Multimed Tools Appl https://doi.org/10.1007/s11042-018-5701-6 Abnormal events’ detection in crowded scenes Mariem Gnouma 1 · Ridha Ejbali 1 · Mourad Zaied 1 Received: 6 June 2017 / Revised: 18 January 2018 / Accepted: 22 January 2018 © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract In this paper, two new methods are developed in order to detect and track unex- pected events in scenes. The process of detecting people may face some difficulties due to poor contrast, noise and the small size of the defects. For this purpose,the perfect knowledge of the geometry of these defects is an essential step in assessing the quality of detection. First, we collected statistical models of the element for each individual for time tracking of different people using the technique of Gaussian mixture model (GMM). Then we improved this method to detect and track the crowd(IGMM). Thereafter, we adopted two methods: the differential method of Lucas and Kanade(LK) and the method of optical flow estimation of Horn Schunck(HS) for optical flow representation. Then, we proposed a novel descrip- tor, named the Distribution of Magnitude of Optical Flow (DMOF) for anomalous events’ detection in the surveillance video. This descriptor represents an algorithm whose aim is to accelerate the action of abnormal events’ detection based on a local adjustment of the velocity field by manipulating the light intensity. Keywords Video surveillance · Anomaly detection · Crowd analysis · Tracking · Motion estimation 1 Introduction Surveillance cameras have invaded all public areas. These cameras needed a regular human presence to monitor the captured scenes and interference if necessary to alert those respon- sible in case of problems. These intelligent surveillance systems have not yet reached the desired level of suitability and robustness resulting from the huge amount of data analysis  Mariem Gnouma mariem.gnouma.tn@ieee.org 1 Research Team on Intelligent Machines, National School of Engineers of Gabes, University of Gabes, Gabes, Tunisia