Application of region-based video surveillance in smart cities using deep learning

Abstract

Smart video surveillance helps to build more robust smart city environment. The varied angle cameras act as smart sensors and collect visual data from smart city environment and transmit it for further visual analysis. The transmitted visual data is required to be in high quality for efficient analysis which is a challenging task while transmitting videos on low capacity bandwidth communication channels. In latest smart surveillance cameras, high quality of video transmission is maintained through various video encoding techniques such as high efficiency video coding. However, these video coding techniques still provide limited capabilities and the demand of high-quality based encoding for salient regions such as pedestrians, vehicles, cyclist/motorcyclist and road in video surveillance systems is still not met. This work is a contribution towards building an efficient salient region-based surveillance framework for smart cities. The proposed framework integrates a deep learning-based video surveillance technique that extracts salient regions from a video frame without information loss, and then encodes it in reduced size. We have applied this approach in diverse case studies environments of smart city to test the applicability of the framework. The successful result in terms of bitrate 56.92%, peak signal to noise ratio 5.35 bd and SR based segmentation accuracy of 92% and 96% for two different benchmark datasets is the outcome of proposed work. Consequently, the generation of less computational region-based video data makes it adaptable to improve surveillance solution in Smart Cities.

A Survey of Video Surveillance Systems in Smart City

“…Pre-processing involves various operations that have often been employed in previous studies, such as ROI segmentation, video compression, noise reduction, image resizing, and reformatting. Specifying an ROI retains the quality of the most pertinent information in a transmission and reduces the amount of data transmitted, which increases the efficiency and bandwidth of a network utility [28][29][30][31][32]. Video compression involves reducing the size of video data to make it easier to store and transmit without sacrificing too much quality, which optimizes the use of bandwidth and reduces the cost of data storage and the transmission time [29,33].…”

“…Specifying an ROI retains the quality of the most pertinent information in a transmission and reduces the amount of data transmitted, which increases the efficiency and bandwidth of a network utility [28][29][30][31][32]. Video compression involves reducing the size of video data to make it easier to store and transmit without sacrificing too much quality, which optimizes the use of bandwidth and reduces the cost of data storage and the transmission time [29,33]. Image resizing and reformatting effectively improves the quality of a video image by adjusting the brightness, contrast, and color balance.…”

Anomaly detection using edge computing in video surveillance system: review

“…DNNs are widely used in smart industries to detect manufacturing anomalies [ 65 ]. DNNs are a popular choice for smart city [ 160 ] including intelligent parking systems [ 49 ], vehicle classification and traffic flow prediction [ 11 ], to prevent vehicle accidents [ 36 ].…”

Multiple Moving Vehicles Tracking Algorithm with Attention Mechanism and Motion Model

“…The video frames of traffic roads contain numerous objects and intricate backgrounds. Objects frequently undergo foreground-background switches, which makes pre-tracking detection very challenging [6]. Consequently, there are numerous low-confidence detection boxes.…”