Ouvrir le document
|
Informations générales |
| Auteur |
Yu, Zhou; Yu, Yao; Lu, Guiliang; Du, Sidan |
| Publié |
InTech Open Access Publisher, 2012
|
| Edition |
|
| Extension |
|
| ISBN |
|
| Abstract |
We address the problem of classifying 3D point
clouds: given 3D urban street scenes gathered by a lidar
sensor, we wish to assign a class label to every point.
This work is a key step toward realizing applications in
robots and cars, for example. In this paper, we present a
novel approach to the classification of 3D urban scenes
based on super‐segments, which are generated from
point clouds by two stages of segmentation: a clustering
stage and a grouping stage. Then, six effective normal
and dimension features that vary with object class are
extracted at the super‐segment level for training some
general classifiers. We evaluate our method both
quantitatively and qualitatively using the challenging
Velodyne lidar data set. The results show that by only
using normal and dimension features we can achieve
better recognition than can be achieved with highdimensional
shape descriptors. We also evaluate the
adopting of the MRF framework in our approach, but
the experimental results indicate that thisbarely
improved the accuracy of the classified results due to
the sparse property of the super‐segments. |
|
| |
|
International Journal of Advanced Robotic Systems
Auteur: Ottaviano, Erika; Ceccarelli, Marco; Husty, Manfred; Yu, Sung-Hoon; Kim, Yong-Tae; Park, Chang-Woo; Hyun, Chang-Ho; Chen, Xiulong; Feng, Weiming; Sun, Xianyang; Gao, Qing; Grigorescu, Sorin M.; Pozna, Claudiu; Liu, Wanli; Zhankui, Wang; Guo, Meng; Fu, Guoyu; Zhang, Jin; Chen, Wenyuan; Peng, Fengchao; Yang, Pei; Chen, Chunlin; Ding, Rui; Yu, Junzhi; Yang, Qinghai; Tan, Min; Polden, Joseph; Pan, [...]
Publié: 2004
|
|
Newsletter
DMG-Lib
Europeana
PDF
Univ. Cassino
