Przeglądaj {{ collection }} wg Autor "Lazarek, Jagoda"

Teraz wyświetlane 1 - 2 z 2

Prediction of Natural Image Saliency for Synthetic Images
(Wydawnictwo Politechniki Łódzkiej, 2021) Rudak, Ewa; Rynkiewicz, Filip; Daszuta, Marcin; Sturgulewski, Łukasz; Lazarek, Jagoda
Numerous saliency models are being developed with the use ofneural networks and are capable of combining various features and predicting the saliency values with great results. In fact, it might be difficult to replace the possibilities of artificial intelligence applied to algorithms responsible for predicting saliency. However, the low-level features are still important and should not be removed completely from new saliency models. This work shows that carefully chosen and integrated features, including a deep learning based one, can be used for saliency prediction. The integration is obtained by using Multiple Kernel Learning. This solution is quite effective, as compared to a few other models tested on the same dataset.
A Review on Point Cloud Semantic Segmentation Methods
(Wydawnictwo Politechniki Łódzkiej, 2018) Lazarek, Jagoda; Pryczek, Michał
Semantic segmentation of 3D point clouds is an open research problem and remains crucial for autonomous driving, robot navigation, human-computer interaction, 3D reconstruction and many others. The large scale of the data and lack of regular data organization make it a very complex task. Research in this ﬁeld focuses on point cloud representation (e.g., 2D images, 3D voxels grid, graph) and segmentation techniques. In the paper, state-of-the-art approaches related to these tasks are presented.