An Assembled Detector Based on Geometrical Constraint for Power Component Recognition
AbstractThe intelligent inspection of power lines and other difficult-to-access structures and facilities has been greatly enhanced by the use of Unmanned Aerial Vehicles (UAVs), which allow inspection in a safe, efficient, and high-quality fashion. This paper analyzes the characteristics of a scene containing power equipment and the operation mode of UAVs. A low-cost virtual scene is created, and a training sample for the power-line components is generated quickly. Taking a vibration-damper as the main object, an assembled detector based on geometrical constraint (ADGC) is proposed and is used to analyze the virtual dataset. The geometric positional relationship is used as the constraint, and the Faster Region with Convolutional Neural Network (R-CNN), Deformable Part Model (DPM), and Haar cascade classifiers are combined, which allows the features of different classifiers, such as contour, shape, and texture to be fully used. By combining the characteristics of virtual data and real data using UAV images, the power components are detected by the ADGC. The result produced by the detector with relatively good performance can help expand the training set and achieve a better detection model. Moreover, this method can be smoothly transferred to other power-line facilities and other power-line scenarios. View Full-Text
Share & Cite This Article
Ji, Z.; Liao, Y.; Zheng, L.; Wu, L.; Yu, M.; Feng, Y. An Assembled Detector Based on Geometrical Constraint for Power Component Recognition. Sensors 2019, 19, 3517.
Ji Z, Liao Y, Zheng L, Wu L, Yu M, Feng Y. An Assembled Detector Based on Geometrical Constraint for Power Component Recognition. Sensors. 2019; 19(16):3517.Chicago/Turabian Style
Ji, Zheng; Liao, Yifan; Zheng, Li; Wu, Liang; Yu, Manzhu; Feng, Yanjie. 2019. "An Assembled Detector Based on Geometrical Constraint for Power Component Recognition." Sensors 19, no. 16: 3517.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.