Low-Cost Camera-Based Smart Surveillance System for Detecting, Recognizing, and Tracking Masked Human Face

A surveillance system is still the most exciting and practical security system to prevent crime effectively. The primary purpose of this system is to recognize the identity of the face caught by the camera. With the advancement of the Internet of things, surveillance systems were implemented on edge devices such as the low-cost Raspberry mobile camera. It raises the challenge of unstructured image/video where the video contains low quality, blur, and variations of human poses. The challenge is increasing because people used to wear a mask during the Covid -19 pandemic. Therefore, we proposed developing an all-in-one surveillance system with face detection, recognition, and face tracking capabilities. This system integrated three modules: MTCNN face detector, VGGFace2 face recognition, and Discriminative Single-Shot Segmentation (D3S) tracker to create a system capable of tracking the faces of people caught on surveillance camera. We also train new face mask data to recognize and track. This system obtains data from the Raspberry Pi camera and processes images on the cloud as a mobile sensor approach. The proposed system successfully implemented and obtained competitive results in detection, recognition, and tracking under an unconstrained surveillance camera.

Real-time performance evaluation of BGSLibrary algorithms for intelligent surveillance

<p>Background subtraction is the first and basic stage in video analysis and smart surveillance to extract moving objects. In fact, the background subtraction library (BGSLibrary) was created by Andrews Sobral in 2012, which currently combines 43 background subtraction algorithms from the most popular and widely used in the field of video analysis. Each algorithm has its own characteristics, strengths and weaknesses in extracting moving objects. The evaluation allows the identification of these characteristics and helps researchers to design the best methods. Unfortunately, the literature lacks a comprehensive evaluation of the algorithms included in the library. Accordingly, the present work will evaluate these algorithms in the BGSLibrary through the segmentation performance, execution time and processor, so as to, achieve a perfect, comprehensive, real-time evaluation of the system. Indeed, a background modeling challenge (BMC) dataset was selected using the synthetic video with the presence of noise. Results are presented in tables, columns and foreground masks.</p>

1295. Susceptibility to Ceftolozane/Tazobactam and Comparators Among Pseudomonas aeruginosa Isolates Collected from Patients in Hospitals in Latin America – SMART 2017-2019

Background Ceftolozane is a cephalosporin specifically developed to have enhanced antibacterial activity against P. aeruginosa. Combined with tazobactam, it was approved by FDA and EMA for complicated urinary tract and intraabdominal infections, as well as hospital-acquired/ventilator-associated bacterial pneumonia. We evaluated the activity of ceftolozane/tazobactam (C/T) against P. aeruginosa isolates collected as part of the global SMART surveillance program in 10 countries in Latin America. Methods In 2017-2019, 41 clinical labs each collected up to 250 consecutive gram-negative pathogens per year from various infection sources. A total of 21,864 isolates were collected, of which 3,335 (15.3%) were P. aeruginosa. MICs were determined using CLSI broth microdilution and breakpoints. C/T-nonsusceptible (NS) P. aeruginosa isolates were screened for genes encoding β-lactamases. Results The table shows the antimicrobial susceptibility of P. aeruginosa and β-lactam-NS subsets. C/T was active against 85.9% of all collected P. aeruginosa, with lowest activity against isolates collected in Chile and Venezuela, where 28.0% and 23.2% of isolates, respectively, carried carbapenemases, and highest activity against isolates from Ecuador and Guatemala, where 2.2% and 4.2%, respectively, were carbapenemase-positive. Substantial variability in the activity of C/T and comparators was observed among β-lactam-NS subsets. In aggregate, however, C/T remained active against 59.9% of all meropenem-NS P. aeruginosa isolates from Latin America (n=1,101), 57.3% of piperacillin/tazobactam-NS isolates (n=1054), 48.9% of cefepime-NS isolates (n=895), and 50.3% of ceftazidime-NS isolates (n=937). Conversely, other common β-lactams (meropenem, cefepime, ceftazidime, and piperacillin/tazobactam) remained active against 8-38% of these resistant isolates. Results Table Conclusion C/T showed the highest activity against P. aeruginosa among the tested β-lactam antibiotics. While amikacin showed similar or better activity in vitro, its toxicities severely limit its clinical use. Given the desirability of β-lactams among clinicians, C/T represents an important option in the treatment of infections caused by P. aeruginosa in Latin America. Disclosures Sibylle Lob, PhD, IHMA (Employee)Pfizer, Inc. (Independent Contractor) Meredith Hackel, PhD MPH, IHMA (Employee)Pfizer, Inc. (Independent Contractor) C. Andrew DeRyke, PharmD, Merck & Co., Inc. (Employee, Shareholder) Jacquleine Pavía, MSc, Merck & Co, Inc (Employee) Fakhar Siddiqui, PhD, Merck & Co, Inc (Employee) Katherine Young, MS, Merck (Employee) Mary Motyl, PhD, Merck & Co., Inc. (Employee, Shareholder) Daniel F. Sahm, PhD, IHMA (Employee)Pfizer, Inc. (Independent Contractor)

Mapping Invisible Surveillance on the North Avenue Smart Corridor, Atlanta

This paper presents a speculative mapping exercise as a feminist resistance method with the aim of rendering surveillance technologies and their fields of view visible. The focus is on the North Avenue Smart Corridor, located in Atlanta, Georgia, which is one of the world's top ten most surveilled cities. Through the design of these speculative maps, I question our relationship with surveillance. More specifically, I show that unnoticeable materiality and invisible processes of smart surveillance technologies prevent the public from forming an opinion on their intrusion into daily life. Acceptance of these technologies allows powerholders to protect and enhance their power over marginalized communities. Therefore, by mapping the intensity of surveillance, this study aims to raise awareness against the lure of technocracy in so-called smart cities. It situates the reader in the position of surveillance sensors and allows the reader to speculate on what they can see. In doing so, it seeks to highlight the oppressive agency of these technologies and question their appeal to objectivity with the potential to disrupt their patriarchal powers. Can we free ourselves from the oppressive gaze of smart surveillance by mapping, seeing, and understanding its remarkably limited fields of view?

A Smart Surveillance System for Uncooperative Gait Recognition Using Cycle Consistent Generative Adversarial Networks (CCGANs)

Surveillance remains an important research area, and it has many applications. Smart surveillance requires a high level of accuracy even when persons are uncooperative. Gait Recognition is the study of recognizing people by the way they walk even when they are unwilling to cooperate. It is another form of a behavioral biometric system in which unique attributes of an individual’s gait are analyzed to determine their identity. On the other hand, one of the big limitations of the gait recognition system is uncooperative environments in which both gallery and probe sets are made under different and unknown walking conditions. In order to tackle this problem, we propose a deep learning-based method that is trained on individuals with the normal walking condition, and to deal with an uncooperative environment and recognize the individual with any dynamic walking conditions, a cycle consistent generative adversarial network is used. This method translates a GEI disturbed from different covariate factors to a normal GEI. It works like unsupervised learning, and during its training, a GEI disrupts from different covariate factors of each individual and acts as a source domain while the normal walking conditions of individuals are our target domain to which translation is required. The cycle consistent GANs automatically find an individual pair with the help of the Cycle Loss function and generate the required GEI, which is tested by the CNN model to predict the person ID. The proposed system is evaluated over a publicly available data set named CASIA-B, and it achieved excellent results. Moreover, this system can be implemented in sensitive areas, like banks, seminar halls (events), airports, embassies, shopping malls, police stations, military areas, and other public service areas for security purposes.