Abstract
Decades of ongoing research have shown that background modelling is a very powerful technique, which is used in intelligent surveillance systems, in order to extract features of interest, known as foregrounds. In order to work with the dynamic nature of different scenes, many techniques of background modelling adopted the unsupervised approach of Gaussian Mixture Model with an iterative paradigm. Although the technique has had much success, a problem occurs in cases of sudden scene changes with high variation (e.g., illumination changes, camera jittering) that the model unknowingly and unnecessarily takes into account those effects and distorts the results. Therefore, this paper proposes an unsupervised, parallelized, and tensor-based approach that algorithmically works with entropy estimations. These entropy estimations are used in order to assess the uncertainty level of a constructed background, which predicts both the present and future variations from the inputs, thereby opting to use either the incoming frames to update the background or simply discard them. Our experiments suggest that this method is highly integrable into a surveillance system that consists of other functions and can be competitive with state-of-the-art methods in terms of processing speed.
Highlights
With static cameras, existing literature in computer vision has accounted for a wide range of applications that include vision-based traffic surveillance [1,2], pedestrian tracking [3,4], behavior analysis [5], and many more that have been nothing short of magnificence
It can be seen that the proposed method takes the first place overall across the different scenarios and even several of the scenarios (i.e., bad weather (BDW), TBL, BSL, dynamic background (DBG), SHD), whilst still in top-3 with night videos (NVD), low frame rate (LFR), and THM among the compared unsupervised methods
TensorMoG is highly effective in foreground segmentation on common cases whose dynamic contexts contain both constant ambient motions innate to the background, and object motions of interest
Summary
With static cameras, existing literature in computer vision has accounted for a wide range of applications that include vision-based traffic surveillance [1,2], pedestrian tracking [3,4], behavior analysis [5], and many more that have been nothing short of magnificence. Decades of ongoing research have shown that background modelling is a very powerful technique, which is used in intelligent surveillance systems, in order to extract features of interest, known as foregrounds. In order to work with the dynamic nature of different scenes, many techniques of background modelling adopted the unsupervised approach of Gaussian Mixture Model with an iterative paradigm. This paper proposes an unsupervised, parallelized, and tensor-based approach that algorithmically works with entropy estimations These entropy estimations are used in order to assess the uncertainty level of a constructed background, which predicts both the present and future variations from the inputs, thereby opting to use either the incoming frames to update the background or discard them. Improved adaptive Gaussian mixture model for background subtraction.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
