How much bandwidth does surveillance system require?

One of the main challenges in surveillance systems lies in the massive amount of video involved in providing potential key content with sufficient resolution. This paper shows that there exists a sweet spot, which we term critical video quality that can be used to reduce bitrate of video transmission without significantly affecting the accuracy of the surveillance tasks. We present a new city surveillance dataset which was divided into three types of scenarios, and we analyze subjective data collected via human subjective testing for object identification. These data are then used to create objective measurements (models) to drive video compression ratio based on the detection probability. The main idea is to find out the lowest bitrate of video transmission while maximizes the probability of detecting objects which are carried or abandoned. Experiment results shown that our generalized models can predict acceptable video quality for object identification in rational ways.

[1]  John R. Staver,et al.  Using Rasch Theory to Guide the Practice of Survey Development and Survey Data Analysis in Science Education and to Inform Science Reform Efforts: An Exemplar Utilizing STEBI Self-Efficacy Data. , 2011 .

[2]  Kjell Brunnström,et al.  VQeg validation and ITU standardization of objective perceptual video quality metrics [Standards in a Nutshell] , 2009, IEEE Signal Processing Magazine.

[3]  Pauline Faye,et al.  Perceptive free sorting and verbalization tasks with naive subjects: an alternative to descriptive mappings , 2004 .

[4]  Adam Schwartz,et al.  Chicago’s Video Surveillance Cameras: A Pervasive and Poorly Regulated Threat to Our Privacy , 2013 .

[5]  Mikolaj Leszczuk Optimising task-based video quality , 2012, Multimedia Tools and Applications.

[6]  D. Valentin,et al.  Perceptual dimensions of tactile textures. , 2003, Acta psychologica.

[7]  Jukka Häkkinen,et al.  What do users really perceive: probing the subjective image quality , 2006, Electronic Imaging.

[8]  Artur Przelaskowski,et al.  Evaluation of Quality Retaining Diagnostic Credibility for Surgery Video Recordings , 2008, VISUAL.

[9]  Philip H. S. Torr,et al.  BING: Binarized normed gradients for objectness estimation at 300fps , 2014, Computational Visual Media.

[10]  Jukka Häkkinen,et al.  Content and quality: Interpretation-based estimation of image quality , 2008, TAP.

[11]  George Ghinea,et al.  QoS impact on user perception and understanding of multimedia video clips , 1998, MULTIMEDIA '98.

[12]  C. Neves Categorical data analysis, third edition , 2014 .

[13]  George Ghinea,et al.  Measuring quality of perception in distributed multimedia: Verbalizers vs. imagers , 2008, Comput. Hum. Behav..

[14]  Dominik Strohmeier,et al.  Open Profiling of Quality: A Mixed Method Approach to Understanding Multimodal Quality Perception , 2010, Adv. Multim..

[15]  Mariusz Duplaga,et al.  Algorithm for Video Summarization of Bronchoscopy Procedures , 2011, Biomedical engineering online.

[16]  Lucjan Janowski,et al.  QoE as a Function of Frame Rate and Resolution Changes , 2010, FMN.

[17]  Carolyn G. Ford,et al.  Subjective video quality assessment methods for recognition tasks , 2009, Electronic Imaging.

[18]  A. Agresti,et al.  Categorical Data Analysis , 1991, International Encyclopedia of Statistical Science.

[19]  Wei Tsang Ooi,et al.  Video quality for face detection, recognition, and tracking , 2011, TOMCCAP.