Real-Time Abnormal Object Detection for Video Surveillance in Smart Cities

Abstract

With the adaptation of video surveillance in many areas for object detection, monitoring abnormal behavior in several cameras requires constant human tracking for a single camera operative, which is a tedious task. In multiview cameras, accurately detecting different types of guns and knives and classifying them from other video surveillance objects in real-time scenarios is difficult. Most detecting cameras are resource-constrained devices with limited computational capacities. To mitigate this problem, we proposed a resource-constrained lightweight subclass detection method based on a convolutional neural network to classify, locate, and detect different types of guns and knives effectively and efficiently in a real-time environment. In this paper, the detection classifier is a multiclass subclass detection convolutional neural network used to classify object frames into different sub-classes such as abnormal and normal. The achieved mean average precision by the best state-of-the-art framework to detect either a handgun or a knife is 84.21% or 90.20% on a single camera view. After extensive experiments, the best precision obtained by the proposed method for detecting different types of guns and knives was 97.50% on the ImageNet dataset and IMFDB, 90.50% on the open-image dataset, 93% on the Olmos dataset, and 90.7% precision on the multiview cameras. This resource-constrained device has shown a satisfactory result, with a precision score of 85.5% for detection in a multiview camera.

Real-World Community-in-the-Loop Smart Video Surveillance -- A Case Study at a Community College

“…Suspicious object detection is crucial for security purposes in real-life applications; however, large object classification datasets like COCO do not include harmful objects. To achieve improved object detection results, a study of Real-Time abnormal object detection [24] shows how to train and implement the abnormal object detection model into smart cities with reaching about 90 percent accuracy [25] [26]. Another paper published in 2023, which discussed person re-identification using deep learningassisted methods [27] focuses on learning spatial and channel attention between different views of the same object to have a machine learning-related solution for better re-identification scores of 24.6 percent and 54.8 percent.…”

A Systematic Review of Using Machine Learning and Natural Language Processing in Smart Policing

“…Furthermore, many studies have focused on the customization of deep neural networks for the real-time detection and classification of weapons during surveillance of criminal activities. These efforts highlight the growing demand for automatic systems in policing, given the increasing rate of crime and the frequent use of handheld weapons like pistols and revolvers in illegal or criminal activities [77,[79][80][81][82][83][84][85][86]. Another study proposed a model to detect handguns based on the individual's pose, utilizing CNNs [87].…”

Global vision object detection using an improved Gaussian Mixture model based on contour

“…Visual object detection plays an important role in the field of computer vision. It has a variety of significant applications in human–computer interfaces, road traffic control, and video surveillance systems ( Ingle & Kim, 2022 ; Roy, 2017 ; Shirpour et al, 2023 ). In addition to classic applications, an increasing number of scholars are expanding the application of object detection to other fields, such as aquaculture and social computing ( Li et al, 2023 ; Wu et al, 2023 ).…”