TRAFFIC SCENE RECOGNITION BASED ON DEEP CNN AND VLAD SPATIAL PYRAMIDS

WU, F, Yan, S, Smith, JS ORCID: 0000-0002-0212-2365 and Zhang, B (2017) TRAFFIC SCENE RECOGNITION BASED ON DEEP CNN AND VLAD SPATIAL PYRAMIDS. In: International Conference of Machine Learning and Cybernetics (ICMLC) 2017, 2017-7-9 - 2017-7-12, Ningbo, China.

Text trafficscene_v3.doc - Author Accepted Manuscript Download (3MB)

Abstract

Traffic scene recognition is an important and challenging issue in Intelligent Transportation Systems (ITS). Recently, Convolutional Neural Network (CNN) models have achieved great success in many applications, including scene classification. The remarkable representational learning capability of CNN remains to be further explored for solving real-world problems. Vector of Locally Aggregated Descriptors (VLAD) encoding has also proved to be a powerful method in catching global contextual information. In this paper, we attempted to solve the traffic scene recognition problem by combining the features representational capabilities of CNN with the VLAD encoding scheme. More specifically, the CNN features of image patches generated by a region proposal algorithm are encoded by applying VLAD, which subsequently represent an image in a compact representation. To catch the spatial information, spatial pyramids are exploited to encode CNN features. We experimented with a dataset of 10 categories of traffic scenes, with satisfactory categorization performances.

Item Type:	Conference or Workshop Item (Unspecified)
Uncontrolled Keywords:	Traffic scene recognition, Convolutional Neural Network, Vector of Locally Aggregated Descriptors encoding
Depositing User:	Symplectic Admin
Date Deposited:	22 May 2017 10:15
Last Modified:	19 Jan 2023 07:04
DOI:	10.1109/icmlc.2017.8107758
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3007598