Power-lines-Detection

The task is to detect the images containing the power lines from set of given visible and infrared images.

Image-based power line detection is highly important for threat avoidance when the aerial vehicles fly in low altitude. However, it is very challenging for the requirements of high detection rates, low false alarms and real-time application.

Given two set of images one containing powerlines and the other not containing the power lines. The task is to detect and classify the images as containing powerlines or not.

Dataset

The Link to the Dataset- https://www.kaggle.com/c/recognizance-2/data

Accuray

The Train Accuracy is 0.9455.

The Test Accuracy is 0.96615.

Here is a Screenshot of Test Accuracy.

Test Accuracy

Built With

  • jupyter-notebook
Share this project:

Updates