Human Detection Aided by Deeply Learned Semantic Masks

Xinyu Wang, Chunhua Shen, Hanxi Li, Shugong Xu

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)

Abstract

Human detection is one of the long-standing computer vision tasks, and it has been a cornerstone for many real-world applications, such as photo album organization, video surveillance, and autonomous driving. Benefiting from deep learning technologies, such as convolutional neural networks and modern object detectors, have been achieving much improved accuracy in generic object detection tasks. In this paper, we aim to improve deep learning-based human detection. Our main idea is to exploit semantic context information for human detection by using deep-learnt semantic features provided by semantic segmentation masks. Segmentation masks play as an attention mechanism and enforce the detectors to focus on the image regions where potential object candidates are likely to appear. Meanwhile, the extra segmentation mask channel can also guide the convolutional kernels to automatically learn more discriminative features which make it easier to distinguish the background and foreground. We implement our methods with two popular detection frameworks, i.e., faster R-CNN and SSD and experimentally analyze the effectiveness of the proposed methods. Evaluation results on the widely used MS-COCO dataset and the very recent CrowdHuman dataset are provided. Our proposed methods outperform the baseline detectors and achieve better performance on highly occluded human detection.

Original languageEnglish
Article number8746171
Pages (from-to)2663-2673
Number of pages11
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume30
Issue number8
DOIs
Publication statusPublished - Aug 2020
Externally publishedYes

Keywords

  • convolutional neural network (CNN)
  • fully convolution network
  • Human detection
  • instance segmentation
  • object detection
  • semantic segmentation

Fingerprint

Dive into the research topics of 'Human Detection Aided by Deeply Learned Semantic Masks'. Together they form a unique fingerprint.

Cite this