Journal
PATTERN RECOGNITION LETTERS
Volume 167, Issue -, Pages 45-52Publisher
ELSEVIER
DOI: 10.1016/j.patrec.2023.01.015
Keywords
Object detection; Small scale; Super -resolution; Convolutional neural networks
Categories
Ask authors/readers for more resources
The use of technology in road management systems has led to real-time visual information in thousands of locations on road networks. Convolutional neural networks have greatly improved object detection in this field, overcoming deficiencies in pre-trained models for detecting small objects. However, retraining the model with manual labeling from each IP camera on the extensive road network is not feasible. Our proposal introduces an automatic procedure for detecting small-scale objects in traffic sequences.
The exponential increase in the use of technology in road management systems has led to real-time vi-sual information in thousands of locations on road networks. A previous step in preventing or detecting accidents involves identifying vehicles on the road. The application of convolutional neural networks in object detection has significantly improved this field, enhancing classical computer vision techniques. Al-though, there are deficiencies due to the low detection rate provided by the available pre-trained models, especially for small objects. The main drawback is that they require manual labeling of the vehicles that appear in the images from each IP camera located on the road network to retrain the model. This task is not feasible if we have thousands of cameras distributed across the extensive road network of each nation or state. Our proposal presented a new automatic procedure for detecting small-scale objects in traffic sequences. In the first stage, vehicle patterns detected from a set of frames are generated automatically through an offline process, using super-resolution techniques and pre-trained object detection networks. Subsequently, the object detection model is retrained with the previously obtained data, adapting it to the analyzed scene. Finally, already online and in real-time, the retrained model is used in the rest of the traffic sequence or the video stream generated by the camera. This framework has been successfully tested on the NGSIM and the GRAM datasets.(c) 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license ( http://creativecommons.org/licenses/by/4.0/ )
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available