A Part-Aware Multi-Scale Fully Convolutional Network for Pedestrian Detection

Peiyu Yang, Guofeng Zhang, Lu Wang, Lisheng Xu, Qingxu Deng, Ming Hsuan Yang

Research output: Contribution to journalArticlepeer-review

32 Citations (Scopus)


Pedestrian detection is a crucial task in intelligent transportation systems, which can be applied in autonomous vehicles and traffic scene video surveillance systems. The past few years have witnessed much progress on the research of pedestrian detection methods, especially through the successful use of the deep learning based techniques. However, occlusion and large scale variation remain the challenging issues for pedestrian detection. In this work, we propose a Part-Aware Multi-Scale Fully Convolutional Network (PAMS-FCN) to tackle these difficulties. Specifically, we present a part-aware Region-of-Interest (RoI) pooling module to mine body parts with different responses, and select the part with the strongest response via voting. As such, a partially visible pedestrian instance can receive a high detection confidence score, making it less likely to become a missing detection. This module operates in parallel with an instance RoI pooling module to combine local parts and global context information. To handle vast scale variation, we construct a fully convolutional network in which multi-scale feature maps are generated efficiently, and small-scale and large-scale pedestrians are detected separately. By integrating these structures, the proposed detector achieves the state-of-the-art performance on the Caltech, KITTI, INRIA and ETH pedestrian detection datasets.

Original languageEnglish
Article number8960286
Pages (from-to)1125-1137
Number of pages13
JournalIEEE Transactions on Intelligent Transportation Systems
Issue number2
Publication statusPublished - 2021 Feb

Bibliographical note

Publisher Copyright:
© 2000-2011 IEEE.

All Science Journal Classification (ASJC) codes

  • Automotive Engineering
  • Mechanical Engineering
  • Computer Science Applications


Dive into the research topics of 'A Part-Aware Multi-Scale Fully Convolutional Network for Pedestrian Detection'. Together they form a unique fingerprint.

Cite this