The adoption of wireless sensor networks has brought a significant breakthrough in structural health monitoring, providing an effective alternative to the challenges associated with traditional cable-based sensors. In recent years, a growing interest in developing contactless, vision-based vibration sensors like video cameras, has led to advancements potentially alleviating the previously mentioned drawbacks. In this study, videos of a vibrating structural case study are created with a specific sampling rate, and then converted into a set of frames, so that local phase information can be extracted from all of the images. The motion matrix is then derived from the phase information; since the number of measuring points is usually greater than the number of the excited modes of the system, the problem can become over-determined. Therefore, by applying dimensionality reduction techniques, like e.g. the Non-Negative Matrix Factorization, the dimensions of the motion matrix are significantly reduced. Finally, by exploiting an output-only identification technique, modal parameters are computed. The performance of the proposed approach is assessed using numerical examples, to prove that the structural frequencies and mode shapes can be accurately identified.