Thermal imaging systems for real-time applications in smart cities

Gade, Rikke; Moeslund, Thomas B.; Nielsen, Søren Zebitz; Skov-Petersen, Hans; Andersen, Hans Jørgen; Basselbjerg, Kent; Dam, Hans Thorhauge; Jensen, Ole B.; Jorgensen, A. M.; Lahrmann, Harry; Bala, Esben Skouboe; Povey, Bo Ø.

doi:10.1504/ijcat.2016.076790

Cited by 16 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several possibilities for monitoring and controlling occupancy levels and the flow of people in cities. Usually, various types of video cameras are employed for that purpose: regular vision, thermal vision, and stereoscopic cameras [22,23]. These sorts of optical systems usually rely on enter-exit counts to supply information in real time.…”

Section: Related Workmentioning

confidence: 99%

Towards Smarter Management of Overtourism in Historic Centres Through Visitor-Flow Monitoring

et al. 2019

View full text Add to dashboard Cite

Historic centres are highly regarded destinations for watching and even participating in diverse and unique forms of cultural expression. Cultural tourism, according to the World Tourism Organization (UNWTO), is an important and consolidated tourism sector and its strong growth is expected to continue over the coming years. Tourism, the much dreamt of redeemer for historic centres, also represents one of the main threats to heritage conservation: visitors can dynamize an economy, yet the rapid growth of tourism often has negative effects on both built heritage and the lives of local inhabitants. Knowledge of occupancy levels and flows of visiting tourists is key to the efficient management of tourism; the new technologies—the Internet of Things (IoT), big data, and geographic information systems (GIS)—when combined in interconnected networks represent a qualitative leap forward, compared to traditional methods of estimating locations and flows. A methodology is described in this paper for the management of tourism flows that is designed to promote sustainable tourism in historic centres through intelligent support mechanisms. As part of the Smart Heritage City (SHCITY) project, a collection system for visitors is developed. Following data collection via monitoring equipment, the analysis of a set of quantitative indicators yields information that can then be used to analyse visitor flows; enabling city managers to make management decisions when the tourism-carrying capacity is exceeded and gives way to overtourism.

show abstract

Section: Related Workmentioning

confidence: 99%

Towards Smarter Management of Overtourism in Historic Centres Through Visitor-Flow Monitoring

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In CV, object tracking remains one of the most significant research challenges [8,9]. This becomes even more complex when using TVS for monitoring multi-occupants, as data only corresponds to variation in temperature.…”

Section: Introductionmentioning

confidence: 99%

uMoDT: an unobtrusive multi-occupant detection and tracking using robust Kalman filter for real-time activity recognition

et al. 2020

View full text Add to dashboard Cite

Human activity recognition (HAR) is an important branch of human-centered research. Advances in wearable and unobtrusive technologies offer many opportunities for HAR. While much progress has been made in HAR using wearable technology, it still remains a challenging task using unobtrusive (non-wearable) sensors. This paper investigates detection and tracking of multi-occupant HAR in a smart-home environment, using a novel low-resolution Thermal Vision Sensor (TVS). Specifically, the research presents the development and implementation of a two-step framework, consisting of a Computer Vision (CV) based method to detect and track multiple occupants combined with Convolutional Neural Network (CNN) based HAR. The proposed algorithm uses frame-difference over consecutive frames for occupant detection, a set of morphological operations to refine identified objects, and features are extracted before applying a Kalman filter for tracking. Laterally, a 19-layer CNN architecture is used for HAR and afterward the results from both methods are fused using time interval based sliding window. This approach is evaluated through a series of experiments based on benchmark Thermal Infrared datasets (VOT-TIR2016) and multi-occupant data collected from TVS. Results demonstrate that the proposed framework is capable of detecting and tracking 88.46% of multi-

show abstract

“…Thermal imaging is a technology used for analyzing the sample images which uses infrared detection process to identify the invisible infrared radiation effects, and making it visible to human eyes [1,2]. An ordinary camera is possible to record the data images event at a distance in real time.…”

Section: Introductionmentioning

confidence: 99%

Color Enhancement Algorithm using the Integrated K-means Clustering and Inverted Otsu Method for Thermal Object Characterization

Park¹,

Kim²

2018

IJIES

View full text Add to dashboard Cite

Thermal imaging plays an important role in numerous applications like in defense, security, military, and other industry that requires a non-contact temperature measurement, etc. This proposed algorithm improves the thermal image especially during the thresholding process in which the desired object is separated from the background and can easily be identified. The separate extracted images produced by K-means clustering and inverted Otsu methods were processed by Canny edge detection and color mapping to highlight the necessary characteristics of the sampled thermal images. This work is synthesized with Xilinx Zync 7000 ZED ZC702. The experimental results of this blended combination of K-means and inverted Otsu methods show significant distinguishable features in terms of edge and color. It outperforms the other color correction method in terms of processing time. Moreover, this implementation reduced resource utilization, and minimizes the misclassified pixel in different noise variance.

show abstract

Thermal imaging systems for real-time applications in smart cities

Cited by 16 publications

References 22 publications

Towards Smarter Management of Overtourism in Historic Centres Through Visitor-Flow Monitoring

Towards Smarter Management of Overtourism in Historic Centres Through Visitor-Flow Monitoring

uMoDT: an unobtrusive multi-occupant detection and tracking using robust Kalman filter for real-time activity recognition

Color Enhancement Algorithm using the Integrated K-means Clustering and Inverted Otsu Method for Thermal Object Characterization

Contact Info

Product

Resources

About