Adjacent Feature Propagation Network (AFPNet) for Real-Time Semantic Segmentation

Junhyuk Hyun, Hongje Seong, Sangki Kim, Euntai Kim

Research output: Contribution to journalArticlepeer-review

Abstract

With the development of deep learning, semantic segmentation has received considerable attention within the robotics community. For semantic segmentation to be applied to mobile robots or autonomous vehicles, real-time processing is essential. In this article, a new real-time semantic segmentation network, called the adjacent feature propagation network (AFPNet), is proposed to achieve high performance and fast inference. AFPNet executes in real time on a commercial embedded GPU. The network includes two new modules. The local memory module (LMM) is the first; it improves the upsampling accuracy by propagating the high-level features to the adjacent grids. The cascaded pyramid pooling module (CPPM) is the second; it reduces computational time by changing the structure of the pyramid pooling module. Using these two modules, the proposed AFPNet achieved 76.4% mean intersection-over-union on the Cityscapes test dataset, outperforming other real-time semantic segmentation networks. Furthermore, AFPNet was successfully deployed on an embedded board Jetson AGX Xavier and applied to the real-world navigation of a mobile robot, proving that AFPNet can be effectively used in a variety of real-time applications.

Original languageEnglish
JournalIEEE Transactions on Systems, Man, and Cybernetics: Systems
DOIs
Publication statusAccepted/In press - 2021

Bibliographical note

Publisher Copyright:
IEEE

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Human-Computer Interaction
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Adjacent Feature Propagation Network (AFPNet) for Real-Time Semantic Segmentation'. Together they form a unique fingerprint.

Cite this