costs are effective to improve the accuracy.
KeywordsLocal Region Class Label Convolutional Neural Network Vote Weight Catchment Basin
This work is partially supported by MEXT KAKENHI 15K00252.
- 1.Hasegawa, H., Ishiyama, N.: Publication of The Digital Maps (Basic Geospatial Information). Geospatial Inf. Authority Jpn 60, 19–24 (2013)Google Scholar
- 2.Umemura, M., Hotta, K., Nonaka, H., Oda, K.: Image labeling for lidar intensity image using K-NN of feature obtained by convolutional neural network, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci. XLI-B3, 931–935 (2016)Google Scholar
- 5.Kohli, P., Osokin, A., Jegelka, S.: A principled deep random field model for image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1971–1978 (2013)Google Scholar
- 8.Jonathan, L., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, pp. 3431–3440 (2015)Google Scholar
- 9.Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. arXiv preprint arXiv:1511.00561 (2015)
- 10.Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the ACM International Conference on Multimedia, Florida, USA, pp. 675–678 (2014)Google Scholar
- 11.Novak, K.: Mobile Mapping System: new tools for the fast collection of GIS information. In: Proceedings of the SPIE, vol. 1943 (1993)Google Scholar