A training algorithm for optimal margin classifiers
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
The nature of statistical learning theory
The nature of statistical learning theory
Machine Learning
Example-Based Object Detection in Images by Components
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Image Processing
Training Support Vector Machines: an Application to Face Detection
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Digital Image Processing: PIKS Scientific Inside
Digital Image Processing: PIKS Scientific Inside
Pedestrian detection and tracking with night vision
IEEE Transactions on Intelligent Transportation Systems
| Hi-index | 0.00 |
Video surveillance (VS) of electric power lines along with its accessories such as insulators has emerged as a potential alternative for the traditional practice of on-site physical detection. There has been a paradigm shift in electric substation automation using substation monitoring system (SMS). Since the damaged insulators severely affect the distribution system performance in terms of reduction in voltage as well as flow of leakage currents, therefore, the incorporation of insulator health as an augmented feature in SMS would improve the quality and reliability of power supply. By using information technology, the automation of insulator monitoring of power system is made faster to recover the fault system immediately. This paper presents a methodology for insulator condition analysis based on VS combined with wavelet coefficient differentiator (WCD) for SMS purposes. The case studies and results contained herein corroborate the efficacy of the proposed methodology to dispense with the conventional on-site physical methods, which are not only tedious, but also time-consuming.