期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2020
卷号：11
期号：3
DOI：10.14569/IJACSA.2020.0110303
出版社：Science and Information Society (SAI)
摘要：Despite recent advances in multiple object tracking and pedestrian tracking, multiple-face tracking remains a challenging problem. In this work, the authors propose a framework to solve the problem in semi-online manner (the framework runs in real-time speed with two-second delay). The proposed framework consists of two stages: detection-tracking and tracklet-tracklet association. Detection-tracking stage is for creating short tracklets. Tracklet-tracklet association is for merging and assigning identifications to those tracklets. To the best of the authors’ knowledge, the authors make contributions in three aspects: 1) the authors adopt a principle often used in online approaches as a part of the framework and introduce a tracklet-tracklet association stage to leverage future information; 2) the authors propose a motion affinity metric to compare trajectories of two tracklets; 3) the authors propose an efficient way to employ deep features in comparing tracklets of faces. The authors achieved 78.7% precision plot AUC, 68.1% success plot AUC on MobiFace dataset (test set). On OTB dataset, the authors achieved 78.2% and 72.5% precision plot AUC, 51.9% and 43.9% success plot AUC on normal and difficult face subsets, respectively. The average speed was maintained at around 44 FPS. In comparison to the state-of-the-art methods, the proposed framework’s performance maintains high rankings in top 3 on two datasets while keeping the processing speed higher than the other methods in top 3.
关键词：Face tracking; face re-identification; detection-tracking; tracklet-tracklet association
