Real Time Image Encoding for Fast IOT (Internet of Things) Based Video Vigilance System

• Published in: Wireless personal communications Vol. 114; no. 2; pp. 995 - 1008
• Main Authors: Siddique, Ali Akbar, Mohy-Ud-Din, Zia, Qadri, M. Tahir
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2020; Springer Nature B.V
• Subjects: Algorithms; Communications Engineering; Computer Communication Networks; Digital media; Discrete cosine transform; Engineering; Frames (data processing); Internet of Things; Masking; Networks; Quality; Real time; Security systems; Signal to noise ratio; Signal,Image and Speech Processing; Surveillance; Video compression; Video data; Visibility; Internet of Things (IOT); Image compression; Video vigilance system; Temporal activity; Discrete cosine transform (DCT); Image processing
• ISSN: 0929-6212; 1572-834X
• DOI: 10.1007/s11277-020-07404-0

In recent times, technology has played an important role in almost every field as it advances. Law and order situation in the third world countries are extensively poor, and it is imperative to aid the institutions providing security by incorporating systems capable of identifying perpetrators and catch them. It is a well-known fact that security and surveillance industry is evolving, and most of the system are based on video surveillance rather than the basic alarm based solutions. Such systems are integrated with multiple cameras which provide live video surveillance features and in turn increases the visibility of the security systems. The Internet of Things (IOT) is helping to create an efficient security system capable of acquiring live video streams from multiple sensory sources. Due to the lack of available bandwidth, it may not be possible to acquire a video stream with decent quality. In this paper, a compression algorithm is proposed based on discrete cosine transform (DCT) and temporal reduction using motion vectors extracted from the incoming frames in order to achieve best compromise between quality and streaming time to properly indicate the perpetrator. Most of the time, it becomes impossible to seize the perpetrator due to the inferior video quality which makes him unidentifiable. Degraded video quality is mostly due to over compression. Implementation of the proposed algorithm is performed in MATLAB environment by acquiring the live video streams of the videos in real time. Mean Squared Error (MSE) and Peak Signal to Noise Ratio are calculated in order to elaborate the quality difference between the reconstructed frames by conventional means and with the incorporated Temporal Masking technique. By incorporating the proposed algorithm in the compression technique, it was discovered that it actually reduces the stream delay by 0.104 s with an acceptable Structural Similarity Index (SSIM) difference between the reconstructed frames acquired by conventional means and by proposed Temporal Masking Technique.