Automatic recognition of scenes with power line wires in real life aerial images using DCT-based features

Autor: Ömer Emre Yetgin, Ömer Nezih Gerek
Přispěvatelé: Anadolu Üniversitesi, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü, Gerek, Ömer Nezih
Rok vydání: 2018
Předmět:
Computer science
Computer Vision
Feature extraction
02 engineering and technology
Image (mathematics)
Matrix (mathematics)
0203 mechanical engineering
Artificial Intelligence
Image Features
0202 electrical engineering
electronic engineering
information engineering
Discrete cosine transform
Computer vision
Electrical and Electronic Engineering
020301 aerospace & aeronautics
business.industry
Applied Mathematics
Dct
Pattern recognition
Classification
Power (physics)
Power Line Wires Recognition
Maxima and minima
Feature Extraction/Selection
Electric power transmission
Computational Theory and Mathematics
Signal Processing
Line (geometry)
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
Statistics
Probability and Uncertainty
business
Zdroj: Digital Signal Processing. 77:102-119
ISSN: 1051-2004
Popis: WOS: 000432635500011
This paper presents results of power line scene detection methods that use new feature extraction/selection strategies based on Discrete Cosine Transform (DCT) of scenes obtained from aircraft-based cameras. Whenever a scene from an aircraft contains power lines (may that be a visible-light image or infrared), the spectrum image or DCT matrix naturally exhibits coefficients with large magnitudes. On the other hand, since the direction of cables is arbitrary, the location of the DCT extrema may appear in different positions. This work attacks the problem of extracting signatures from the DCT coefficients by systematically changing the DCT matrix sizes and applying known classifiers to the DCT sub-matrices. These sub-matrices were selected at six different sizes (4 x 4, 8 x 8, 16 x 16, 32 x 32, 64 x 64, 128 x 128) with three types of starting points: (i) top-leftner (around DC), (ii) bottom-right corner (high frequency) and (iii) block-wise scanning the complete DCT matrix. A thorough dataset that contains thousands of aerial images with cables are used for testing the efficiencies of these DCT region selection approaches. Fast and successful detection performances are obtained and presented
Anadolu University Scientific Research Project Commission [1508F598]
This work is supported by Anadolu University Scientific Research Project Commission under the grant No. 1508F598. The authors would like to thank Turkish Electricity Transmission Company for providing power line videos. The authors also thank Assistant Professor Cihan TOPAL for his valuable support in technical issues and Fatih SAGLAM for his valuable discussions during development of the algorithms.
Databáze: OpenAIRE
Externí odkaz: