Fire and Gun Violence based Anomaly Detection System Using Deep Neural Networks

Mehta, Parth; Kumar, Atulya U.; Bhattacharjee, Shivani

doi:10.1109/icesc48915.2020.9155625

Cited by 25 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They achieved an accuracy of 93.1% for firearm detection. Research by Mehta et al [37] used the same dataset (IMFDB) to develop a DL model based on the YOLOv3 algorithm in which they process videos frame-by-frame in real-time to detect anomalies such as gun violence, mass shootings, home fires, industrial explosions, and wildfires. They achieve a detection rate of 45 FPS, and their final model had a validation loss of 0.2864.…”

Section: Related Workmentioning

confidence: 99%

Image and video-based crime prediction using object detection and deep learning

Boukabous¹,

Azizi²

2023

Bulletin EEI

View full text Add to dashboard Cite

In recent years, the use of artificial intelligence (AI) for image and video-based crime detection has gained significant attention from law enforcement agencies and security experts. Indeed, deep learning (DL) models can learn complex patterns from data and help law enforcement agencies save time and resources by automatically identifying and tracking potential criminals. This contributes to make deep investigations and better steer their targets’ searches. Among others, handheld firearms and bladed weapons are the most frequent objects encountered at crime scenes. In this paper, we propose a DL-based surveillance system that can detect the presence of tracked objects, such as handheld firearms and bladed weapons, as well as may proceed to alert authorities regarding eventual threats before an incident occurs. After making a comparison of different DL-based object detection techniques, such as you only look once (YOLO), single shot multibox detector (SSD), or faster region-based convolutional neural networks (R-CNN), YOLO achieves the optimal balance of mean average precision (mAP) and inference speed for real-time prediction. Thus, we retain YOLOv5 for the implementation of our solution.

show abstract

Section: Related Workmentioning

confidence: 99%

Image and video-based crime prediction using object detection and deep learning

Boukabous¹,

Azizi²

2023

Bulletin EEI

View full text Add to dashboard Cite

show abstract

“…Although there has been a recent advance in image-based machine learning, recognizing a knife-wielding assailant remains difficult. To address this issue, the authors [16] describe three approaches for automated threat detection utilizing various knife image datasets, with the goal of narrowing down plausible assault aims while decreasing false negatives and false positives. To begin, they employ a classification model based on Mobile Net in a sparse and pruned neural network that can notify an observer to the presence of a knife-wielding attacker with high accuracy (95%) and a low memory demand (2.2 MB).…”

Section: B Automatic Hanggun Detection Using Machine Learningmentioning

confidence: 99%

“…The following layer (the pooling layer) decreases the previous layer's output by pooling together all the pixels in a fixed-size square of the input picture. This layer reduces the number of parameters and makes the network more error-resistant [16,25]. CNN is trained on a large dataset of pictures containing the items to be recognized in order for the network to learn the characteristics that identify each object and correlate them with a given class.…”

Section: Automatic Hanggun Detection Using Machine Learningmentioning

confidence: 99%

Deep Learning Models for Crime Intention Detection Using Object Detection

Hashi¹,

Abdirahman²,

Elmi³

et al. 2023

IJACSA

View full text Add to dashboard Cite

The majority of visual based surveillance applications and security systems heavily rely on object detection, which serves as a critical module. In the context of crime scene analysis, images and videos play an essential role in capturing visual documentation of a particular scene. By detecting objects associated with a specific crime, police officers are able to reconstruct a scene for subsequent analysis. Nevertheless, the task of identifying objects of interest can be highly arduous for law enforcement agencies, mainly because of the massive amount of data that must be processed. Hence, the main objective of this paper is to propose a DL-based model for detecting tracked objects such as handheld firearms and informing the authority about the threat before the incident happens. We have applied VGG-19, ResNet, and GoogleNet as our deep learning models. The experiment result shows that ResNet50 has achieved the highest average accuracy of 0.92% compared to VGG19 and GoogleNet, which have achieved 0.91% and 0.89%, respectively. Also, YOLOv6 has achieved the highest MAP and inference speed compared to the faster R-CNN.

show abstract

“…In particular, as already anticipated, as a proof of concept, the VSU set up for the proposed framework was conceived with the purpose of detecting the presence of fire nearby bins and drop-off containers. The software infrastructure for the VSU exploits the following tools: You Only Look Once (YOLO): a machine learning tool customized for object recognition in images and video streaming; Yolo Fire Custom: a YOLO neural networking tool ad-hoc customized for fire detection [ 77 ]; Server Manager: a software ad-hoc developed in Python programming language for the image acquisition from the HikVison Mini PTZ Camera, their processing and the subsequent transmission of the extracted information by means of the data transmission sub-system. …”

Section: System Overviewmentioning

confidence: 99%

A Multi-Layer LoRaWAN Infrastructure for Smart Waste Management

Baldo

Mecocci

Parrino

et al. 2021

Sensors

View full text Add to dashboard Cite

Long Range Wide Area Network (LoRaWAN) has rapidly become one of the key enabling technologies for the development of Internet of Things (IoT) architectures. A wide range of different solutions relying on this communication technology can be found in the literature: nevertheless, the most part of these architectures focus on single task systems. Conversely, the aim of this paper is to present the architecture of a LoRaWAN infrastructure gathering under the same network different typologies of services within one of the most significant sub-systems of the Smart City ecosystem (i.e., the Smart Waste Management). The proposed architecture exploits the whole range of different LoRaWAN classes, integrating nodes of growing complexity according to the different functions. The lowest level of this architecture is occupied by smart bins that simply collect data about their status. Moving on to upper levels, smart drop-off containers allow the interaction with users as well as the implementation of asynchronous downlink queries. At the top level, Video Surveillance Units (VSUs) are provided with machine learning capabilities for the detection of the presence of fire nearby bins or drop-off containers, thus fully implementing the Edge Computing paradigm. The proposed network infrastructure and its subsystems have been tested in a laboratory and in the field. This study has enhanced the readiness level of the proposed technology to Technology Readiness Level (TRL) 3.

show abstract

Fire and Gun Violence based Anomaly Detection System Using Deep Neural Networks

Cited by 25 publications

References 10 publications

Image and video-based crime prediction using object detection and deep learning

Image and video-based crime prediction using object detection and deep learning

Deep Learning Models for Crime Intention Detection Using Object Detection

A Multi-Layer LoRaWAN Infrastructure for Smart Waste Management

Contact Info

Product

Resources

About