Next Article in Journal
Automatic Fabric Defect Detection with a Multi-Scale Convolutional Denoising Autoencoder Network Model
Next Article in Special Issue
Comparative Analysis of Warp Function for Digital Image Correlation-Based Accurate Single-Shot 3D Shape Measurement
Previous Article in Journal
Mobile Sinks Assisted Geographic and Opportunistic Routing Based Interference Avoidance for Underwater Wireless Sensor Network
Previous Article in Special Issue
Dynamic Non-Rigid Objects Reconstruction with a Single RGB-D Sensor
Article Menu
Issue 4 (April) cover image

Export Article

Open AccessArticle
Sensors 2018, 18(4), 1063; https://doi.org/10.3390/s18041063

Delving Deep into Multiscale Pedestrian Detection via Single Scale Feature Maps

1
National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China, Chengdu 611731, China
2
Department of Computer Science, University College London, London WC1E 6BT, UK
3
Department of Computer Science & Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
4
Department of MOE Research Center for Software/Hardware Co-Design Engineering and Application, East China Normal University, Shanghai 200062, China
*
Author to whom correspondence should be addressed.
Received: 28 February 2018 / Revised: 25 March 2018 / Accepted: 26 March 2018 / Published: 2 April 2018
(This article belongs to the Special Issue Visual Sensors)
Full-Text   |   PDF [1820 KB, uploaded 3 May 2018]   |  

Abstract

The standard pipeline in pedestrian detection is sliding a pedestrian model on an image feature pyramid to detect pedestrians of different scales. In this pipeline, feature pyramid construction is time consuming and becomes the bottleneck for fast detection. Recently, a method called multiresolution filtered channels (MRFC) was proposed which only used single scale feature maps to achieve fast detection. However, there are two shortcomings in MRFC which limit its accuracy. One is that the receptive field correspondence in different scales is weak. Another is that the features used are not scale invariance. In this paper, two solutions are proposed to tackle with the two shortcomings respectively. Specifically, scale-aware pooling is proposed to make a better receptive field correspondence, and soft decision tree is proposed to relive scale variance problem. When coupled with efficient sliding window classification strategy, our detector achieves fast detecting speed at the same time with state-of-the-art accuracy. View Full-Text
Keywords: pedestrian detection; boosted decision tree; scale invariance; receptive field correspondence; soft decision tree pedestrian detection; boosted decision tree; scale invariance; receptive field correspondence; soft decision tree
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Fu, X.; Yu, R.; Zhang, W.; Wu, J.; Shao, S. Delving Deep into Multiscale Pedestrian Detection via Single Scale Feature Maps. Sensors 2018, 18, 1063.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top