Our purpose is to devise an algorithm for an Israeli Navy USV that will enable it to autonomously detect potential obstacles along its path.
Abstract
Our purpose is to devise an algorithm for an Israeli Navy USV that will enable it to autonomously detect potential obstacles along its path. 4 Cameras are installed on the USV therefore the obtained video is panoramic. This part main goal is to execute precursory processing, in order to tackle the object detection problem from a better starting point. The first step was finding the horizon in the videos. After accomplishing the first task, we need to stabilize the video.
Flowchart
Horizon Detection – Method I
- Drag a line across the frame
- Use predetermined conditions to stop the line
Results – Method I
Horizon Detection – Method II
- Detect lines across the picture
- Choose the best line
Results – Method II
Conclusion
- For our purposes, we prefer method II
- We are able to detect the horizon in the given videos to great accuracy