Abstract
The convolutional neural network (CNN) has shown excellent benefits in the classification of objects in the latest years. An important job in the context of intelligent transportation is to properly identify and classify vehicles from videos into various kinds (e.g., car, truck, bus, etc.). For monitoring, tracking and counting purposes, the classified vehicles can be further evaluated. At least two major difficulties stay, however; excluding the uninteresting area (e.g., swinging movement, noise, etc.) and designing an effective and precise system. In order to obviously differentiate the interesting region (moving car) from the un-interesting region (the rest of the area), we introduce a novel attention-based approach. Finally, to significantly increase the classification efficiency, we feed the deep CNN with the respective interesting region. We use several challenging outdoor sequences from the CDNET 2014 (baseline, bad weather and camera jitter classes), and our own dataset to assess the proposed approach. Experimental results show that it costs around ~85 fps in GPU (and ~50 fps in CPU) to classify moving vehicles and maintaining a highly accurate rate. Compared with other state-of-the-art object detection approaches, our method obtains a competitive detection accuracy. In addition, we also verify the result of the proposed approach by comparing with recent 3D CNN method, called saliency tubes.
Highlights
In the previous occasions, under the highways are mounted the detectors, inductive ground loops or laser scanners to classify the vehicle type [1]
Instead of utilizing the deep approach, our work proposes a completely distinct yet light approach by introducing a robust attention-based moving object detection in video sequences
The contributions of this paper are the following: a) We demonstrate that an effective detection of static surveillance cameras can significantly enhance the efficiency of the convolutional neural network (CNN) classification, b) Rather than the full frame dimension, the fine-grained classification of the vehicle only inferred interesting area, c) We have gathered a particular vehicle sample dataset that is appropriate for Indonesia areas
Summary
Under the highways are mounted the detectors, inductive ground loops or laser scanners to classify the vehicle type [1]. Due to a latest advance in an integrated surveillance system, the image dataset of vehicles on the highway is commonly accessible at low price. This system provides well-integrated CCTV and built-in communication. It is highly practical to provide an automatic vehicle type classification system using a computer vision method. Earlier researches related to the image classification tend to use a well-known model and image features, such as Bayesian [2], support vector machine [3]–[5], LBP (local binary pattern), SIFT [6], and etc.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
