Person Re-identification Using Masked Keypoints
In this work, a method for person re-identification from surveillance videos is proposed. In this approach, person detection is based on moving objects from sequences of images, and on incorporating a feature extraction technique that can distinguish distinct persons according to their physical appearance by using masked images that reduce noise from the background. Our approach uses keypoints to build an image’s descriptor so that the best discriminative keypoints can be identified between different persons. Experiments using our masked re-identification method show significant improvements in the recognition rate when masked frames are used to reduce noise of the second plane.
This research was supported by FONDECYT (Chile) under grant number 1170002: “An effective Linguistically-motivated computational model for opinion retrieval in sentiment analysis tasks”.
- 1.Bauml, M., Stiefelhagen, R.: Evaluation of local features for person re-identification in image sequences. In: 10th IEEE International Conference on Advanced Video and Signal-Based Surveillance, Klagenfurt, Austria (2011)Google Scholar
- 4.Farenzena, M., Bazzani, L., Perina, A., Murino, V., Cristani, M.: Person re-identification by symmetry-driven accumulation of local features. In: IEEE Computer Vision and Pattern Recognition, San Francisco, CA (2010)Google Scholar
- 5.Hamdoun, O., Moutarde, F., Stanciulescu, B., Steux, B.: Person re-identification in multi-camera system by signature based on interest point descriptors collected on short video sequences. In: Second ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC), pp. 1–6 (2008)Google Scholar
- 6.Karanam, S., Yang, L., Richard, J.: Person re-identification with discriminatively trained viewpoint invariant dictionaries. In: IEEE International Conference on Computer Vision (2015)Google Scholar
- 12.Munaro, M., Ghidoni, S., Tartaro, D., Menegatti, E.: A feature-based approach to people re-identification using skeleton keypoints. In: IEEE International Conference on Robotics and Automation, Hong Kong, China (2014)Google Scholar
- 13.Pedagadi, S., Orwell, J., Velastin, S., Boghossian, B.: Local fisher discriminant analysis for pedestrian re-identification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3318–3325, June 2013Google Scholar
- 14.Xiao, L., Mingli, S., Dacheng, T., Xingchen, Z., Chen, C., Jiajun, B.: Semi-supervised coupled dictionary learning for person re-identification. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3550–3557, June 2014Google Scholar