KLASIFIKACIJA TIPA RADARSKOG OBJEKTA KORISTEĆI LSTM NEURONSKE MREŽE SA KONVOLUCIJAMA NA SKUPOVIMA TAČAKA
DOI:
https://doi.org/10.24867/29BE26LunicKljučne reči:
Veštačka inteligencija, neuronske mreže, radarska klasifikacijaApstrakt
Rad predstavlja model neuronskih mreža za klasifikaciju tipa radaskog objekta na osnovu skupa tačaka koje definišu objekat. Arhitektura koristi konvolucije na neuređenim skupovima tačaka u okviru kratkotrajno-dugotrajne memorijske ćelije da enkodira geometriju i osobine tačaka kroz vreme. Model pokazuje visoke mere performansi na skupu podataka View of Delft sa 94% tačnosti i 0.94 F1 merom na klasama pešaka, automobila i biciklista.
Reference
[1] Qi, C.R., Su, H., Mo, K. and Guibas, L.J., 2017. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 652-660).
[2] Qi, C.R., Yi, L., Su, H. and Guibas, L.J., 2017. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30.
[3] Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F. and Guibas, L.J., 2019. Kpconv: Flexible and deformable convolution for point clouds. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 6411-6420).
[4] Palffy, A., Pool, E., Baratam, S., Kooij, J.F. and Gavrila, D.M., 2022. Multi-class road user detection with 3+ 1D radar in the View-of-Delft dataset. IEEE Robotics and Automation Letters, 7(2), pp.4961-4968.
[5] Nobis, F., Fent, F., Betz, J. and Lienkamp, M., 2021. Kernel point convolution LSTM networks for radar point cloud segmentation. Applied Sciences, 11(6), p.2599.
[6] Fent, F., 2020. Machine Learning-Based Radar Point Cloud Segmentation.
[7] Fan, H. and Yang, Y., 2019. PointRNN: Point recurrent neural network for moving point cloud processing. arXiv preprint arXiv:1910.08287.
[8] Schumann, O., Hahn, M., Dickmann, J. and Wöhler, C., 2018, July. Semantic segmentation on radar point clouds. In 2018 21st International Conference on Information Fusion (FUSION) (pp. 2179-2186). IEEE.
[2] Qi, C.R., Yi, L., Su, H. and Guibas, L.J., 2017. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30.
[3] Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F. and Guibas, L.J., 2019. Kpconv: Flexible and deformable convolution for point clouds. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 6411-6420).
[4] Palffy, A., Pool, E., Baratam, S., Kooij, J.F. and Gavrila, D.M., 2022. Multi-class road user detection with 3+ 1D radar in the View-of-Delft dataset. IEEE Robotics and Automation Letters, 7(2), pp.4961-4968.
[5] Nobis, F., Fent, F., Betz, J. and Lienkamp, M., 2021. Kernel point convolution LSTM networks for radar point cloud segmentation. Applied Sciences, 11(6), p.2599.
[6] Fent, F., 2020. Machine Learning-Based Radar Point Cloud Segmentation.
[7] Fan, H. and Yang, Y., 2019. PointRNN: Point recurrent neural network for moving point cloud processing. arXiv preprint arXiv:1910.08287.
[8] Schumann, O., Hahn, M., Dickmann, J. and Wöhler, C., 2018, July. Semantic segmentation on radar point clouds. In 2018 21st International Conference on Information Fusion (FUSION) (pp. 2179-2186). IEEE.
##submission.downloads##
Objavljeno
2024-11-05
Broj časopisa
Rubrika
Elektrotehničko i računarsko inženjerstvo
