S3-Net: A Fast Scene Understanding Network by Single-shot Segmentation for Autonomous Driving

YUAN CHENG1; Yuchao Yang2; Hai-Bao Chen1; NGAI WONG3; HAO YU2

2021-09

10.1145/3470660

ACM Transactions on Intelligent Systems and Technology   影响因子和分区

2157-6904

2157-6912

Real-time segmentation and understanding of driving scenes are crucial in autonomous driving. Traditional pixel-wise approaches extract scene information by segmenting all pixels in a frame, and hence are inefficient and slow. Proposal-wise approaches only learn from the proposed object candidates. but still require multiple steps on the expensive proposal methods. Instead, this work presents a fast single-shot segmentation strategy for video scene understanding. The proposed net, called S3-Net, quickly locates and segments target subscenes, and meanwhile extracts attention-aware time-series sub-scene features (ats-features) as inputs to an attention-aware spatio-temporal model (ASM). Utilizing tensorization and quantization techniques, S3-Net is intended to be lightweight for edge computing. Experiments results on CityScapes, UCF11, HMDB51, and MOMENTS datasets demonstrate that the proposed S3-Net achieves an accuracy improvement of 8.1% versus the 3D-CNN based approach on UCF11, a storage reduction of 6.9x and an inference speed of 22.8 FPS on CityScapes with a GTX1080Ti GPU.

Video scene understanding single-shot segmentation spatio-temporal model time-series features tensorization quantization

SCI ; EI

英语

通讯

National Natural Science Foundation of China (NSFC)[6203000189] ; National Key Research and Development Program of China[2019YFB2205005] ; Key-Area Research and Development Program of Guangdong Province[2019B010142001] ; Innovative Team Program of Education Department of Guangdong Province[2018KCXTD028] ; Shenzhen Science and Technology Program[KQTD20200820113051096]

Computer Science

Computer Science, Artificial Intelligence ; Computer Science, Information Systems

WOS:000732997200007

ASSOC COMPUTING MACHINERY

人工提交

1.Shanghai Jiao Tong University
2.Southern University of Science and Technology
3.The University of Hong Kong

YUAN CHENG,Yuchao Yang,Hai-Bao Chen,et al. S3-Net: A Fast Scene Understanding Network by Single-shot Segmentation for Autonomous Driving[J]. ACM Transactions on Intelligent Systems and Technology,2021,12(5).

YUAN CHENG,Yuchao Yang,Hai-Bao Chen,NGAI WONG,&HAO YU.(2021).S3-Net: A Fast Scene Understanding Network by Single-shot Segmentation for Autonomous Driving.ACM Transactions on Intelligent Systems and Technology,12(5).

YUAN CHENG,et al."S3-Net: A Fast Scene Understanding Network by Single-shot Segmentation for Autonomous Driving".ACM Transactions on Intelligent Systems and Technology 12.5(2021).