Open AccessScene recognition under special traffic conditions based on deep multi‐task learning
Author(s) -
Hu Xiaochang,
Xu Xin,
Xiao Yongqian,
Chen Hongjun,
Zhang Hongjia
Publication year - 2020
Publication title -
the journal of engineering
Language(s) - English
Resource type - Journals
ISSN - 2051-3305
DOI - 10.1049/joe.2019.1191
Subject(s) - computer science , task (project management) , convolutional neural network , feature (linguistics) , artificial intelligence , deep learning , machine learning , pattern recognition (psychology) , engineering , systems engineering , linguistics , philosophy
Traffic scene recognition under special conditions is one of the most promising yet challenging tasks for autonomous driving systems. This study presents a deep multi‐task classification framework for scene recognition involving special traffic conditions. The framework incorporates four learning tasks where the recognition of special traffic scenes is the chief task and the time of occurrence (daytime or night‐time), the weather type and the road attribute are the three auxiliary tasks for improving the recognition performance. The four tasks share the feature map generated by a convolutional neural network followed by task‐specific sub‐networks which are merged in the end via a joint loss function. Moreover, a small dataset of typical special traffic conditions was built for training and testing the recognition model. Experimental results demonstrate that the proposed framework significantly improves the accuracy of scene recognition under special traffic conditions.