Next Article in Journal
A Fast Linearly Wavelength Step-Swept Light Source Based on Recirculating Frequency Shifter and Its Application to FBG Sensor Interrogation
Next Article in Special Issue
Deep Learning-Based Multinational Banknote Type and Fitness Classification with the Combined Images by Visible-Light Reflection and Infrared-Light Transmission Image Sensors
Previous Article in Journal
Carrier-to-Noise-Threshold Filtering on Off-Shore Wind Lidar Measurements
Previous Article in Special Issue
Real-Time Semantic Segmentation for Fisheye Urban Driving Images Based on ERFNet
Article Menu
Issue 3 (February-1) cover image

Export Article

Open AccessArticle

Vehicle Detection in Urban Traffic Surveillance Images Based on Convolutional Neural Networks with Feature Concatenation

School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, Beijing 100083, China
*
Author to whom correspondence should be addressed.
Sensors 2019, 19(3), 594; https://doi.org/10.3390/s19030594
Received: 4 January 2019 / Revised: 24 January 2019 / Accepted: 29 January 2019 / Published: 30 January 2019
(This article belongs to the Special Issue Deep Learning-Based Image Sensors)
  |  
PDF [7220 KB, uploaded 12 February 2019]
  |  

Abstract

Vehicle detection with category inference on video sequence data is an important but challenging task for urban traffic surveillance. The difficulty of this task lies in the fact that it requires accurate localization of relatively small vehicles in complex scenes and expects real-time detection. In this paper, we present a vehicle detection framework that improves the performance of the conventional Single Shot MultiBox Detector (SSD), which effectively detects different types of vehicles in real-time. Our approach, which proposes the use of different feature extractors for localization and classification tasks in a single network, and to enhance these two feature extractors through deconvolution (D) and pooling (P) between layers in the feature pyramid, is denoted as DP-SSD. In addition, we extend the scope of the default box by adjusting its scale so that smaller default boxes can be exploited to guide DP-SSD training. Experimental results on the UA-DETRAC and KITTI datasets demonstrate that DP-SSD can achieve efficient vehicle detection for real-world traffic surveillance data in real-time. For the UA-DETRAC test set trained with UA-DETRAC trainval set, DP-SSD with the input size of 300 × 300 achieves 75.43% mAP (mean average precision) at the speed of 50.47 FPS (frames per second), and the framework with a 512 × 512 sized input reaches 77.94% mAP at 25.12 FPS using an NVIDIA GeForce GTX 1080Ti GPU. The DP-SSD shows comparable accuracy, which is better than those of the compared state-of-the-art models, except for YOLOv3. View Full-Text
Keywords: vehicle detection; feature concatenation; default box; convolutional neural network; real-time vehicle detection; feature concatenation; default box; convolutional neural network; real-time
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

Zhang, F.; Li, C.; Yang, F. Vehicle Detection in Urban Traffic Surveillance Images Based on Convolutional Neural Networks with Feature Concatenation. Sensors 2019, 19, 594.

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