Vehicle-Rear: A New Dataset to Explore Feature Fusion for Vehicle Identification Using Convolutional Neural Networks
Open Access
- 19 July 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 101065-101077
Abstract
This work addresses the problem of vehicle identification through non-overlapping cameras. As our main contribution, we introduce a novel dataset for vehicle identification, called Vehicle-Rear, that contains more than three hours of high-resolution videos, with accurate information about the make, model, color and year of nearly 3,000 vehicles, in addition to the position and identification of their license plates. To explore our dataset we design a two-stream Convolutional Neural Network (CNN) that simultaneously uses two of the most distinctive and persistent features available: the vehicle’s appearance and its license plate. This is an attempt to tackle a major problem: false alarms caused by vehicles with similar designs or by very close license plate identifiers. In the first network stream, shape similarities are identified by a Siamese CNN that uses a pair of low-resolution vehicle patches recorded by two different cameras. In the second stream, we use a CNN for Optical Character Recognition (OCR) to extract textual information, confidence scores, and string similarities from a pair of high-resolution license plate patches. Then, features from both streams are merged by a sequence of fully connected layers for decision. In our experiments, we compared the two-stream network against several well-known CNN architectures using single or multiple vehicle features. The architectures, trained models, and dataset are publicly available at https://github.com/icarofua/vehicle-rear .Keywords
All Related Versions
Funding Information
- National Council for Scientific and Technological Development (428333/2016-8, 313423/2017-2, 309292/2020-4, 308879/2020-1)
- Coordination for the Improvement of Higher Education Personnel (88887.516264/2020-00)
This publication has 52 references indexed in Scilit:
- Deep Metric Learning Using Triplet Network2015
- Evaluating Two-Stream CNN for Video Classification2015
- Learning to compare image patches via convolutional neural networks2015
- Hierarchical and Networked Vehicle Surveillance in ITS: A SurveyIEEE Transactions on Intelligent Transportation Systems, 2014
- A survey of approaches and trends in person re-identificationImage and Vision Computing, 2014
- T-HOG: An effective gradient-based descriptor for single line text regionsPattern Recognition, 2013
- Vehicle re-identification using wireless magnetic sensors: Algorithm revision, modifications and performance analysis2011
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Long Short-Term MemoryNeural Computation, 1997
- SIGNATURE VERIFICATION USING A “SIAMESE” TIME DELAY NEURAL NETWORKInternational Journal of Pattern Recognition and Artificial Intelligence, 1993