• Home
  • Search
  • Mutual-Supervised Feature Modulation Network for Occluded Pedestrian Detection
  • Open Access IconOpen Access
  • Cite Icon6
  • https://doi.org/10.1109/icpr48806.2021.9412981Copy DOI Icon

Mutual-Supervised Feature Modulation Network for Occluded Pedestrian Detection

  • Jan 10, 2021
  • Ye He +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

State-of-the-art pedestrian detectors have achieved significant progress on non-occluded pedestrians, yet they are still struggling under heavy occlusions. The recent occlusion handling strategy of popular two-stage approaches is to build a two-branch architecture with the help of additional visible body annotations. Nonetheless, these methods still have some weaknesses. Either the two branches are trained independently with only score-level fusion, which cannot guarantee the detectors to learn robust enough pedestrian features. Or the attention mechanisms are exploited to only emphasize on the visible body features. However, the visible body features of heavily occluded pedestrians are concentrated on a relatively small area, which will easily cause missing detections. To address the above issues, we propose in this paper a novel Mutual-Supervised Feature Modulation (MSFM) network, to better handle occluded pedestrian detection. The key MSFM module in our network calculates the similarity loss of full body boxes and visible body boxes corresponding to the same pedestrian so that the full-body detector could learn more complete and robust pedestrian features with the assist of contextual features from the occluding parts. To facilitate the MSFM module, we also propose a novel two-branch architecture, consisting of a standard full body detection branch and an extra visible body classification branch. These two branches are trained in a mutual-supervised way with full body annotations and visible body annotations, respectively. To verify the effectiveness of our proposed method, extensive experiments are conducted on two challenging pedestrian datasets: Caltech and CityPersons, and our approach achieves superior performance compared to other state-of-the-art methods on both datasets, especially in heavy occlusion cases.

Similar Papers
  • Research Article
  • Citations32

PRNet++: Learning towards generalized occluded pedestrian detection via progressive refinement network

  • Jan 21, 2022
  • Neurocomputing
  • Xiaolin Song +4
  • Research Article
  • Citations3

Replacing the human driver: An objective benchmark for occluded pedestrian detection

  • Jul 18, 2023
  • Biomimetic Intelligence and Robotics
  • Shane Gilroy +4
  • Conference Article
  • Citations466

Occluded Pedestrian Detection Through Guided Attention in CNNs

  • Jun 01, 2018
  • Shanshan Zhang +2
  • Research Article

Low-Light Amodal Objects Tracking: A Benchmark

  • Jan 01, 2025
  • IEEE Robotics and Automation Letters
  • Junjie Ding +5
  • PDF
  • Research Article
  • Citations21

Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet.

  • Mar 05, 2021
  • Sensors
  • Xiaotao Shao +6
  • Conference Article
  • Citations29

An End-To-End Framework For Pose Estimation Of Occluded Pedestrians

  • Oct 01, 2020
  • Sudip Das +2
  • Research Article
  • Citations3

Recognition of occluded pedestrians from the driver's perspective for extending sight distance and ensuring driving safety at signal-free intersections

  • Jan 01, 2024
  • Digital Transportation and Safety
  • Kun Qie +4
  • Research Article
  • Citations34

Feature Calibration Network for Occluded Pedestrian Detection

  • Dec 21, 2020
  • IEEE Transactions on Intelligent Transportation Systems
  • Tianliang Zhang +5
  • Conference Article
  • Citations5

Part-based deep network for pedestrian detection in surveillance videos

  • Dec 01, 2015
  • Qi Chen +3
  • Research Article
  • Citations28

Improved Instance Discrimination and Feature Compactness for End-to-End Person Search

  • May 22, 2021
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Shaowei Hou +5
  • Dissertation

Face Recognition with Attention Mechanisms

  • Jan 01, 2022
  • Qiangchang Wang
  • PDF
  • Research Article
  • Citations15

Joint Pedestrian and Body Part Detection via Semantic Relationship Learning

  • Feb 21, 2019
  • Applied Sciences
  • Junhua Gu +3
  • Book Chapter
  • Citations4

Visible Feature Guidance for Crowd Pedestrian Detection

  • Jan 01, 2020
  • Zhida Huang +3
  • Research Article
  • Citations17

A robust pedestrian detection approach based on shapelet feature and Haar detector ensembles

  • Feb 01, 2012
  • Tsinghua Science and Technology
  • Wentao Yao +1
  • Conference Article
  • Citations14

Pedestrian detection based on attention mechanism and feature enhancement with SSD

  • Nov 01, 2020
  • T T Feng +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.