Výsledky vyhledávání - "Multi-class object segmentation"

An encoder-decoder deep learning method for multi-class object segmentation from 3D tunnel point clouds Autor Ji, Ankang, Chew, Alvin Wei Ze, Xue, Xiaolong, Zhang, Limao

“… To address this problem, this research proposes an encoder-decoder deep learning method combined with point cloud techniques for multi-class object segmentation, including seepage, from 3D tunnel point clouds…”
Získat plný text

Multi-class object segmentation based on jointly integrating segment-level and image-level object priors Autor Yao, Tuozhong, Song, Jiatao, An, Peng, Liu, Liangxu

“… deformation and occlusion. This paper proposed a new multi-class object segmentation algorithm which jointly combines the segment-level and image-level object priors in a different way…”
Získat plný text

Robust Higher Order Potentials for Enforcing Label Consistency Autor Kohli, Pushmeet, Ladický, L’ubor, Torr, Philip H. S.

“…This paper proposes a novel framework for labelling problems which is able to combine multiple segmentations in a principled manner. Our method is based on…”
Získat plný text

Semi-supervised learning-based point cloud network for segmentation of 3D tunnel scenes Autor Ji, Ankang, Zhou, Yunxiang, Zhang, Limao, Tiong, Robert L.K., Xue, Xiaolong

“…Automatic identifying target multi-class objects in tunnel scenes from 3D point clouds is widely thought to be critical for maintaining the healthy condition…”
Získat plný text

Region based level sets for image segmentation: a brief comparative review with a fast model FREEST Autor Feng, Chaolu, Chen, Shuaizheng, Zhao, Dazhe, Yang, Jinzhu

“…Region based level sets are one class of popular image segmentation models. Sorting out the inheritance relationship and comparing their performance on same…”
Získat plný text

Object Segmentation for Autonomous Driving Using iseAuto Data Autor Gu, Junyi, Bellone, Mauro, Sell, Raivo, Lind, Artjom

“…–camera fusion, with only a few annotated scenarios and semi-supervised learning, it is possible to achieve robust performance on real-world data in a multi-class object segmentation problem…”
Získat plný text

Improved hierarchical conditional random field model for object segmentation Autor Wang, Li-Li, Yung, Nelson H. C.

“…Although the hierarchical conditional random field (HCRF) model has been successfully applied to multi-class object segmentation, there is still room for improvement…”
Získat plný text

Robust higher order potentials for enforcing label consistency Autor Kohli, P., Ladicky, L., Torr, P.

“… ]. We test our method on the problem of multi-class object segmentation by augmenting the conventional…”
Získat plný text

From video to text: Semantic driving scene understanding using a coarse-to-fine method Autor Huiyuan Fu, Huadong Ma

“… In the fine phase, we join multi-class object segmentation and detection algorithms together in a unified Conditional Random Filed (CRF…”
Získat plný text

Multi-class Video Objects Segmentation Based on Conditional Random Fields Autor He, Zhiwei, Xu, Lijun, Zhao, Wei, Gao, Mingyu

“… Experimental results show that the proposed algorithm can achieve high performance for multi-class objects segmentation in videos under complex environment. It can also get good recognition results when dealing with multi-viewed objects or serious sheltered objects. [PUBLICATION ABSTRACT]…”
Získat plný text