This paper presents an enhanced methodology for Recurrence Quantification Analysis (RQA) designed specifically for video analysis. By utilizing image quality metrics, with a focus on the Peak Signal-to-Noise Ratio (PSNR), we determine meaningful values for the RQA threshold ε, a critical factor for successful image processing. Utilizing the False Nearest Neighbors (FNN) technique, we identify the optimal embedding dimension D for each patch within the video frames. Our approach produces a heatmap that visualizes temporal recurrence information for each video patch.
@INPROCEEDINGS{10647991, author={Kyprianidi, T. and Doutsi, E. and Tzagkarakis, G. and Tsakalides, P.}, booktitle={2024 IEEE International Conference on Image Processing (ICIP)}, title={Exploring the Potential of Recurrence Quantification Analysis for Video Analysis and Motion Detection}, year={2024}, volume={}, number={}, pages={2606-2612}, keywords={Measurement;Image quality;Heating systems;Visualization;PSNR;Image processing;Redundancy;Recurrence Quantification Analysis;Motion detection;video analysis;embedded dimension;temporal redundancy}, doi={10.1109/ICIP51287.2024.10647991}}