Open AccessFast single shot multibox detector and its application on vehicle counting system
Author(s) -
Chen Lili,
Zhang Zhengdao,
Peng Li
Publication year - 2018
Publication title -
iet intelligent transport systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.579
H-Index - 45
eISSN - 1751-9578
pISSN - 1751-956X
DOI - 10.1049/iet-its.2018.5005
Subject(s) - detector , computer science , single shot , object detection , pascal (unit) , artificial intelligence , computer vision , set (abstract data type) , pattern recognition (psychology) , telecommunications , physics , optics , programming language
Real‐time vehicle detection and counting of multiple types is a difficult problem. To solve this problem, this study presents an efficient method based on single shot detection (SSD) to construct a vehicle detection and counting system. The proposed method named Fast‐SSD first combines the Slim ResNet‐34 with Single Shot MultiBox Detector. Then the authors limit the location prediction at each cell in the feature map and modify the detection network. When the input size of the picture is 300 × 300, Fast‐SSD achieves the accuracy of 76.7 mAP on the PASCAL visual object classes 2007 test set. The network can be implemented at the speed of 20.8 FPS based on the GTX650Ti. Furthermore, they obtain the centre point of each type of vehicle which is detected by the Fast‐SSD model in the image and set the virtual loop detectors to specify the detection range. The number of vehicles is calculated when the centre of the vehicle passes the virtual loop detector. Results show that the vehicle detection accuracy achieves 99.3% and the classification accuracy is 98.9%.