Multi-Feature Fusion Approach for Object Classification on Oil/Gas Pipeline Right-of-Ways
Pipeline right of way (ROW) monitoring and safety pre-warning is a vital way to guarantee safe operation of the oil/gas transportation. Any construction equipment or heavy vehicle intrusion is a potential safety hazard to the pipeline infrastructure. Therefore, we propose a novel technique that can detect and classify any intrusion on oil/gas pipeline ROW. The detection part has been done based on our previous work, where we built a robust feature set to represent an object from two parts. Firstly, we divide an image into two circular regions with linearly increasing areas and pyramid levels. Then the histogram of the local feature is extracted for each sub-region and in multiple pyramid levels. After that a support vector machine with radial basis kernel is used to detect objects. For the classification part, the object can be represented by a robust fusion feature set, which is a combination of three different feature extraction techniques, histogram of oriented gradient (HOG), local binary pattern (LBP), and the color histogram of HSV (hue, saturation, value). Then a decision making model based support vector machine classifier is utilized for automatic object identification. It is observed that the proposed method provides promising results in identifying the objects that are present on the oil/gas pipeline ROW.
Vijayan K Asari, Almabrok Essa Essa
Primary Advisor's Department
Electrical and Computer Engineering
Stander Symposium poster
"Multi-Feature Fusion Approach for Object Classification on Oil/Gas Pipeline Right-of-Ways" (2018). Stander Symposium Posters. 1261.