QuickBlaze: Early Fire Detection Using a Combined Video Processing Approach

Qureshi, Waqar S.; Ekpanyapong, Mongkol; Dailey, Matthew N.; Rinsurongkawong, Suchet; Malenichev, Anton; Krasotkina, Olga

doi:10.1007/s10694-015-0489-7

Cited by 59 publications

(35 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples included ML analysis of social media posts to detect and localize an incident 59,145,172 and machine vision-based detection of anomalies, such as fire, and prediction about the severity of disaster damage. 175,177 If implemented, AI/ML has the potential to revolutionize SA during disaster response operations. Articles also mentioned data analysis architectures, such as fog and edge computing, 55,65 that enable data processing and analysis (including sensor data and video footage) close to the field collection site, rather than requiring transmission to a central server in the EOC for integration and analysis and transmission back to first responders, thus saving valuable time during a disaster response.…”

Section: Figurementioning

confidence: 99%

Technologies Enabling Situational Awareness During Disaster Response: A Systematic Review

Kedia

Ratcliff

O'Connor

et al. 2020

Disaster med. public health prep.

View full text Add to dashboard Cite

Situational awareness (SA) is critical to mobilizing a rapid, efficient, and effective response to disasters. Limited by time and resources, response agencies must make decisions about rapidly evolving situations, which requires the collection, analysis, and sharing of actionable information across a complex landscape. Emerging technologies, if appropriately applied, can enhance SA and enable responders to make quicker, more accurate decisions. The aim of this systematic review is to identify technologies that can improve SA and assist decision-making across the United States Government and the domestic and international agencies they support during disaster response operations. A total of 1459 articles and 36 after-action reports were identified during literature searches. Following the removal of duplicates and application of inclusion/exclusion criteria, 302 articles and after-action reports were included in the review. Our findings suggest SA is constrained primarily due to unreliable and significantly delayed communications, time-intensive data analysis and visualization, and a lack of interoperable sensor networks and other capabilities providing data to shared platforms. Many of these challenges could be addressed by existing technologies. Bridging the divide between research and development efforts and the operational needs of response agencies should be prioritized.

show abstract

Section: Figurementioning

confidence: 99%

Technologies Enabling Situational Awareness During Disaster Response: A Systematic Review

Kedia

Ratcliff

O'Connor

et al. 2020

Disaster med. public health prep.

View full text Add to dashboard Cite

show abstract

“…If we want to limit fire consequences, it is important to detect the fire as soon as possible. A possible approach is to use IP cameras to detect the smoke at its beginning using some detection algorithms [31,32,33]. Another approach is to use geostationary satellites and image processing [34].…”

Section: Firementioning

confidence: 99%

The Internet of Things for Natural Risk Management (Inte.Ri.M.)

Beltramo¹,

Cantore²,

Vesce³

et al. 2019

Perspectives on Risk, Assessment and Management Paradigms

View full text Add to dashboard Cite

This chapter deals with the development of a management system, which integrates the use of IoT in natural risk detection, revention, and management with economic evaluation of each stage. In the introductory part, recent data are presented that document the importance that natural disasters have for the environment and for the Italian economy. Section 2 presents the Inte.Ri.M. project-the Internet of Things for Natural Risk Management-its purpose, activity plan, and bodies involved. Technical aspects are treated in Section 3 with the choice of hardware and software components and the solutions for collecting and transmitting data. Section 4 is about the economic aspects considering the stages of prevention, intervention, and restoration and the relation between the intensity of human activity and environment to define a range of situations. These scenarios call for different economic methodologies useful to estimate economic implications of each stage in the short, medium, and long term. Section 5 describes the structure of the Inte.Ri.M. management system and the foreseen functionalities. In the conclusion, the critical points are discussed, and the steps for the transposition of the work carried out on the territory are outlined, according to the provisions of the work program.

show abstract

“…This method has a better segmentation effect when the smoke concentration is high, but the effect is not satisfactory when the concentration is low. According to the characteristics of local background color change caused by smoke, Qureshi et al extracted the three‐component change amplitude of the pixels in the RGB color model by background difference and set threshold ranges for the change amplitude, respectively. The pixels satisfying the change amplitude threshold requirement are the smoke pixels.…”

Section: Introductionmentioning

confidence: 99%

A smoke segmentation algorithm based on improved intelligent seeded region growing

et al. 2019

View full text Add to dashboard Cite

Summary Image segmentation method based on region growing has the advantages of simple segmentation method and complete segmentation target. Because the color discrimination and gray gradient of smoke are not obvious, the traditional region growing segmentation method is difficult to separate it from the image, resulting in an unsatisfactory segmentation effect. To solve this problem, this paper partially improved the region growing method and proposed a new smoke segmentation algorithm based on the improved intelligent seeded region growing (IISRG) method. First, smoke images obtained from experimental videos were converted from the RGB color space to the HSV color space, and image binarization was achieved using background subtraction with an adaptive threshold in the V channel. Then, a pixel in the binary image was selected intelligently as the seed point, which was used for the regional growth. The final smoke segmentation images were obtained by the morphological processing of region growing images. Experimental smoke segmentation results show that the proposed algorithm has a higher overlap rate and a lower overflow rate, and performs a better smoke segmentation effect compared with the other two approaches. In addition, this algorithm can also effectively solve the problems of under‐segmentation and over‐segmentation of smoke images.

show abstract

QuickBlaze: Early Fire Detection Using a Combined Video Processing Approach

Cited by 59 publications

References 30 publications

Technologies Enabling Situational Awareness During Disaster Response: A Systematic Review

Technologies Enabling Situational Awareness During Disaster Response: A Systematic Review

The Internet of Things for Natural Risk Management (Inte.Ri.M.)

A smoke segmentation algorithm based on improved intelligent seeded region growing

Contact Info

Product

Resources

About