Logo MachVis

Person Re-Identification for Intelligent Visual Surveillance

Person Re-Identification for Intelligent Visual Surveillance

Person Re-Identification for Intelligent Visual Surveillance


Large networks of cameras are increasingly deployed in public places like airports, railway stations, college campuses and office buildings. These cameras typically span large geospatial areas and have non-overlapping fields-of-views (FOVs) to provide enhanced coverage. Such networks provide huge amounts of video data, which is either manually monitored by law enforcement officers or utilized after the fact for forensic purposes. Human monitoring of these videos is erroneous, time consuming and expensive, thereby severely reducing the effectiveness of surveillance. Automated analysis of large amounts of video data can not only process the data faster but significantly improve the quality of surveillance. Video analysis can enable long term activity and behavior characterization of people in a scene. Such analysis is required for high-level surveillance tasks like suspicious activity detection or undesirable event prediction for timely alerts to security personnel making surveillance more pro-active.
Understanding of a surveillance scene through computer vision requires the ability to track people across multiple cameras, perform crowd movement analysis and activity detection. Tracking people across multiple cameras is essential for wide area scene analytics and person re-identification is a fundamental aspect of multi-camera tracking. Re-identification (Re-ID) is defined as a process of establishing correspondence between images of a person taken from different cameras. It is used to determine whether instances captured by different cameras belong to the same person, in other words, assign a stable ID to different instances of the person.


Person Re-Identification Generic Pipeline: (a) Input Images/video feed from non-overlapping camera views; (b) Person detection in natural scene; (c) Person representation using discriminative features; (d) Person matching using similarity/dissimilarity learning.


  • Dr Muhammad Moazam Faraz
  • Dr Muhammad Shahzad


  • Ms Nazia Pervaiz (PhD Student)
  • Asmat Zahra (PhD Student)
  • Rao Faizan
  • Wajeeha Ansar
  • Saadia Batool
  • Saba Mumtaz
  • Naima Mubariz

Selected Publications

  • N. Pervaiz, M. M. Fraz, M. Shahzad , “Person Re-Identification Using Hybrid Representation Reinforced by Metric Learning”, IEEE Access, Vol. 7 , No. 1, Dec, 2018. IF: 4.098
  • N. Pervaiz, M. M. Fraz, M. Shahzad , “Hierarchical Refined Local Associations for Robust Person Re-Identification”, Proceedings of the International Conference on Robotics and Automation in Industry (ICRAI), Oct, 2019, Islamabad , Pakistan.
  • S. Batool, M. Z. Ali ; M. Shahzad and M. M. Fraz , “End to End Person Re-Identification for Automated Visual Surveillance”, Proceedings of the International Conference on Image Processing, Applications and Systems (IPAS), Dec, 2018, Sophia Antipolis , France.
  • W. Anser, M M Fraz, M Shahzad , , “Two Stream Deep CNN-RNN Attentive Pooling Architecture for Video-based Person Re-identification”, Proceedings of the 23rd Iberoamerican Congress on Pattern Recognition, Nov, 2018, Madrid , Spain.
  • Naima Mubariz, Saba Mumtaz, M. M. Hamayun and M. M. Fraz , , “Optimization of Person Re-Identification through Visual Descriptors”, Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Jan, 2018, Funchal, Madeira , Portugal.
  • S. Mumtaz, N. Mubariz , S. Saleem, M. M. Fraz , , “Weighted hybrid features for person re-identification”, Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications (IPTA), 2017 , Dec, 2017, Montreal, QC , Canada.