Multilevel Traffic State Detection in Traffic Surveillance System Using a Deep Residual Squeeze-and-Excitation Network and an Improved Triplet Loss
Open Access
- 22 June 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 114460-114474
Abstract
Although a substantial number of traffic videos have been accumulated via daily monitoring, deep learning is seldom utilized to process these data for multilevel traffic state detection. The application of deep learning is limited for two reasons: (1) the multilevel traffic state based on traffic images has not been defined. (2) The high noise information in traffic images and extremely similar features of adjacent traffic states hinder accurate detection. Based on this situation, A new definition of the image-based multilevel traffic state is proposed using the ratio of the vehicle areas to the road areas in a traffic image, and a standard image dataset, including various illuminations and vast scenes, are established. A deep residual network named TrafficNet, which is embedded with Squeeze-and-Excitation blocks and is learned by the improved triplet loss, is proposed for multilevel traffic state detection. The Squeeze-and-Excitation block effectively reduces the model’s attention to noise information and focuses on road areas that are associated with traffic features in an image. The improved triplet loss maps the learned features to a metric space where the distance between features of inter-class is larger than that within the same class, which improves the discrimination of features between adjacent traffic states. Relevant experiments prove that the performance of TrafficNet, whose accuracy (Acc) in classifying 10 traffic states reaches 94.27% with the testing dataset, is much better than that of traditional deep classification models, which do not include Squeeze-and-Excitation blocks or the improved triplet loss.Keywords
Funding Information
- National Natural Science Foundation of China (51978283)
- National Natural Science Foundation of China (51778242)
This publication has 38 references indexed in Scilit:
- Congested scene classification via efficient unsupervised feature learning and density estimationPattern Recognition, 2016
- Look and Think Twice: Capturing Top-Down Visual Attention with Feedback Convolutional Neural Networks2015
- Deep feature learning with relative distance comparison for person re-identificationPattern Recognition, 2015
- FaceNet: A unified embedding for face recognition and clustering2015
- Learning to rank in person re-identification with metric ensembles2015
- Online Anomaly Detection in Crowd Scenes via Structure AnalysisIEEE Transactions on Cybernetics, 2014
- Symbolic Classification of Traffic Video Shots2013
- A neural-based crowd estimation by hybrid global learning algorithmIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1999
- Determining optical flow using a differential methodImage and Vision Computing, 1997
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992