IoT-Driven Automated Object Detection Algorithm for Urban Surveillance Systems in Smart Cities

Abstract

Automated object detection algorithm is an important research challenge in intelligent urban surveillance systems for IoT and smart cities applications. In particular, smart vehicle license plate recognition (VLPR) and vehicle detection are recognized as core research issues of these IoT-driven intelligent urban surveillance systems. They are key techniques in most of the traffic related IoT applications, such as road traffic real-time monitoring, security control of restricted areas, automatic parking access control, searching stolen vehicles, etc. In this paper, we propose a novel unified method of automated object detection for urban surveillance systems. We use this novel method to determine and pick out the highest energy frequency areas of the images from the digital camera imaging sensors, that is, either to pick the vehicle license plates or the vehicles out from the images. Our proposed method can not only help to detect object vehicles rapidly and accurately, but also can be used to reduce big data volume needed to be stored in urban surveillance systems.

Big data oriented novel background subtraction algorithm for urban surveillance systems

“…Another advantage of our method is that it does not depend on object motion; even nonmoving objects are detected automatically. In [11], we proposed a simple filter for detecting vehicles or license plates from captured images. We found that an object (for example, a vehicle or human being) is normally the highest energy frequency aspect of an image and the energy frequency curves decrease sharply outside object boundaries.…”

“…To do so, the computer determines whether or not this image can be used as a background. Using the pretreatment method proposed in [11], we first transfer the original image into a gray-scale image to reduce the image data that must be calculated. After generating the grayscale image, we calculate its gradient using P x to denote differences in the x direction (horizontal) and P y to denote differences in the y direction (vertical).…”

“…As in [11], after calculating the gradients of both the horizontal and vertical directions, for every pixel, we obtain the overall gradient of each pixel as follows:…”

“…In [11], we designed a smart filter based algorithm that scans and identifies the object areas in an image. This method was inspired by the mathematical definition of intercorrelation and the function pulse δ(x), which has the following important characteristic:…”

Metropolitan intelligent surveillance systems for urban areas by harnessing IoT and edge computing paradigms

“…Similarly, in the work of Lu et al, traffic conditions of an urban area are monitored in real time by exploiting the capabilities of smart cameras that are able to preprocess and filter information before sending them to a remote server. Furthermore, the work of Hu and Ni introduced an algorithm for license plate recognition through smart cameras on the basis of a lightweight filter for digital camera sensors to reduce network bandwidth and latency. As far as large metropolitan areas are concerned, data and information fusion techniques on the server/cloud side can be used to properly investigate underlying physical phenomena and events captured by an ISS as discussed in the work of Fan et al Indeed, enhanced elaboration can be performed by exploiting big data techniques as shown in the work of Shao et al, where a novel workflow exploiting (big) surveillance data based on event detection and alarming messages from front‐end smart cameras is proposed.…”