Edge Artificial Intelligence: A Multi-Camera Video Surveillance Application

2021 ◽  
Author(s):  
Daniele Berardini ◽  
Adriano Mancini ◽  
Primo Zingaretti ◽  
Sara Moccia
Keyword(s):  
Artificial Intelligence ◽  
Real Time ◽  
Video Surveillance ◽  
Cost Effective ◽  
Fast Response ◽  
Video Stream ◽  
Single Shot ◽  
Central Unit ◽  
Surveillance Video ◽  
People Detection

Abstract Nowadays, video surveillance has a crucial role. Analyzing surveillance videos is, however, a time consuming and tiresome procedure. In the last years, artificial intelligence paved the way for automatic and accurate surveillance-video analysis. In parallel to the development of artificial-intelligence methodologies, edge computing is becoming an active field of research with the final goal to provide cost-effective and real time deployment of the developed methodologies. In this work, we present an edge artificial intelligence application to video surveillance. Our approach relies on a set of four IP cameras, which acquire video frames that are processed on the edge using the NVIDIA® Jetson Nano. A state-of-the-art deep-learning model, called Single Shot multibox Detector (SSD) MobileNetV2 network, is used to perform object and people detection in real-time. The proposed infrastructure obtained an inference speed of ∼10.0 Frames per Second (FPS) for each parallel video stream. These results prompt the possibility of translating our work into a real word scenario. The integration of the presented application into a wider monitoring system with a central unit could bring benefits to the overall infrastructure. Indeed our application could send only video-related high-level information to the central unit, allowing it to combine information with data coming from other sensing devices without unuseful data overload. This would ensure a fast response in case of emergency or detected anomalies. We hope this work will contribute to stimulate the research in the field of edge artificial intelligence for video surveillance.

Artificial Intelligence-Aided Automated Detection of Railroad Trespassing

2019 ◽  
Vol 2673 (7) ◽  
pp. 25-37 ◽  
Author(s):  
Asim Zaman ◽  
Baozhang Ren ◽  
Xiang Liu
Keyword(s):  
Artificial Intelligence ◽  
Real Time ◽  
Video Clip ◽  
Text Message ◽  
The United States ◽  
Video Data ◽  
Surveillance Video ◽  
Railroad Industry ◽  
Real Time Analysis ◽  
Safety Research

Trespassing is the leading cause of rail-related deaths and has been on the rise for the past 10 years. Detection of unsafe trespassing of railroad tracks is critical for understanding and preventing fatalities. Witnessing these events has become possible with the widespread deployment of large volumes of surveillance video data in the railroad industry. This potential source of information requires immense labor to monitor in real time. To address this challenge this paper describes an artificial intelligence (AI) framework for the automatic detection of trespassing events in real time. This framework was implemented on three railroad video live streams, a grade crossing and two right-of-ways, in the United States. The AI algorithm automatically detects trespassing events, differentiates between the type of violator (car, motorcycle, truck, pedestrian, etc.) and sends an alert text message to a designated destination with important information including a video clip of the trespassing event. In this study, the AI has analyzed hours of live footage with no false positives or missed detections yet. This paper and its subsequent studies aim to provide the railroad industry with state-of-the-art AI tools to harness the untapped potential of an existing closed-circuit television infrastructure through the real-time analysis of their data feeds. The data generated from these studies will potentially help researchers understand human factors in railroad safety research and give them a real-time edge on tackling the critical challenges of trespassing in the railroad industry.

Cost-Effective Security Support in Real-Time Video Surveillance

2015 ◽  
Vol 11 (6) ◽  
pp. 1457-1465 ◽  
Author(s):  
Udaya L. N. Puvvadi ◽  
Kevin Di Benedetto ◽  
Aditya Patil ◽  
Kyoung-Don Kang ◽  
Youngjoon Park
Keyword(s):  
Real Time ◽  
Video Surveillance ◽  
Cost Effective

A Design and Implementation of Video Monitoring System at Smart Home

2014 ◽  
Vol 568-570 ◽  
pp. 1162-1167 ◽  
Author(s):  
Heng Xu ◽  
Cheng Hua Fu ◽  
Yun Jin Yang
Keyword(s):  
Real Time ◽  
Monitoring System ◽  
Video Surveillance ◽  
Surveillance System ◽  
Smart Home ◽  
Video Stream ◽  
Video Monitoring ◽  
Video Surveillance System ◽  
Infrared Sensor ◽  
Design And Implementation

The traditional real-time video surveillance system at smart home tends to occupy a lot of resource .In order to solve this kind of problem, a design of an infrared sensor to trigger video monitoring system is proposed in this paper .The system uses arm9-Linux as the platform ,and infrared sensor as the trigger device and uses the mpeg-4 algorithm to encode the video stream finally .The article mainly introduces how to build the hardware and software platform and tests the feasibility of the system.

scholarly journals UAV-Based and WebRTC-Based Open Universal Framework to Monitor Urban and Industrial Areas

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4061
Author(s):  
Agnieszka Chodorek ◽  
Robert Ryszard Chodorek ◽  
Paweł Sitek
Keyword(s):  
Real Time ◽  
Smart Cities ◽  
Rapid Development ◽  
Fast Response ◽  
Video Stream ◽  
Monitoring Systems ◽  
High Temporal Resolution ◽  
Ability To Work ◽  
Industrial Areas ◽  
Video Information

Nowadays, we are observing a rapid development of UAV-based monitoring systems, which are faced with more and more new tasks, such as high temporal resolution and high spatial resolution of measurements, or Artificial Intelligence on board. This paper presents the open universal framework intended for fast prototyping or building a short series of specialized flying monitoring systems able to work in urban and industrial areas. The proposed framework combines mobility of UAV with IoT measurements and full-stack WebRTC communications. WebRTC offers simultaneous transmission of both a real-time video stream and the flow of data coming from sensors, and ensures a kind of protection of data flow, which leads to preserving its near-real-time character and enables contextual communication. Addition of the AI accelerator hardware makes this system AI-ready, i.e., the IoT communication hub, which is the air component of our system, is able to perform tasks of AI-supported computing. The exemplary prototype of this system was evaluated in terms of the ability to work with fast-response sensors, the ability to work with high temporal and high spatial resolutions, video information in poor visibility conditions and AI-readiness. Results show that prototypes based on the proposed framework are able to meet the challenges of monitoring systems in smart cities and industrial areas.

scholarly journals A Cost Effective Approach to Real Time Video-Surveillance of Outdoor Scenes

1999 ◽  
Author(s):  
Inaki Goirizelaia ◽  
Juan Jose Igarza ◽  
Federico Perez ◽  
Koldo Espinosa ◽  
Pedro Iriondo
Keyword(s):  
Real Time ◽  
Video Surveillance ◽  
Cost Effective ◽  
Cost Effective Approach ◽  
Outdoor Scenes

scholarly journals Cost effective Parking System Using Computer Vision

2020 ◽  
pp. 241-246
Author(s):  
Kaushal Shah ◽  
Shivang Rajbhoi ◽  
Nikhil Prasad ◽  
Charmi Patel ◽  
Roushan Raj
Keyword(s):  
Real Time ◽  
Cost Effective ◽  
Video Stream ◽  
Sensor Data ◽  
Practical Implementation ◽  
Wireless System ◽  
Central System ◽  
Static Images ◽  
High Processing ◽  
Changing Light

This paper presents an approach for detecting real-time parking slots which includes vision-based techniques. Traditional sensor-based systems are not cost effective as 'n' number of sensors are required for 'n' parking slots. Transmitting sensor data to central system is done by hardwiring or installing dedicated wireless system which is again costly. Our technique will overcome this problem by using camera instead of number of sensors which is expensive. For detection we are using a Convolutional Neural Networks (CNN) classifier which is custom trained. It is more robust and effective in changing light conditions and weather. The following system do not require high processing as detections are done on static images not on video stream. We have also demonstrated real-time parking scenario by constructing a small prototype which shows practical implementation of our system.

Event Detection, Query, and Retrieval for Video Surveillance

2011 ◽  
pp. 342-370 ◽  
Author(s):  
Ying-li Tian ◽  
Arun Hampapur ◽  
Lisa Brown ◽  
Rogerio Feris ◽  
Max Lu ◽  
...  
Keyword(s):  
Software Architecture ◽  
Real Time ◽  
Video Surveillance ◽  
Event Detection ◽  
Airport Security ◽  
Surveillance Video ◽  
Multiple Dimensions ◽  
Video Parsing ◽  
Geographically Distributed ◽  
Typically Real

Video surveillance automation is used in two key modes: watching for known threats in real-time and searching for events of interest after the fact. Typically, real-time alerting is a localized function, for example, an airport security center receives and reacts to a “perimeter breach alert,” while investigations often tend to encompass a large number of geographically distributed cameras like the London bombing, or Washington sniper incidents. Enabling effective event detection, query and retrieval of surveillance video for preemption, and investigation, involves indexing the video along multiple dimensions. This chapter presents a framework for event detection and surveillance search that includes: video parsing, indexing, query and retrieval mechanisms. It explores video parsing techniques that automatically extract index data from video indexing, which stores data in relational tables; retrieval which uses SQL queries to retrieve events of interest and the software architecture that integrates these technologies.

scholarly journals Rain Streak Removal for Single Images Using Conditional Generative Adversarial Networks

2021 ◽  
Vol 11 (5) ◽  
pp. 2214
Author(s):  
Prasad Hettiarachchi ◽  
Rashmika Nawaratne ◽  
Damminda Alahakoon ◽  
Daswin De Silva ◽  
Naveen Chilamkurti
Keyword(s):  
Real Time ◽  
Video Surveillance ◽  
Smart City ◽  
Motion Blur ◽  
Generative Adversarial Networks ◽  
Great Success ◽  
Surveillance Systems ◽  
Surveillance Video ◽  
Deep Convolutional Neural Networks ◽  
Adversarial Networks

Rapid developments in urbanization and smart city environments have accelerated the need to deliver safe, sustainable, and effective resource utilization and service provision and have thereby enhanced the need for intelligent, real-time video surveillance. Recent advances in machine learning and deep learning have the capability to detect and localize salient objects in surveillance video streams; however, several practical issues remain unaddressed, such as diverse weather conditions, recording conditions, and motion blur. In this context, image de-raining is an important issue that has been investigated extensively in recent years to provide accurate and quality surveillance in the smart city domain. Existing deep convolutional neural networks have obtained great success in image translation and other computer vision tasks; however, image de-raining is ill posed and has not been addressed in real-time, intelligent video surveillance systems. In this work, we propose to utilize the generative capabilities of recently introduced conditional generative adversarial networks (cGANs) as an image de-raining approach. We utilize the adversarial loss in GANs that provides an additional component to the loss function, which in turn regulates the final output and helps to yield better results. Experiments on both real and synthetic data show that the proposed method outperforms most of the existing state-of-the-art models in terms of quantitative evaluations and visual appearance.

scholarly journals Investigasi Pengaruh Step Training pada Metode Single Shot Multibox Detector untuk Marker dalam Teknologi Augmented Reality

2020 ◽  
Vol 12 (1) ◽  
pp. 1
Author(s):  
Vivian Alfionita Sutama ◽  
Suryo Adhi Wibowo ◽  
Rissa Rahmania
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Augmented Reality ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Transfer Learning ◽  
Learning Rate ◽  
Batch Size ◽  
Single Shot

Nowadays, Artificial Intelligence is one of the most developing technology, especially on Augmented Reality (AR). AR is a technology which connected between real world and virtual in a real time that allows user to interact directly and display it in 3D. AR technology has two methods, that are AR based on marker and AR based on markerless. However, AR based on marker need an object detection system which has high performance as an interaction tools between user and the device. Single shot multibox detector (SSD) is an object detection algorithm that has fast learning computation and good performance. This method is affected by some parameters like number of epoch, learning rate, batch size, step training, etc. However, to create a good system it took a long process such as taking dataset, labelling process, then training and testing models to gain the best performance. In this experiment, we analyze SSD method in AR technology using inception architecture as pre-trained Convolutional neural network (CNN), and then do transfer learning to minimize amount training time. The configuration that used is the number of step training. The result of this experiment gets the best accuracy in 70.17%. Then, the best performance is used as an object detection model for marker’s AR technology.Abstrak Saat ini, Artificial intelligence merupakan teknologi yang sedang berkembang pesat. Salah satunya adalah teknologi Augmented Reality (AR). AR adalah teknologi yang menggabungkan dunia nyata dengan virtual secara real-time dengan interaksi pengguna secara langsung dan menampilkannya dalam bentuk 3D. Teknologi AR ini memiliki dua metode yaitu dengan marker dan markerless. Dalam perkembangannya, AR berbasis marker membutuhkan sistem deteksi objek yang memiliki performa tinggi sebagai alat interaksi antara pengguna dengan perangkatnya. Single shot multibox detector (SSD) merupakan algoritma deteksi objek yang memiliki komputasi pembelajaran dan kinerja yang baik. Metode ini dipengaruhi oleh beberapa parameter seperti jumlah lapisan konvolusi, epoch, learning rate, jumlah batch, step training, dll. Namun, dalam mengimplementasikannya diperlukan proses yang cukup panjang seperti, pengambilan dataset, proses pelabelan, proses pelatihan menggunakan metode SSD, dan melakukan pengujian terhadap beberapa model untuk mencari perfomansi paling baik. Dalam percobaan ini, kami melakukan analisis terhadap metode SSD pada teknologi AR menggunakan arsitektur Inception sebagai pre-trained Convolutional neural network (CNN), kemudian dilakukan transfer learning untuk memperkecil jumlah kelas data pelatihan dan waktu pelatihan data. Konfigurasi yang digunakan berupa jumlah step pada pelatihan. Hasil dari penilitian ini menunjukan akurasi terbaik sebesar 70,17%. Kemudian, perfomansi terbaik digunakan sebagai model deteksi objek untuk marker pada teknologi AR.

scholarly journals Cloud based Single Shot Multi Box Detection (SSD) Architecture Models for Jakarta Traffic Jam Monitoring

2019 ◽  
Vol 9 (2) ◽  
pp. 3617-3622
Keyword(s):  
Artificial Intelligence ◽  
Real Time ◽  
Single Shot ◽  
Vehicle Speed ◽  
Artificial Intelligence System ◽  
Road Density ◽  
Traffic Jam ◽  
The Road ◽  
Intelligence System ◽  
Ip Camera

Traffic jam is still one of the main problems in Jakarta Indonesia. To encounter this problem, we proposed system to monitor the road and perform calculation on vehicles speed and road density. To achieve this, we used SSD to detect vehicle traffic on Jakarta’s road which obtained from public IP Camera. The main contribution of this work are utilization of public IP Camera and remote traffic analytics via cloud based artificial intelligence system. As a result, the program can perform monitoring on roads condition in real time. The accuracy of the system in average is 80% with highest accuracy achieved 92% to detect vehicle speed and road density.

Sign in / Sign up

Export Citation Format

Share Document