Real-Time Gaze-Aware Cognitive Support System for Security Surveillance

Author(s):  
Alexandre Marois ◽  
Daniel Lafond ◽  
Alexandre Williot ◽  
François Vachon ◽  
Sébastien Tremblay

Security surveillance entails many cognitive challenges (e.g., task interruption, vigilance decrements, cognitive overload). To help surveillance operators overcome these difficulties and perform more efficient visual search, gaze-based intelligent systems can be developed. The present study aimed at testing the impact of the Scantracker system—which pinpointed neglected cameras while detecting and correcting attentional tunneling and vigilance decrease—on human scanning behavior and surveillance performance. Participants took part in a surveillance simulation, monitoring cameras and searching for ongoing incidents, and half of them was supported by the Scantracker. Although behavioral surveillance performance was not improved, participants supported by the Scantracker showed more efficient gaze-based measures of surveillance. Moreover, some of these measures were associated with performance, suggesting that scan pattern improvements might lead indirectly to more efficient incident detection. Overall, these results speak to the potential of using gaze- aware intelligent systems to support surveillance operators.

2021 ◽  
Vol 6 (1) ◽  
pp. 1-4
Author(s):  
Nagarjun Gururaj ◽  
Kanika Batra

In recent times the usage of intelligent systems have paved way formany applications to be robust and self-reliant. One such popularand vast growing technology is face recognition. Facial Recognitiontechnology is used in security, surveillance, criminal justice systemsand many other multimedia platforms. This work proposes a realtime facial recognition technology which can be used in any industrialsetup eliminating manual supervision, ensuring authorized accessto the personnel in the plant. Due to the recent development ofCOVID-19 pandemic around the world, wearing masks has becomea necessity. Our proposed facial recognition technology identifies aperson’s face with mask or no mask in real time with a speed of20 FPS on a CPU and an F1-score of 95.07%. This makes ouralgorithm fast, secure, robust and deployable on a simple personalcomputer or any edge device at any industrial plant or organization.


2012 ◽  
Vol 22 (4) ◽  
pp. 273-283 ◽  
Author(s):  
Pero Škorput ◽  
Sadko Mandžuka ◽  
Niko Jelušić

The paper analyses the real-time detection of incidents in road traffic. A general model is presented of an integral road traffic incident management system. The paper presents the major incident detection methods. The detection procedure on open highway sections has been dealt with in particular. Adequate mathematical model has been defined, as the base for the realisation of the estimators of the traffic flow condition variables. The proposed method is the Extended Kalman Filter. The final part of the paper deals with an example for the realisation of the Incident Management Decision Support System (IMDSS). KEY WORDS: intelligent transport system, incident management system, traffic model in the status space, theory of estimation, extended Kalman filter, automatic incident detection, decision support system


Author(s):  
Ruxandra Calapod Ioana ◽  
Irina Bojoga ◽  
Duta Simona Gabriela ◽  
Ana-Maria Stancu ◽  
Amalia Arhire ◽  
...  

2019 ◽  
Vol 2019 ◽  
pp. 790-791
Author(s):  
Cunhyeong Ci ◽  
◽  
Hyo-Gyoo Kim ◽  
Seungbae Park ◽  
Heebok Lee
Keyword(s):  

Diabetes ◽  
2020 ◽  
Vol 69 (Supplement 1) ◽  
pp. 778-P
Author(s):  
ZIYU LIU ◽  
CHAOFAN WANG ◽  
XUEYING ZHENG ◽  
SIHUI LUO ◽  
DAIZHI YANG ◽  
...  

2007 ◽  
Vol 30 (4) ◽  
pp. 51 ◽  
Author(s):  
A. Baranchuk ◽  
G. Dagnone ◽  
P. Fowler ◽  
M. N. Harrison ◽  
L. Lisnevskaia ◽  
...  

Electrocardiography (ECG) interpretation is an essential skill for physicians as well as for many other health care professionals. Continuing education is necessary to maintain these skills. The process of teaching and learning ECG interpretation is complex and involves both deductive mechanisms and recognition of patterns for different clinical situations (“pattern recognition”). The successful methodologies of interactive sessions and real time problem based learning have never been evaluated with a long distance education model. To evaluate the efficacy of broadcasting ECG rounds to different hospitals in the Southeastern Ontario region; to perform qualitative research to determine the impact of this methodology in developing and maintaining skills in ECG interpretation. ECG rounds are held weekly at Kingston General Hospital and will be transmitted live to Napanee, Belleville, Oshawa, Peterborough and Brockville. The teaching methodology is based on real ECG cases. The audience is invited to analyze the ECG case and the coordinator will introduce comments to guide the case through the proper algorithm. Final interpretation will be achieved emphasizing the deductive process and the relevance of each case. An evaluation will be filled out by each participant at the end of each session. Videoconferencing works through a vast array of internet LANs, WANs, ISDN phone lines, routers, switches, firewalls and Codecs (Coder/Decoder) and bridges. A videoconference Codec takes the analog audio and video signal codes and compresses it into a digital signal and transmits that digital signal to another Codec where the signal is decompressed and retranslated back into analog video and audio. This compression and decompression allows large amounts of data to be transferred across a network at close to real time (384 kbps with 30 frames of video per second). Videoconferencing communication works on voice activation so whichever site is speaking has the floor and is seen by all the participating sites. A continuous presence mode allows each site to have the same visual and audio involvement as the host site. A bridged multipoint can connect between 8 and 12 sites simultaneously. This innovative methodology for teaching ECG will facilitate access to developing and maintaining skills in ECG interpretation for a large number of health care providers. Bertsch TF, Callas PW, Rubin A. Effectiveness of lectures attended via interactive video conferencing versus in-person in preparing third-year internal medicine clerkship students for clinical practice examinations. Teach Learn Med 2007; 19(1):4-8. Yellowlees PM, Hogarth M, Hilty DM. The importance of distributed broadband networks to academic biomedical research and education programs. Acad Psychaitry 2006;30:451-455


1998 ◽  
Vol 37 (1) ◽  
pp. 347-354 ◽  
Author(s):  
Ole Mark ◽  
Claes Hernebring ◽  
Peter Magnusson

The present paper describes the Helsingborg Pilot Project, a part of the Technology Validation Project: “Integrated Wastewater” (TVP) under the EU Innovation Programme. The objective of the Helsingborg Pilot Project is to demonstrate implementation of integrated tools for the simulation of the sewer system and the wastewater treatment plant (WWTP), both in the analyses and the operational phases. The paper deals with the programme for investigating the impact of real time control (RTC) on the performance of the sewer system and wastewater treatment plant. As the project still is in a very early phase, this paper focuses on the modelling of the transport of pollutants and the evaluation of the effect on the sediment deposition pattern from the implementation of real time control in the sewer system.


Sign in / Sign up

Export Citation Format

Share Document