Object detection and activity recognition in video surveillance using neural networks

Purpose: This paper aims to implement and extend the You Only Live Once (YOLO) algorithm for detection of objects and activities. The advantage of YOLO is that it only runs a neural network once to detect the objects in an image, which is why it is powerful and fast. Cameras are found at many different crossroads and locations, but video processing of the feed through an object detection algorithm allows determining and tracking what is captured. Video Surveillance has many applications such as Car Tracking and tracking of people related to crime prevention. This paper provides exhaustive comparison between the existing methods and proposed method. Proposed method is found to have highest object detection accuracy. Design/methodology/approach: The goal of this research is to develop a deep learning framework to automate the task of analyzing video footage through object detection in images. This framework processes video feed or image frames from CCTV, webcam or a DroidCam, which allows the camera in a mobile phone to be used as a webcam for a laptop. The object detection algorithm, with its model trained on a large data set of images, is able to load in each image given as an input, process the image and determine the categories of the matching objects that it finds. As a proof of concept, this research demonstrates the algorithm on images of several different objects. This research implements and extends the YOLO algorithm for detection of objects and activities. The advantage of YOLO is that it only runs a neural network once to detect the objects in an image, which is why it is powerful and fast. Cameras are found at many different crossroads and locations, but video processing of the feed through an object detection algorithm allows determining and tracking what is captured. For video surveillance of traffic cameras, this has many applications, such as car tracking and person tracking for crime prevention. In this research, the implemented algorithm with the proposed methodology is compared against several different prior existing methods in literature. The proposed method was found to have the highest object detection accuracy for object detection and activity recognition, better than other existing methods. Findings: The results indicate that the proposed deep learning–based model can be implemented in real-time for object detection and activity recognition. The added features of car crash detection, fall detection and social distancing detection can be used to implement a real-time video surveillance system that can help save lives and protect people. Such a real-time video surveillance system could be installed at street and traffic cameras and in CCTV systems. When this system would detect a car crash or a fatal human or pedestrian fall with injury, it can be programmed to send automatic messages to the nearest local police, emergency and fire stations. When this system would detect a social distancing violation, it can be programmed to inform the local authorities or sound an alarm with a warning message to alert the public to maintain their distance and avoid spreading their aerosol particles that may cause the spread of viruses, including the COVID-19 virus. Originality/value: This paper proposes an improved and augmented version of the YOLOv3 model that has been extended to perform activity recognition, such as car crash detection, human fall detection and social distancing detection. The proposed model is based on a deep learning convolutional neural network model used to detect objects in images. The model is trained using the widely used and publicly available Common Objects in Context data set. The proposed model, being an extension of YOLO, can be implemented for real-time object and activity recognition. The proposed model had higher accuracies for both large-scale and all-scale object detection. This proposed model also exceeded all the other previous methods that were compared in extending and augmenting the object detection to activity recognition. The proposed model resulted in the highest accuracy for car crash detection, fall detection and social distancing detection. © 2023, Emerald Publishing Limited.

PULMONARY CMV REACTIVATION FOLLOWING SARS-CoV-2: IMPLICATIONS for IMMUNOPATHOLOGY

Background: SARS-CoV-2 infection results in a spectrum of disease severity attributable to the magnitude of the underlying inflammatory response. Aged individuals with co-morbidities are most vulnerable and severely affected, but the mechanisms driving aberrant immune responses fueling SARS-CoV-2 immunopathology in this high-risk population are not fully elucidated. We hypothesized that asymptomatic CMV infection might exacerbate SARS-CoV-2 pathogenesis since its replication is both a cause and consequence of inflammation and appears to worsen oxygenation in critically ill patients (Limaye, JAMA, 2017). CMV-seropositivity was associated with increased hospitalization among people with SARS-CoV-2 infection (Shrock, Science, 2020). To begin to address this hypothesis, we utilized the rhesus macaque model of natural rhesus (Rh)CMV infection to investigate the extent to which SARS-CoV-2 induces CMV reactivation in the anatomic sites of SARS-CoV-2 pathology. Methods: To assess CMV reactivation, eight aged, type 2 diabetic RhCMV-seropositive rhesus macaques (sera anti-CMV IgG: 300-1400 ng/ml) were infected with high-dose SARS-CoV-2 (2.5x10 6 PFU) and monitored for 7 days prior to euthanasia. Samples from the respiratory tract, intestinal tract, and blood were collected to assess viral and inflammatory dynamics in distinct tissue compartments. Results: Following infection, SARS-CoV-2 replication was observed throughout the respiratory tract, which was associated with local and systemic inflammation and immune activation. Lung histopathological assessments revealed development of interstitial pneumonia with colocalization of SARS nucleocapsid protein within pneumocytes. qPCR assays targeting RhCMV gB showed CMV DNA within the caudal lung lobe (up to 103 CMV DNA copies/mg of tissue) in all animals at day 7, and the animal with the highest CMV DNA presented with the most profound clinical symptoms. Strikingly, CMV DNA copies strongly correlated with CD4 and CD8 T cell activation indices in blood and spleen (r = 0.96, p< 0.001). Additionally, we found RhCMV reactivation in the ileum, where high levels of ACE2 are reported. Conclusion: SARS-CoV-2 infection of RhCMV-seropositive macaques results in CMV reactivation in the anatomic sites where SARS-CoV-2 causes pathology. Future experimental studies should address whether CMV reactivation exacerbates SARS-CoV-2 pathogenesis.

Yoga The Saviour From Mental Sickness

COVID - 19 pandemic has brought many problems after recovery. The problems ranges from body functions to all other small issues related to health. But the major impact of COVID - 19 has been on mental health resulting into suicidal tendencies in many patients. Due to lockdown in many parts of country, people have been in their home for a major part of time which has resulted into changes in their mental condition. Socializing has been minimal and going out to work also was hampered due to work from home. In January 2021, 41% adults have been reported with problems of mental fatigue. The efficiency has come down, the outcome of work has been to 80% - 85%, business has gone down because of less innovation and creativeness ability and other related problems. Yoga is giving an impetus to life for many, so to cope up with mental problems the various asanas is providing remedies which will be effective for the entire life. The asanas are being promoted by many yoga experts. The various recommended asanas will provide support to patients having mental problems which are very simple. The yoga guru send a message that if the asanas are done regularly and systematically to get relieved from many different ailment. If the recommended asanas are performed each day it will lead to a better life even if you are suffering from any long term ailment. In this article few postures (asana's) which can be performed at any time in the day but early morning will always be preferred (empty stomach) to get good result. All the asanas should be performed in presence of a trained person after due consultation with your physician. © The Electrochemical Society

Utility of post-operative review following Nd:YAG laser capsulotomy

Purpose : Nd:YAG laser capsulotomy (YAG) is a common procedure with infrequent adverse events. We reviewed intraocular pressure (IOP) measurements 30 minutes after YAG in glaucomatous and non-glaucomatous eyes and a one-week post-op dilated fundus exam (DFE) to detect retinal tear (RT) and detachment (RD). We are interested in the utility of these same day and one-week visits, especially in glaucoma patients and in this COVID19 era. Methods : We analyzed 1,406 eyes from 1,138 patients who received YAG from 2011 to 2020 at the University of Florida. Exclusion criteria included YAG performed for reasons other than posterior capsular opacification, IOP not recorded and glaucoma status not analyzed. IOP (pre-op, 30 minutes post-op and at follow-up), follow-up DFE and glaucoma history were recorded. Primary outcome measures were change in IOP at same day and one-week post-op visits and incidence of RT and RD. Statistical analyses were conducted in IBM SPSS Statistics. Pre-op and same day post-op IOP in all patients (N=578) and in glaucoma patients (N=93) were compared with paired ttest. Univariate regression analysis was performed to assess if glaucoma history predicted which patients would have a rise in IOP of 5mmHg or more. ANOVA was used for comparison of intergroup difference between pre-op, same day post-op, and follow-up. Results : There was no significant change in mean pre-op and post-op IOP in all patients (p = 0.557), nor in the glaucoma patients (p = 0.194). Many patients (68.9%, N=404) were given a drop of brimonidine prior to YAG procedure. 69 patients had a rise in IOP of 5 mmHg or more at 30 minutes following YAG, including 13/93 (14%) of glaucoma eyes and 56/485 (12%) of non-glaucoma eyes. An IOP spike of 10mmHg occurred in 9 of these eyes of which 1 eye had glaucoma (1%) and 8 did not (89%). Using binary logistic regression, we found that glaucoma was not predictive for rise in IOP of 5mmHg or more following YAG (OR 1.23;95% CI=0.64-2.34). No patients had RT or RD detected during one-week follow-up visit. Conclusions : There is no significant change in IOP in all patients and in glaucoma patients. Glaucoma was not considered a risk factor for rise in IOP. YAG does not seem to increase the risk of RT or RD. In this COVID-19 era, when all practitioners aim to decrease in-person visits, small changes on a large scale can make an impact. If validated, our results bring into question the necessity of post-op visits after YAG.