Tecsis: Low-Cost Methodology To Distinguish Archaeological Findings

The automatic or semi-automatic research of archaeological findings includes some methodologies and algorithms of the Computer Vision. Reconstruction of a scene is one of the key step to get the solution to that challenge. This paper will address a methodology to reconstruction underwater scenes with mosaicingtechniques. The reconstruction of scene will be the video-mosaic of sea bottom landscapes starting from single video frames. The methodology is based on the evaluation of the optic °ow in between frames, and its motion estimation has been evaluated on the extracted features from the common areas of consecutivepairs frames. This approach carried out the motion model from a geometric projection framework. The camera movement estimation is a second key point in the mosaicing problem. The used methodology have to be enough robust to achieve a good performance because of the high level of noise and turbulence involved in sea bottom video acquisition. For this purpose geometrical transformations have been usedto map each frame global into a unique big common reference frame which dimensions are similar to the union of frames.