A Fast Browsing System with Colour Image Enhancement for Surveillance Videos

Abstract

Surveillance cameras have been widely installed in large cities to monitor and record human activities for different applications. Since surveillance cameras often record all events 24 hours/day, it necessarily takes huge workforce watching surveillance videos to search for specific targets, thus a system that helps the user quickly look for targets of interest is highly demanded. This paper proposes a quick surveillance video browsing system with colour image enhancement. The basic idea is to collect all of moving objects which carry the most significant information in surveillance videos to construct a corresponding compact video. The compact video rearranges the spatiotemporal coordinates of moving objects to enhance the compression, but the temporal relationships among moving objects are still kept. The compact video can preserve the essential activities involved in the original surveillance video. This paper presents the details of browsing system and the approach to producing the compact video from a source surveillance video. At the end we will get the compact video with high resolution.

Introduction

I. INTRODUCTION

Surveillance cameras are widely installed in large cities to monitor and record human activities either in inside or outside environments. To efficiently utilize surveillance videos, how to extract valuable information from hundreds-of-hours videos becomes an important task. An intuitive method is to retrieve relevant segments according to the user’s queries in surveillance videos. Unfortunately; it is still difficult to automatically understand the user’s intentions and the video contents. Video retrieval based on the semantic level is still a challenging task. Video understanding and analysis is a key technology when we try to automatically extract valuable information from hundreds-of-hours surveillance videos. A basic method is to extract video segments that can represent most of informative contents of the source video. These informative segments are also known as key frames [1] in a video. The collection of key frames is the simplest way to compactly represent a video. Other possible methods for video understanding and analysis are called video summarization or video abstraction that extracts key frames based on a semantic level from a video and fuses them to form a shorter one. In a real application for the surveillance video, all of moving objects may not be negligible because it may be necessary to preserve them for the witness while crimes occur. In general, the most informative parts involved in surveillance videos are the foreground, i.e., the moving parts appearing in video frames. It is similar to a movie by watching the trailer and then determine whether to watch the movie or not. A. Rav-Acha et al. [5] proposed trailer: the user can roughly understand the contents of a the dynamic video synopsis to shorten videos by defining an energy function that describes activities of moving objects in a video. The energy function is minimized to optimally compress the corresponding behaviours of the moving objects to form the video synopsis. Their method can achieve a very large compression ratio in video representation, with destroying temporal relationship among objects. It may be difficult to focus on correct targets when the user looks for subjects of interest in surveillance videos. P. De Camp et al. [6] designed an interactive browsing and visualization system called House Fly for home- surveillance applications. Manual browsing of millions of hours of digitalized video from thousands of cameras proved impossible writhen a time sensed period but our proposed system is very beneficial for quick browsing of digitalized video.

II. BLOCK DIAGRAM OF PROPOSED SYSTEM

Block diagram of project is as shown in Figure 1. For each short-time segment from surveillance videos, a background model can be constructed under the assumptions of the fixed camera view and the unchanged delighting, and thus the corresponding background images are generated. We employ a background model for executing the difference between the current image and background image [11], to eliminate all same frames. The compact video is the collection of all compact frames. The compact video not only compactly represents for a copious surveillance video but also preserves all essential components of moving objects appeared in the source video. Using our system, the user can spend only several minutes watching the compact video instead of hours monitoring a large number of surveillance videos. This paper is organized as follows,

III. BACKGROUND SUBTRACTION METHOD

The background subtraction [18] method is the common method of motion detection. It is a technology that uses the difference of the current image and the background image to detect the motion region [9], and it is generally able to provide data included object information. The key of this method lies in the initialization and update of the background image. The effectiveness of both will affect the accuracy of test results. Therefore, this paper uses an effective method to initialize the background, and update the background in real time.

A. Background image initialization

There are many ways to obtain the initial background image. For example, with the first frame as the background directly, or the average pixel brightness of the first few frames as the background or using a background image sequences without the prospect of moving objects to estimate the background model parameters and so on. Among these methods, the time average method is the most commonly used method of the establishment of an initial background However, this method cannot deal with the background image (especially the region of frequent movement) which has the shadow problems. While the method of taking the median from continuous multi-frame can resolve this problem simply and effectively. So the median method is selected in this paper to initialize the background. Expression is as follows:

Conclusion

In this paper, we are reducing the video length of Surveillance video, by using Quick browsing system. We establish reliable background model for finding the motion between two frames and in pre-processing suppress the unwanted frames and enhance the image by using Adaptive filter, then finally reconstruct all those frames to video. (Quick Browsing system).

References

[1] Cheng-Chieh Chiang, Ming-Nan, Huei-Fang Yang,” A Quick Browsing System for Surveillance Videos” MVA2011 IAPR Conference on Machine Vision Applications, June 13-15, 2011, Nara, JAPAN. [2] Shizheng Wang, Jianwei Yang, Yanyun Zhao, Anni Cai, Stan Z.Li,” “A Surveillance Video Analysis and Storage Scheme for Scalable Synopsis Browsing” 2011 IEEE [3] International Conference on Computer Vision Workshops,978-1-4673-0063-6/11/$26.00 c 2011 IEEE. [4] Lijing Zhang, Yingli Liang “Motion human detection based on background Subtraction” 2010 Second International Workshop on Education Technology and Computer Science, 978-0-7695-3987-4/10 $26.00 © 2010 IEEE. [5] M.Dimitrijevic, \"Human body pose detection using Bayesian spatiotemporal templates,\" 2007 International Conference on Intelligent and Advanced Systems, 2008, pp.764-9. [6] Tao Jianguo, Yu Changhong, \"Real-Time Detection and Tracking of Moving Object,\" Intelligent Information Technology Application, 2008. [7] UTA \'08. Second International Symposium on Volume 2, 20-22 Dec. 2008 Page(s):860 – 863 [8] Niu Lianqiang and Nan Jiang, \"A moving objects detection algorithm based on improved background subtraction,\" Intelligent Systems Design and Applications, 2008. ISDA \'08. Eighth International Conference on Volume 3, 26-28 Nov. 2008 Page(s):604 – 607 [9] Axel Beaugendre, Hiroyoshi Miyano, Eiki Ishidera, Satoshi Goto.” Human Tracking System for Automatic Video Surveillance with Particle Filters” 978-1-4244-7456- 1/10/$26.00 ©2010 IEEE. [10] Y. Pritch, A. Rav-Acha, and S. Peleg, “No chronological Video Synopsis and Indexing,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, no. 11, pp. 1971-1984, 2008. [11] Rohit Nair, Benny Bing “Intelligent Activity Detection Techniques for Advanced HD Video Surveillance SystemsM.Dimitrijevic” [12] Color Image Enhancement with a Human Visual System Based Adaptive Filter Xinghao Ding1, Xinxin Wang2, Quan Xiao3 School of Information Science and Technology, Xiamen University Xiamen, China1dxh@xmu.edu.cn2p20414098@yahoo.com.cn 3xq_xmu@yahoo.com.cn 978-1-4244-5555-3/10/$26.00 ©2010 IEEE [13] Meylan L, Susstrunk S. High dynamic range image rendering with a retinex-based adaptive filter [J]. IEEE Transactions on Image Processing, 2006, 15(9): 2820- 2830. [14] Funt B, Ciurea F, McCann J. Retinex in MATLAB [J]. Journal of Electronic Imaging, 2004, 13(1): 48-57. [15] Kimmel R, Elad M, Shaked D, et al. A variational framework for Retime [J]. International Journal of Computer Vision, 2003, 52(1): 7-23. [16] Li Tao, Vijayan K. Asari. A Robust Image Enhancement Technique for Improving Image Visual Quality in Shadowed Scenes [A]. Proceedings of the 4th International Conference on Image and Video Retrieval[C]. Springer, Berlin, ALLEMAGNE,2005, vol.3568,395-404. [17] Wang Shou-jue, Ding Xing-hao, Liao Ying-hao, Guo dong-hui, A Novel Bio-inspired Algorithm for Color Image Enhancement, Act Electronic Sinica, 2008.10, Vol.36, No.10: 1970-1973.(in Chinese) [18] Novel Bio-inspired Algorithm for Color Image Enhancement, Acta Electronic Sinica, 2008.10, Vol.36, No.10: 1970-1973.(in Chinese) [19] Xu Jian, Chang Zhi-guo, An Adaptive and Nonlinear Technique for Color Image Enhancement. Computer Simulation, 2008.6, Vol.25, No.6: 214-216,227.(in Chinese) Gestures. Published a paper at International conference organized by ASTAR, INDIA held on May 2012 at Nagpur. Title: Feature E extraction in Trajectory Guided Recognition of Hand Gestures.

Copyright

Copyright © 2024 Prof. Kirti K. Kamble, Prof. Rahul G. Deshmukh, Prof. Bhavana Shinde. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.