Toward the automatic detection of access holes in disaster rubble

Kong, Christopher; Ferworn, Alexander; Tran, Jimmy; Herman, Scott; Coleshill, Elliott; Derpanis, Konstantinos G.

doi:10.1109/ssrr.2013.6719364

Cited by 10 publications

(14 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A baseline for the automation of access hole detection in USAR disaster environments using a vision based technique was established by Kong et al [5]- [7]. The system uses colourdepth sensors mounted on an UAV carrying agent that travels over the rubble; the colour-depth images are then processed by an algorithm which segments the images and marks regions of interest based on the properties of holes as extracted from the functional definition of an access hole's utility.…”

Section: Ccdmentioning

confidence: 99%

Advancements toward autonomous access hole detection for urban search and rescue

Waismark¹

2021

Preprint

View full text Add to dashboard Cite

The collapse of buildings creates voids underneath rubble, where victims may be trapped. First responder crews arriving at a collapse scene are responsible for the location of access holes, among other tasks. Access holes are entry points through which rubble voids may be reached by search and rescue personnel. Previously presented work aimed to autonomously locate such holes, aiding concentration of resources to areas of interest, such as those leading into rubble. The work proposed improves upon existing work by increasing accuracy while reducing total number of detections. A new process is introduced for segmentation of colour and depth images, significantly improving the hole finding system’s accuracy. The ability to score holes based on multiple frames, considering various points of view is introduced. As an added benefit, matching holes across frames allows the algorithm to report holes once per group of matches, rather than once per frame.

show abstract

Section: Ccdmentioning

confidence: 99%

Advancements toward autonomous access hole detection for urban search and rescue

Waismark¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Here we demonstrate how this novel image processing framework can be used to efficiently process RGB-D images. We make use of a publicly available RGB-D dataset [8] collected by an unmanned aerial vehicle. The dataset explores the possibility that in the case of collapsed buildings there should be a way of automatically identifying potential access holes to guide rescuers to trapped people.…”

Section: Application Scenariomentioning

confidence: 99%

“…In this paper, we present a novel framework for efficient processing of RGB-D images, using superpixel segmentation and a finite element-based image processing framework to extract domain specific image features in a perceptually meaningful and computationally efficient manner. We make use of the access hole RGB-D dataset [8] to demonstrate the operation of our technique. This paper is organised as follows: Section II contains an overview of superpixel segmentation and details of the specific superpixel image representations used in the work presented here.…”

Section: Introductionmentioning

confidence: 99%

Superpixel finite element segmentation for RGB-D images

Kerr

Coleman

Scotney

2017

2017 2nd Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)

View full text Add to dashboard Cite

Computer vision research has advanced from focusing solely on intensity images to the use of depth images, or combinations of RGB, intensity and depth images, mainly due to the recent development of low cost depth cameras. These images can be efficiently represented as a space-variant image by segmenting the images using a superpixel representation. Whilst superpixel representations offer advantages in terms of reduced processing requirements they present challenges in further processing as many existing image processing techniques require regularly distributed image data. We overcome this issue by making use of the Finite element framework for processing these images and demonstrate the application of the technique for detecting access holes in disaster management situations.

show abstract

“…The limitation of triangular oriented structure is that, it is not a proper hole detection solution because, in a large WSNs, it is complex to connect the centre of three adjacent sensors. There are lots of research works going on in this area [13,14,15,16,17,18] to find a good and effective solution to find hole in a wireless sensor network. In the next section, we propose a simple but efficient hole detection algorithm.…”

Section: B Triangular Oriented Diagram Approachmentioning

confidence: 99%

Holes Detection in Wireless Sensor Networks: A Survey

Karmakar¹,

Roy²

2014

IJMECS

View full text Add to dashboard Cite

Abstract-Now a day's, it has been a great idea of research on using Wireless Sensor Networks (WSNs) to assist in the initial deployment of sensor nodes. Hole problem in WSNs is the most fundamental Problem in WSNs. Hole means a communication gap in WSNs. Finding an optimal sensor deployment strategy that would minimize the cost, reduce the node failure and also reduce the communication overhead. Then it provides a maximum degree of area coverage with lower cost of deployment of sensor nodes, best possible communication and maintaining the network connectivity. However, it increases the quality of service in WSNs that is extremely challenging. In this article, we present various types of holes, a comparative study of various types of holes and various types of coverage holes. At the end, we proposed an Algorithm to detect hole. In this paper, we aim to give the solution of hole problems of area coverage in WSNs.

show abstract

Toward the automatic detection of access holes in disaster rubble

Cited by 10 publications

References 15 publications

Advancements toward autonomous access hole detection for urban search and rescue

Advancements toward autonomous access hole detection for urban search and rescue

Superpixel finite element segmentation for RGB-D images

Holes Detection in Wireless Sensor Networks: A Survey

Contact Info

Product

Resources

About