Reconstructing power lines from images

We present a method for reconstructing overhead power lines from images. The solution to this problem has a deep impact over the strategies adopted to monitor the many thousand of kilometers of power lines where nowadays the only effective solution requires a high-end laser scanner. The difficulty with image based algorithms is that images of wires of the power lines typically do not have point features to match among different images. We use a Structure from Motion algorithm to retrieve the approximate camera poses and then formulate a minimization problem aimed to refine the camera poses so that the image of the wires project consistently on a 3D hypothesis.