Engineering Vehicles Detection Based on Modified Faster R-CNN for Power Grid Surveillance

Engineering vehicles intrusion detection is a key problem for the security of power grid operation, which can warn of the regional invasion and prevent external damage from architectural construction. In this paper, the authors propose an intelligent surveillance method based on the framework of Faster R-CNN for locating and identifying the invading engineering vehicles. In our detection task, the type of the objects is varied and the monitoring scene is large and complex. In order to solve these challenging problems, the authors modify the network structure of the object detection model by adjusting the position of the ROI pooling layer. The convolutional layer is added to the feature classification part to improve the accuracy of the detection model. The authors verify that increasing the depth of the feature classification part is effective for detecting engineering vehicles in realistic transmission lines corridors. The authors also collect plenty of scene images taken from the monitor site and label the objects to create a fine-tuned dataset. The authors train the modified deep detection model based on the technology of transfer learning and conduct training and test on the newly labeled dataset. Experimental results show that the proposed intelligent surveillance method can detect engineering vehicles with high accuracy and a low false alarm rate, which can be used for the early warning of power grid surveillance.

Language

  • English

Media Info

  • Media Type: Web
  • Features: Figures; Photos; References; Tables;
  • Pagination: 14p
  • Serial:
  • Publication flags:

    Open Access (libre)

Subject/Index Terms

Filing Info

  • Accession Number: 01678716
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Jul 26 2018 11:48AM