Volume XLII-4/W18
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W18, 741–744, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W18-741-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W18, 741–744, 2019
https://doi.org/10.5194/isprs-archives-XLII-4-W18-741-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

  18 Oct 2019

18 Oct 2019

AUTOMATIC VEHICLE RECOGNITION FOR URBAN TRAFFIC MANAGEMENT

M. Mohammadi1, F. Tabib Mahmoudi1, and M. Hedayatifard2 M. Mohammadi et al.
  • 1Dept. of Geomatic Engineering, Civil Engineering Faculty, Shahid Rajaee Teacher Training University, Tehran, Iran
  • 2Geodesy and Geomatic Engineering Faculty, Khaje Nasir Toosi University, Tehran, Iran

Keywords: Vehicle Detection, Image pyramid, Segmentation, Object Based Image Analysis, structural features

Abstract. Automatic vehicle recognition has an important role for many applications such as supervision, traffic management and rescue tasks. The ability of online supervision on the distribution of vehicles in urban environments prevents traffic, which in turn reduces air pollution and noise. However, this is extremely challenging due to the small size of vehicles, their different types and orientations, and the visual similarity to some other objects in very high resolution images. In this paper, an automatic vehicle recognition algorithm is proposed based on very high spatial resolution aerial images. In the first step of the proposed method, by generating the image pyramid, the candidate regions of the vehicles are recognized. Then, performing reverse pyramid, decision level fusion of the vehicle candidates and the land use/cover classification results of the original image resolution are performed in order to modify recognized vehicle regions. For evaluating the performance of the proposed method in this study, Ultracam aerial imagery with spatial resolution of 11 cm and 3 spectral bands have been used. Comparing the obtained vehicle recognition results from the proposed decision fusion algorithm with some manually selected vehicle regions confirm the accuracy of about %80. Moreover, the %78.87 and 0.71 are respectively the values for overall accuracy and Kappa coefficient of the obtained land use/cover classification map from decision fusion algorithm.