Efficient and Lightweight Convolutional Neural Network for Lane Mark and Road Segmentation

Guan Ting Lin, Jiun-In Guo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Semantic segmentation is one of an important task in computer vision that takes a great part in the perception needs of intelligent autonomous vehicles. ConvNets excel at this task, as they can be adaptively trained end-to-end to yield a set of robust hierarchies of features. The proposed key method is to reduce the unnecessary weights to build an efficient and lightweight network to acquire high accuracy on lane mark and road segmentation at pixel level. The proposed fully convolutional neural network achieves 360textx480 @ 28 fps and 97.6% accuracy on our in-house pixel-based hand-annotated lane mark and road datasets. All our models and results are trained and evaluated on an NVIDIA GTX 1080 GPU device.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781538663011
DOIs
StatePublished - 27 Aug 2018
Event5th IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2018 - Taichung, Taiwan
Duration: 19 May 201821 May 2018

Publication series

Name2018 IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2018

Conference

Conference5th IEEE International Conference on Consumer Electronics-Taiwan, ICCE-TW 2018
CountryTaiwan
CityTaichung
Period19/05/1821/05/18

Fingerprint Dive into the research topics of 'Efficient and Lightweight Convolutional Neural Network for Lane Mark and Road Segmentation'. Together they form a unique fingerprint.

Cite this