Semantic Segmentation and Scene Reconstruction for Traffic Simulation Using CNN

Huihui Huo; Yaochen Li; Chuan Wu; Xiao Wu; Zhiqiang Tian; Yuehu Liu

doi:10.1109/CCHI.2019.8901938

Semantic Segmentation and Scene Reconstruction for Traffic Simulation Using CNN

Huihui Huo
, Yaochen Li
, Chuan Wu
, Xiao Wu
, Zhiqiang Tian
, Yuehu Liu

College of Artificial Intelligence and Robotics

Xi'an Jiaotong University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

In this paper, we propose a framework for 3D traffic scenes construction based on semantic segmentation using convolutional neural networks (CNNs). Firstly, the segmentation network, whose architecture is constructed with encoder-decoder model and a hall module, divides traffic scenes into different parts: Road, sky, vehicle and other regions. Furthermore, we generate spatio-temporal graph models and construct 3D traffic scenes according to semantic segmentation results. The applications for scene simulation are then developed. The experimental results on the KITTI dataset demonstrate the effectiveness of the proposed framework.

Original language	English
Title of host publication	Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	117-122
Number of pages	6
ISBN (Electronic)	9781728140919
DOIs	https://doi.org/10.1109/CCHI.2019.8901938
State	Published - Sep 2019
Event	2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019 - Xi'an, China Duration: 21 Sep 2019 → 22 Sep 2019

Publication series

Name	Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019

Conference

Conference	2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019
Country/Territory	China
City	Xi'an
Period	21/09/19 → 22/09/19

Keywords

CNN
Semantic segmentation
scene simulation
traffic scene

Access to Document

10.1109/CCHI.2019.8901938

Cite this

Huo, H., Li, Y., Wu, C., Wu, X., Tian, Z., & Liu, Y. (2019). Semantic Segmentation and Scene Reconstruction for Traffic Simulation Using CNN. In Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019 (pp. 117-122). Article 8901938 (Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCHI.2019.8901938

Huo, Huihui ; Li, Yaochen ; Wu, Chuan et al. / Semantic Segmentation and Scene Reconstruction for Traffic Simulation Using CNN. Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 117-122 (Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019).

@inproceedings{c131000275134d41bac0f2811922d546,

title = "Semantic Segmentation and Scene Reconstruction for Traffic Simulation Using CNN",

abstract = "In this paper, we propose a framework for 3D traffic scenes construction based on semantic segmentation using convolutional neural networks (CNNs). Firstly, the segmentation network, whose architecture is constructed with encoder-decoder model and a hall module, divides traffic scenes into different parts: Road, sky, vehicle and other regions. Furthermore, we generate spatio-temporal graph models and construct 3D traffic scenes according to semantic segmentation results. The applications for scene simulation are then developed. The experimental results on the KITTI dataset demonstrate the effectiveness of the proposed framework.",

keywords = "CNN, Semantic segmentation, scene simulation, traffic scene",

author = "Huihui Huo and Yaochen Li and Chuan Wu and Xiao Wu and Zhiqiang Tian and Yuehu Liu",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019 ; Conference date: 21-09-2019 Through 22-09-2019",

year = "2019",

month = sep,

doi = "10.1109/CCHI.2019.8901938",

language = "英语",

series = "Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "117--122",

booktitle = "Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019",

}

Huo, H, Li, Y, Wu, C, Wu, X, Tian, Z & Liu, Y 2019, Semantic Segmentation and Scene Reconstruction for Traffic Simulation Using CNN. in Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019., 8901938, Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019, Institute of Electrical and Electronics Engineers Inc., pp. 117-122, 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019, Xi'an, China, 21/09/19. https://doi.org/10.1109/CCHI.2019.8901938

Semantic Segmentation and Scene Reconstruction for Traffic Simulation Using CNN. / Huo, Huihui; Li, Yaochen; Wu, Chuan et al.
Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 117-122 8901938 (Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Semantic Segmentation and Scene Reconstruction for Traffic Simulation Using CNN

AU - Huo, Huihui

AU - Li, Yaochen

AU - Wu, Chuan

AU - Wu, Xiao

AU - Tian, Zhiqiang

AU - Liu, Yuehu

PY - 2019/9

Y1 - 2019/9

N2 - In this paper, we propose a framework for 3D traffic scenes construction based on semantic segmentation using convolutional neural networks (CNNs). Firstly, the segmentation network, whose architecture is constructed with encoder-decoder model and a hall module, divides traffic scenes into different parts: Road, sky, vehicle and other regions. Furthermore, we generate spatio-temporal graph models and construct 3D traffic scenes according to semantic segmentation results. The applications for scene simulation are then developed. The experimental results on the KITTI dataset demonstrate the effectiveness of the proposed framework.

AB - In this paper, we propose a framework for 3D traffic scenes construction based on semantic segmentation using convolutional neural networks (CNNs). Firstly, the segmentation network, whose architecture is constructed with encoder-decoder model and a hall module, divides traffic scenes into different parts: Road, sky, vehicle and other regions. Furthermore, we generate spatio-temporal graph models and construct 3D traffic scenes according to semantic segmentation results. The applications for scene simulation are then developed. The experimental results on the KITTI dataset demonstrate the effectiveness of the proposed framework.

KW - CNN

KW - Semantic segmentation

KW - scene simulation

KW - traffic scene

UR - https://www.scopus.com/pages/publications/85075764923

U2 - 10.1109/CCHI.2019.8901938

DO - 10.1109/CCHI.2019.8901938

M3 - 会议稿件

AN - SCOPUS:85075764923

T3 - Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019

SP - 117

EP - 122

BT - Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019

Y2 - 21 September 2019 through 22 September 2019

ER -

Huo H, Li Y, Wu C, Wu X, Tian Z, Liu Y. Semantic Segmentation and Scene Reconstruction for Traffic Simulation Using CNN. In Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 117-122. 8901938. (Proceedings - 2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019). doi: 10.1109/CCHI.2019.8901938

Semantic Segmentation and Scene Reconstruction for Traffic Simulation Using CNN

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this