Next Article in Journal
Covariance-Based Estimation for Clustered Sensor Networks Subject to Random Deception Attacks
Previous Article in Journal
Mobile Phone Usage Detection by ANN Trained with a Metaheuristic Algorithm
Previous Article in Special Issue
Learning the Cost Function for Foothold Selection in a Quadruped Robot
Article Menu

Export Article

Open AccessArticle

Dual-Resolution Dual-Path Convolutional Neural Networks for Fast Object Detection

1
School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China
2
School of Mathematics, Tianjin University, Tianjin 300072, China
3
WMG Data Science, University of Warwick, Conventry CV4 7AL, UK
*
Author to whom correspondence should be addressed.
Sensors 2019, 19(14), 3111; https://doi.org/10.3390/s19143111
Received: 5 June 2019 / Revised: 8 July 2019 / Accepted: 11 July 2019 / Published: 14 July 2019
(This article belongs to the Special Issue Semantic Representations for Behavior Analysis in Robotic System)
  |  
PDF [4728 KB, uploaded 14 July 2019]
  |  

Abstract

Downsampling input images is a simple trick to speed up visual object-detection algorithms, especially on robotic vision and applied mobile vision systems. However, this trick comes with a significant decline in accuracy. In this paper, dual-resolution dual-path Convolutional Neural Networks (CNNs), named DualNets, are proposed to bump up the accuracy of those detection applications. In contrast to previous methods that simply downsample the input images, DualNets explicitly take dual inputs in different resolutions and extract complementary visual features from these using dual CNN paths. The two paths in a DualNet are a backbone path and an auxiliary path that accepts larger inputs and then rapidly downsamples them to relatively small feature maps. With the help of the carefully designed auxiliary CNN paths in DualNets, auxiliary features are extracted from the larger input with controllable computation. Auxiliary features are then fused with the backbone features using a proposed progressive residual fusion strategy to enrich feature representation.This architecture, as the feature extractor, is further integrated with the Single Shot Detector (SSD) to accomplish latency-sensitive visual object-detection tasks. We evaluate the resulting detection pipeline on Pascal VOC and MS COCO benchmarks. Results show that the proposed DualNets can raise the accuracy of those CNN detection applications that are sensitive to computation payloads. View Full-Text
Keywords: dual-resolution; CNN; visual object detection; progressive fusion dual-resolution; CNN; visual object detection; progressive fusion
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

Pan, J.; Sun, H.; Song, Z.; Han, J. Dual-Resolution Dual-Path Convolutional Neural Networks for Fast Object Detection. Sensors 2019, 19, 3111.

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