TY - JOUR
T1 - Rapid detection of blind roads and crosswalks by using a lightweight semantic segmentation network
AU - Cao, Zhengcai
AU - Xu, Xiaowen
AU - Hu, Biao
AU - Zhou, Mengchu
N1 - Funding Information:
This work was supported in part by the Beijing Leading Talents Program under Grant Z191100006119031, the National Key Research and Development Program of China under Grant 2018YFB1304600, the National Natural Science Foundation of China under Grant U1813220, the Beijing Municipal Natural Science Foundation under Grant 3202022, and The Deanship of Scientific Research (DSR) at King Abdulaziz University under grant no. RG-48-135-40.
Publisher Copyright:
© 2000-2011 IEEE.
PY - 2021/10/1
Y1 - 2021/10/1
N2 - Achieving the high accuracy of blind roads and crosswalks recognition is important for blind guiding equipment to help blind people sense the surrounding environment. A lightweight semantic segmentation network is proposed to quickly and accurately segment blind roads and crosswalks in a complex road environment. Specifically, a lightweight network with depthwise separable convolution as a component is used as a basic module to reduce the number of parameters of the model and increase the speed of semantic segmentation. In order to ensure the segmentation accuracy of the network, we use a densely connected atrous spatial pyramid pooling module to extract feature information of different angles and context feature modules to enhance the effectiveness of different levels of feature information fusion. To verify the effectiveness of the proposed method, we collect and produce a data set from a real environment, which contains two objects of blind roads and crosswalks1. Experimental results demonstrate that, compared to some state-of-the-art approaches, the proposed approach greatly improves the segmentation speed, while achieving better or similar accuracy, which shows that the proposed approach provides a better basis for the application of devices for guiding the blind.
AB - Achieving the high accuracy of blind roads and crosswalks recognition is important for blind guiding equipment to help blind people sense the surrounding environment. A lightweight semantic segmentation network is proposed to quickly and accurately segment blind roads and crosswalks in a complex road environment. Specifically, a lightweight network with depthwise separable convolution as a component is used as a basic module to reduce the number of parameters of the model and increase the speed of semantic segmentation. In order to ensure the segmentation accuracy of the network, we use a densely connected atrous spatial pyramid pooling module to extract feature information of different angles and context feature modules to enhance the effectiveness of different levels of feature information fusion. To verify the effectiveness of the proposed method, we collect and produce a data set from a real environment, which contains two objects of blind roads and crosswalks1. Experimental results demonstrate that, compared to some state-of-the-art approaches, the proposed approach greatly improves the segmentation speed, while achieving better or similar accuracy, which shows that the proposed approach provides a better basis for the application of devices for guiding the blind.
KW - Blind roads and crosswalks
KW - Deep convolutional network
KW - Lightweight structure
KW - Semantic segmentation
UR - http://www.scopus.com/inward/record.url?scp=85117038473&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85117038473&partnerID=8YFLogxK
U2 - 10.1109/TITS.2020.2989129
DO - 10.1109/TITS.2020.2989129
M3 - Article
AN - SCOPUS:85117038473
VL - 22
SP - 6188
EP - 6197
JO - IEEE Transactions on Intelligent Transportation Systems
JF - IEEE Transactions on Intelligent Transportation Systems
SN - 1524-9050
IS - 10
ER -