scholarly journals Non-Temporal Lightweight Fire Detection Network for Intelligent Surveillance Systems

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 169257-169266
Author(s):  
Hunjun Yang ◽  
Hyeok Jang ◽  
Taeyong Kim ◽  
Bowon Lee
Keyword(s):  
Fire Detection ◽  
Surveillance Systems ◽  
Intelligent Surveillance

scholarly journals A Collaborative Region Detection and Grading Framework for Forest Fire Smoke Using Weakly Supervised Fine Segmentation and Lightweight Faster-RCNN

Forests ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 768
Author(s):  
Jin Pan ◽  
Xiaoming Ou ◽  
Liang Xu
Keyword(s):  
Forest Fire ◽  
Forest Fires ◽  
Learning Strategy ◽  
Early Stage ◽  
Fire Detection ◽  
Surveillance Systems ◽  
Region Detection ◽  
Decision Network ◽  
Fire Smoke ◽  
Weakly Supervised

Forest fires are serious disasters that affect countries all over the world. With the progress of image processing, numerous image-based surveillance systems for fires have been installed in forests. The rapid and accurate detection and grading of fire smoke can provide useful information, which helps humans to quickly control and reduce forest losses. Currently, convolutional neural networks (CNN) have yielded excellent performance in image recognition. Previous studies mostly paid attention to CNN-based image classification for fire detection. However, the research of CNN-based region detection and grading of fire is extremely scarce due to a challenging task which locates and segments fire regions using image-level annotations instead of inaccessible pixel-level labels. This paper presents a novel collaborative region detection and grading framework for fire smoke using a weakly supervised fine segmentation and a lightweight Faster R-CNN. The multi-task framework can simultaneously implement the early-stage alarm, region detection, classification, and grading of fire smoke. To provide an accurate segmentation on image-level, we propose the weakly supervised fine segmentation method, which consists of a segmentation network and a decision network. We aggregate image-level information, instead of expensive pixel-level labels, from all training images into the segmentation network, which simultaneously locates and segments fire smoke regions. To train the segmentation network using only image-level annotations, we propose a two-stage weakly supervised learning strategy, in which a novel weakly supervised loss is proposed to roughly detect the region of fire smoke, and a new region-refining segmentation algorithm is further used to accurately identify this region. The decision network incorporating a residual spatial attention module is utilized to predict the category of forest fire smoke. To reduce the complexity of the Faster R-CNN, we first introduced a knowledge distillation technique to compress the structure of this model. To grade forest fire smoke, we used a 3-input/1-output fuzzy system to evaluate the severity level. We evaluated the proposed approach using a developed fire smoke dataset, which included five different scenes varying by the fire smoke level. The proposed method exhibited competitive performance compared to state-of-the-art methods.

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

2018 ◽  
Vol 48 (8) ◽  
pp. 1475-1492 ◽  
Author(s):  
Rustem Dautov ◽  
Salvatore Distefano ◽  
Dario Bruneo ◽  
Francesco Longo ◽  
Giovanni Merlino ◽  
...  
Keyword(s):  
Urban Areas ◽  
Edge Computing ◽  
Surveillance Systems ◽  
Intelligent Surveillance

scholarly journals Præventive potentialer – Populærkulturens overvejelser om overvågning

2018 ◽  
pp. 99-112
Author(s):  
Lone Koefoed Hansen ◽  
Christopher Gad
Keyword(s):  
Popular Culture ◽  
Technological Development ◽  
Entry Point ◽  
Surveillance Systems ◽  
Research Project ◽  
Intelligent Surveillance ◽  
Technological Research ◽  
The Future ◽  
Minority Report ◽  
Basic Level

This article uses the movie Minority Report (2002) as an entry point for discussing conceptions of surveillance technologies and their preventive capacities. The technological research project Intelligent Surveillance Systems located in Belfast shares a vision with MR: that it is possible to construct surveillance systems that are able to foresee criminal acts and thus to prevent them from happening. We argue that the movie exemplifies that technological development and popular culture share dreams, ideas and visions and that on a very basic level, popular culture informs technological development and vice versa. The article explores this relation and argues that popular culture provides analytic insight on important discussions about surveillance and the (future) capacities of technology.

Intelligent Surveillance Systems for Smart Cities: A Systematic Literature Review

2021 ◽  
pp. 135-147
Author(s):  
Nour Ahmed Ghoniem ◽  
Samiha Hesham ◽  
Sandra Fares ◽  
Mariam Hesham ◽  
Lobna Shaheen ◽  
...  
Keyword(s):  
Literature Review ◽  
Systematic Literature Review ◽  
Smart Cities ◽  
Surveillance Systems ◽  
Intelligent Surveillance

scholarly journals Wireless Sensor Network for Ignitions Detection: An IoT approach

Electronics ◽  
2020 ◽  
Vol 9 (6) ◽  
pp. 893 ◽  
Author(s):  
Thadeu Brito ◽  
Ana I. Pereira ◽  
José Lima ◽  
António Valente
Keyword(s):  
Decision Making ◽  
Fire Detection ◽  
Barometric Pressure ◽  
Wireless Sensor ◽  
Surveillance Systems ◽  
Data Simulation ◽  
Central System ◽  
Flame Ignition ◽  
Wide Scale ◽  
Point Data

Wireless Sensor Networks (WSN) can be used to acquire environmental variables useful for decision-making, such as agriculture and forestry. Installing a WSN on the forest will allow the acquisition of ecological variables of high importance on risk analysis and fire detection. The presented paper addresses two types of WSN developed modules that can be used on the forest to detect fire ignitions using LoRaWAN to establish the communication between the nodes and a central system. The collaboration between these modules generate a heterogeneous WSN; for this reason, both are designed to complement each other. The first module, the HTW, has sensors that acquire data on a wide scale in the target region, such as air temperature and humidity, solar radiation, barometric pressure, among others (can be expanded). The second, the 5FTH, has a set of sensors with point data acquisition, such as flame ignition, humidity, and temperature. To test HTW and 5FTH, a LoRaWAN communication based on the Lorix One gateway is used, demonstrating the acquisition and transmission of forest data (simulation and real cases). Even in internal or external environments, these results allow validating the developed modules. Therefore, they can assist authorities in fighting wildfire and forest surveillance systems in decision-making.

scholarly journals Motion Saliency Detection for Surveillance Systems Using Streaming Dynamic Mode Decomposition

Symmetry ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 1397
Author(s):  
Thien-Thu Ngo ◽  
VanDung Nguyen ◽  
Xuan-Qui Pham ◽  
Md-Alamgir Hossain ◽  
Eui-Nam Huh
Keyword(s):  
Saliency Detection ◽  
Saliency Map ◽  
Dynamic Mode Decomposition ◽  
Dynamic Mode ◽  
Detection Accuracy ◽  
Surveillance Systems ◽  
Reconstruction Process ◽  
Intelligent Surveillance ◽  
Mode Decomposition ◽  
Motion Saliency

Intelligent surveillance systems enable secured visibility features in the smart city era. One of the major models for pre-processing in intelligent surveillance systems is known as saliency detection, which provides facilities for multiple tasks such as object detection, object segmentation, video coding, image re-targeting, image-quality assessment, and image compression. Traditional models focus on improving detection accuracy at the cost of high complexity. However, these models are computationally expensive for real-world systems. To cope with this issue, we propose a fast-motion saliency method for surveillance systems under various background conditions. Our method is derived from streaming dynamic mode decomposition (s-DMD), which is a powerful tool in data science. First, DMD computes a set of modes in a streaming manner to derive spatial–temporal features, and a raw saliency map is generated from the sparse reconstruction process. Second, the final saliency map is refined using a difference-of-Gaussians filter in the frequency domain. The effectiveness of the proposed method is validated on a standard benchmark dataset. The experimental results show that the proposed method achieves competitive accuracy with lower complexity than state-of-the-art methods, which satisfies requirements in real-time applications.

Sign in / Sign up

Export Citation Format

Share Document