Smoky vehicle emissions remain a significant contributor in many areas where air quality standards are under threat. The existing smoky vehicle detection methods are inefficiency and with high false alarm rate. This study presents an automatic detection method of smoky vehicles from traffic surveillance video based on vehicle rear detection and multi-feature fusion. In this method, the Vibe background subtraction algorithm is utilised to detect foreground objects, and some rules are used to remove non-vehicle objects. To obtain the key region behind the vehicle rear where the most possible has black smoke in, an improved integral projection method is proposed to detect vehicle rear. To analyse if the key region has black smoke, three groups of representative features are designed and extracted to distinguish smoky vehicles and non-smoke vehicles. More specifically, the features include the artificial features based on deep investigation of smoky vehicles, the statistical features based on grey-level co-occurrence matrix, and the frequency domain features based on discrete wavelet transform (DWT). Finally, support vector machine is used as the classifier for the extracted features. The experimental results show that the proposed method achieves lower false alarm rate than the existing smoke detection methods.
Automatic smoky vehicle detection from traffic surveillance video based on vehicle rear detection and multi-feature fusion
IET Intelligent Transport Systems ; 13 , 2 ; 252-259
2018-10-18
8 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
classifier , nonvehicle object removal , image fusion , image representation , smoky vehicle emissions , representative features , Vibe background subtraction algorithm , grey-level co-occurrence matrix , DWT , foreground object detection , statistical features , traffic surveillance video , automatic smoky vehicle detection method , improved integral projection method , feature extraction , black smoke , object detection , frequency-domain analysis , vehicle rear detection , video surveillance , image classification , road vehicles , statistical analysis , support vector machine , artificial features , discrete wavelet transforms , matrix algebra , discrete wavelet transform , multifeature fusion , traffic engineering computing , air quality standards , frequency domain features , high false alarm rate
Metadata by IET is licensed under CC BY 3.0