People Detection Research Articles

New opportunities for biomarkers in cardiovascular risk stratification. Resolution of Advisory board

Early detection of people with a high-risk of developing cardiovascular diseases is a key point of the prevention strategy. The existing risk scales have a number of limitations: insufficient accuracy for an individual or the appearance of a “residual risk”. Existing approaches to improving the accuracy of risk prediction include the use of biomarkers. Troponin I is promising, which has proven its prognostic value in healthy and asymptomatic individuals at the population level. For example, the BiomarCARE study with the participation of 74 thousand people from 5 countries showed an association of increased troponin I concentration and the frequency of cardiovascular events and overall mortality. Similar results were obtained in other cohorts. The simulation results indicate the potential economic feasibility of using troponin I for the purpose of risk stratification. The first pilot Russian study was conducted, which made it possible to describe the population distribution of troponin levels. It confirmed the prognostic significance of the biomarker in relation to the development of cardiovascular outcomes in men in the Russian population. Further studies on large cohorts are needed to clarify the results of the pilot project.

NOVEL SOFTWARE IN MATLAB DESIGNED FOR UWB SENSOR-BASED LOCALIZATION OF PEOPLE IN 2D AND 3D SPACE

Detection, localization, and tracking of people in 2D or 3D space using Ultra-wideband (UWB) short-range sensors is a subject of worldwide intensive research. In this paper, we describe a proposal for a novel software called UWB-PerLoc-2D3D. This software has been created in a MATLAB programming environment and designed to process UWB radar signals for the purpose of movement monitoring of human targets in 2D and 3D space. We present an evaluation of the proposed software properties as well as examples of its utilization in practice.

Proactive detection of people in need of mental healthcare: accuracy of the community case detection tool among children, adolescents and families in Sri Lanka

BackgroundMost children and adolescents in need of mental healthcare remain untreated even when services are available. This study evaluates the accuracy of a new tool, the Community Case Detection Tool (CCDT). The CCDT uses illustrated vignettes, two questions and a simple decision algorithm to support proactive community-level detection of children, adolescents and families in need of mental healthcare to improve help-seeking.MethodsTrusted and respected community members in the Eastern Province of Sri Lanka used the CCDT in their daily routine. Children and families detected as potentially in need of mental healthcare based on utilizing the CCDT (N = 157, aged 6–18 years) were invited for a clinical interview by a mental health counsellor using the Mini-International Neuropsychiatric Interview for Children and Adolescents (MINI-KID). The CCDT results were compared against the results of the clinical interview. The concurrent validity and performance of the CCDT were also evaluated by comparing the CCDT outcomes against the Strengths and Difficulties Questionnaire (SDQ).Results7 out of 10 children and families detected by community members using the CCDT were confirmed to be in need for treatment (positive predictive value [PPV] = 0.69; 0.75 when compared to the SDQ). Detections based on the family problem vignette were most accurate (PPV = 0.76), followed by the internalising problem vignette (PPV = 0.71) and the externalising problem vignette (PPV = 0.62).ConclusionsThe CCDT is a promising low-cost solution to overcome under-detection of children and families in need of mental healthcare. Future research should focus on evaluating the effectiveness, as well as additional strategies to improve help-seeking.

Towards dense people detection with deep learning and depth images

This paper describes a novel DNN-based system, named PD3net, that detects multiple people from a single depth image, in real time. The proposed neural network processes a depth image and outputs a likelihood map in image coordinates, where each detection corresponds to a Gaussian-shaped local distribution, centered at each person’s head. This likelihood map encodes both the number of detected people as well as their position in the image, from which the 3D position can be computed. The proposed DNN includes spatially separated convolutions to increase performance, and runs in real-time with low budget GPUs. We use synthetic data for initially training the network, followed by fine tuning with a small amount of real data. This allows adapting the network to different scenarios without needing large and manually labeled image datasets. Due to that, the people detection system presented in this paper has numerous potential applications in different fields, such as capacity control, automatic video-surveillance, people or groups behavior analysis, healthcare or monitoring and assistance of elderly people in ambient assisted living environments. In addition, the use of depth information does not allow recognizing the identity of people in the scene, thus enabling their detection while preserving their privacy. The proposed DNN has been experimentally evaluated and compared with other state-of-the-art approaches, including both classical and DNN-based solutions, under a wide range of experimental conditions. The achieved results allows concluding that the proposed architecture and the training strategy are effective, and the network generalize to work with scenes different from those used during training. We also demonstrate that our proposal outperforms existing methods and can accurately detect people in scenes with significant occlusions.

Epidemiology of undiagnosed depression in people with diabetes mellitus: a comparative analysis of Ireland, England and the USA

ObjectivesImproving detection of depression in people with diabetes is recommended. However, little is known about how different health systems compare in depression detection. We estimated and compared the (1) prevalence...

Biomechanical Measures for Fall Risk Assessment and Fall Detection in People with Transfemoral Amputations for the Next-Generation Prostheses: A Scoping Review

ABSTRACT Introduction Transfemoral amputations are known to compromise balance control capabilities, thus increasing the probability of falling. Current research in robotic prostheses is exploring novel strategies to assess the risk of fall and, if required, enable assistive strategies to promote balance recovery. Objectives The aim of this study was to identify a set of biomechanical variables associated with fall risk and fall detection in people with transfemoral amputation (pwTFA), which can be potentially assessed through the next generation of sensorized powered prostheses. Study Design The study design was scoping review. Methods Screening of the literature (CINAHL, PubMed, Scopus, and Web of Science) carried out in February 2020 (quality assessment of retained articles through Downs and Black checklist; retrieved information: measurement tests and biomechanical variables). Results From the initial 595 documents, only 25 citations met eligibility criteria. The pwTFA's fall risk assessment and fall detection are usually carried out by using different measurement tests. Conclusions Two classes of biomechanical markers for fall risk assessment have the potential to be incorporated in self-contained transfemoral powered prostheses equipped with sensory network and suitable computational capabilities. The first consists of kinematic/kinetic variables of some prosthesis components (e.g., foot acceleration, force loading the pylon, knee angle) to detect either an abrupt lack of balance or a fall-related occurrence as a consequence of knee buckling, slipping, or tripping. The second involves implementing automatic procedures to allow pwTFA to routinely carry out clinical tests, such as the timed up and go test and/or the Four Square Step Test to monitor the decline of sensory motor capabilities, likely documenting an increased fall risk. Clinical Relevance The next generation of powered prostheses could both monitor decline on neuromuscular capabilities and gather early signs of an acute lack of balance based on a suitable network of sensors on board. This approach is expected to prevent the fall risk in pwTFA.

Improved Heart Disease Prediction Using Particle Swarm Optimization Based Stacked Sparse Autoencoder

Heart disease is the leading cause of death globally. The most common type of heart disease is coronary heart disease, which occurs when there is a build-up of plaque inside the arteries that supply blood to the heart, making blood circulation difficult. The prediction of heart disease is a challenge in clinical machine learning. Early detection of people at risk of the disease is vital in preventing its progression. This paper proposes a deep learning approach to achieve improved prediction of heart disease. An enhanced stacked sparse autoencoder network (SSAE) is developed to achieve efficient feature learning. The network consists of multiple sparse autoencoders and a softmax classifier. Additionally, in deep learning models, the algorithm’s parameters need to be optimized appropriately to obtain efficient performance. Hence, we propose a particle swarm optimization (PSO) based technique to tune the parameters of the stacked sparse autoencoder. The optimization by the PSO improves the feature learning and classification performance of the SSAE. Meanwhile, the multilayer architecture of autoencoders usually leads to internal covariate shift, a problem that affects the generalization ability of the network; hence, batch normalization is introduced to prevent this problem. The experimental results show that the proposed method effectively predicts heart disease by obtaining a classification accuracy of 0.973 and 0.961 on the Framingham and Cleveland heart disease datasets, respectively, thereby outperforming other machine learning methods and similar studies.

Association Between Cognitive Trajectories and Disability Progression in Patients With Relapsing-Remitting Multiple Sclerosis.

Longitudinal cognitive trajectories in multiple sclerosis are heterogeneous and difficult to measure. We aimed to identify discrete longitudinal reaction time trajectories in relapsing-remitting multiple sclerosis using a computerized cognitive battery and to assess the association between trajectories of reaction time and disability progression. All participants serially completed computerized reaction time tasks measuring psychomotor speed, visual attention, and working memory. Participants completed at least 3 testing sessions over a minimum of 180 days. Longitudinal reaction times were modeled with latent class mixed models to identify groups of individuals sharing similar latent characteristics. Optimal models were validated for consistency and baseline associations with class membership tested using multinomial logistic regression. Interclass differences in the probability of reaction time worsening and the probability of 6-month confirmed disability progression were assessed with survival analysis. A total of 460 people with relapsing-remitting multiple sclerosis were included in the analysis. For each task of the MSReactor battery, the optimal model comprised 3 latent classes. All MSReactor tasks could identify a group with high probability of reaction time slowing. The visual attention and working memory tasks could identify a group of participants who were 3.7 and 2.6 times more likely to experience a 6-month confirmed disability progression, respectively. Participants could be classified into predicted cognitive trajectories after just 5 tests with 64% to 89% accuracy. Latent class modeling of longitudinal cognitive data collected by a computerized battery identified patients with worsening reaction times and increased risk of disability progression. Slower baseline reaction time, age, and disability increased assignment into this trajectory. Monitoring of cognition in clinical practice with computerized tests may enable detection of cognitive change trajectories and people with relapsing-remitting multiple sclerosis at risk of disability progression.

KL-MOB: automated COVID-19 recognition using a novel approach based on image enhancement and a modified MobileNet CNN.

The emergence of the novel coronavirus pneumonia (COVID-19) pandemic at the end of 2019 led to worldwide chaos. However, the world breathed a sigh of relief when a few countries announced the development of a vaccine and gradually began to distribute it. Nevertheless, the emergence of another wave of this pandemic returned us to the starting point. At present, early detection of infected people is the paramount concern of both specialists and health researchers. This paper proposes a method to detect infected patients through chest x-ray images by using the large dataset available online for COVID-19 (COVIDx), which consists of 2128 X-ray images of COVID-19 cases, 8,066 normal cases, and 5,575 cases of pneumonia. A hybrid algorithm is applied to improve image quality before undertaking neural network training. This algorithm combines two different noise-reduction filters in the image, followed by a contrast enhancement algorithm. To detect COVID-19, we propose a novel convolution neural network (CNN) architecture called KL-MOB (COVID-19 detection network based on the MobileNet structure). The performance of KL-MOB is boosted by adding the Kullback–Leibler (KL) divergence loss function when trained from scratch. The KL divergence loss function is adopted for content-based image retrieval and fine-grained classification to improve the quality of image representation. The results are impressive: the overall benchmark accuracy, sensitivity, specificity, and precision are 98.7%, 98.32%, 98.82% and 98.37%, respectively. These promising results should help other researchers develop innovative methods to aid specialists. The tremendous potential of the method proposed herein can also be used to detect COVID-19 quickly and safely in patients throughout the world.

Camouflaged people detection based on a semi-supervised search identification network

Automated detection of military people based on the images in different environments plays an important role in accurately completing military missions. With the equipment gradually moving towards intelligence, unmanned aerial vehicles (UAVs) will be widely used for integrated reconnaissance/attack in the future. The lightweight and compact design of the small UAV allows it to travel through dense forests and other environments to capture images with its convenient mobility. However, as the camouflage has been designed to blend in with surroundings, which greatly reduces the probability of the target being discovered. Moreover, the lack of training data on camouflaged people detection will inhibit the training of a deep model. To address these problems, a novel semi-supervised camouflaged military people detection network is proposed to automatically detect the target from the images. In this paper, the camouflaged object detection dataset (COD10K) is first supplemented according to our mission requirements, then the edge attention is utilized to enhance the boundaries based on search identification network. Further, a semi-supervised learning strategy is presented to take advantage of the unlabeled data which can alleviate insufficient data and improve the detection accuracy. Experiments demonstrate that the proposed semi-supervised search identification network (Semi-SINet) performs well in camouflaged people detection compared with other object detection methods.

PROTOTIPE SISTEM DETEKSI SUHU TUBUH DAN MASKER WAJAH MENGGUNAKAN ALGORITMA LOCAL BINARY PATTERN (LBP) DAN ARDUINO NANO

The COVID-19 pandemic has changed the lifestyle of everyone around the world. In this change, wearing a mask is very important for every individual. Detection of people not wearing masks is a challenge as the outbreak of the Coronavirus pandemic has created large populations. In addition, detection of body temperature is also very important because one of the symptoms of COVID-19 is a high body temperature, therefore an effective method against the virus is to use a face mask and check body temperature in real time, and which will be the main focus in this prototype. how the LBP Algorithm can detect the use of masks and the Arduino Nano design with an infrared camera to measure body temperature which can be implemented in public places as a digital scanning tool. This testing prototype aims to be used in evaluating, preventing, and planning actions against COVID-19 and maintaining a distance between officers and the public in an environment where masks are mandatory and normal body temperature is required. The steps for building the model are collecting data, pre-processing, testing the model, and implementing the model. The results of this prototype test show an F1 score of 0.99 accuracy for mask detection and body temperature measurement in real time every second in degrees Celsius (C) with the highest average percentage error of 3.10% at a distance of 4 meters. DOI : https://doi.org/10.33005/sibc.v14i2.2679

A Method for Detecting and Analyzing Facial Features of People with Drug Use Disorders.

Drug use disorders caused by illicit drug use are significant contributors to the global burden of disease, and it is vital to conduct early detection of people with drug use disorders (PDUD). However, the primary care clinics and emergency departments lack simple and effective tools for screening PDUD. This study proposes a novel method to detect PDUD using facial images. Various experiments are designed to obtain the convolutional neural network (CNN) model by transfer learning based on a large-scale dataset (9870 images from PDUD and 19,567 images from GP (the general population)). Our results show that the model achieved 84.68%, 87.93%, and 83.01% in accuracy, sensitivity, and specificity in the dataset, respectively. To verify its effectiveness, the model is evaluated on external datasets based on real scenarios, and we found it still achieved high performance (accuracy > 83.69%, specificity > 90.10%, sensitivity > 80.00%). Our results also show differences between PDUD and GP in different facial areas. Compared with GP, the facial features of PDUD were mainly concentrated in the left cheek, right cheek, and nose areas (p < 0.001), which also reveals the potential relationship between mechanisms of drugs action and changes in facial tissues. This is the first study to apply the CNN model to screen PDUD in clinical practice and is also the first attempt to quantitatively analyze the facial features of PDUD. This model could be quickly integrated into the existing clinical workflow and medical care to provide capabilities.

Resource Optimization through Group, Pooling, Tests, Testing in the Detection of Asymptomatic People with COVID-19

Resource Optimization through Group, Pooling, Tests, Testing in the Detection of Asymptomatic People with COVID-19

Interferon gamma release assays for detection of latent Mycobacterium tuberculosis in older Hispanic people

Background:Interferon gamma release assays (IGRAs) are used to detect latent Mycobacterium tuberculosis (M.tb) infection (LTBI) in adults, but their performance in older people is not well-established. We evaluated IGRAs for LTBI detection in older Hispanic recent TB contacts (ReC) or community controls (CoC).Methods:Cross-sectional assessment of LTBI with T-SPOT.TB and/or QuantiFERON-Gold in-tube or –Plus assay in older (≥60 years) and adult (18–50 years) Hispanic people.Results:We enrolled 193 CoC (119 adults, 74 older persons) and 459 ReC (361 adults, 98 older persons). LTBI positivity increased with age in CoC (19%–59%, P<0.001), but was similar in ReC (59%–69%, P=0.329). Older people had lower concordance between IGRAs (kappa 0.465 vs 0.688 in adults) and more inconclusive results (indeterminate/borderline 11.6% vs 5.8% in adults, P=0.012). With simultaneous IGRAs, inconclusive results were resolved as positive or negative with the other IGRA. The magnitude of response to M.tb peptides in IGRAs was similar among age groups, but responsiveness to mitogens was lower in older people.Conclusions:IGRAs are suitable for LTBI detection in older people. Discordant and inconclusive findings are more prevalent in older people, but results are resolved when IGRA is repeated with a different IGRA test.

Detection of Inflatable Boats and People in Thermal Infrared with Deep Learning Methods.

Smuggling of drugs and cigarettes in small inflatable boats across border rivers is a serious threat to the EU’s financial interests. Early detection of such threats is challenging due to difficult and changing environmental conditions. This study reports on the automatic detection of small inflatable boats and people in a rough wild terrain in the infrared thermal domain. Three acquisition campaigns were carried out during spring, summer, and fall under various weather conditions. Three deep learning algorithms, namely, YOLOv2, YOLOv3, and Faster R-CNN working with six different feature extraction neural networks were trained and evaluated in terms of performance and processing time. The best performance was achieved with Faster R-CNN with ResNet101, however, processing requires a long time and a powerful graphics processing unit.

YOLO Algorithm for Detecting People in Social Distancing System

Social distancing is an effort to prevent the spread of the coronavirus. Several systems for monitoring social distancing have been developed. People detection is an essential step in implementing a social distancing system. Failure to detect people causes the social distancing system to be inaccurate. Two people who communicate cannot occur violations of social distancing because one person is not detected. Therefore, we propose a precise person detection method for the social distancing system. The proposed social distancing system uses the YOLOv3 method for people detection and Euclidean Distance for measuring the distance of social distancing. YOLOv3 can detect people's objects precisely, even people who are caught small by the camera. Experiments on two outdoor video datasets result in an F1 value of more than 0.8. This proposed system can serve as a reference for future social distancing research.

EXAMINATION OF COVID-19 DEATHS IN G-7 COUNTRIES BY PANEL DATA ANALYSIS METHOD

The Covid-19 outbreak continues as a pandemic that affects all societies today. Thousands of people died from the virus in question. With the cooperation of national and international organizations, struggles are being given to get rid of this pandemic. Within the scope of the fight, vaccination programs are applied to ensure permanent recovery while testing for the detection of infected people. But deaths from Covid-19 are increasing irrepressibly. In this context in the study, the number of tests applied in the 7 most developed countries of the world, the number of vaccine doses applied, the number of cases encountered and the number of deaths from Covid-19 was analyzed by panel data analysis method. It was predicted that the vaccines applied could reduce deaths from Covid-19. It was predicted that if each dose of vaccine administered increases, deaths from Covid-19 could decrease by 0.57 units. On the other hand, the increase in the number of cases has been observed to lead to an increase in deaths caused by Covid-19. The importance of the number of tests applied was also determined in the fight against Covid-19. As a result, the importance of vaccination activities in the fight against Covid-19 has been scientifically demonstrated with the model obtained. On average, it is predicted that both vaccines could save a person's life.

Cooperative People Tracking by Distributed Cameras Network

In the application of video surveillance, reliable people detection and tracking are always challenging tasks. The conventional single-camera surveillance system may encounter difficulties such as narrow-angle of view and dead space. In this paper, we proposed multi-cameras network architecture with an inter-camera hand-off protocol for cooperative people tracking. We use the YOLO model to detect multiple people in the video scene and incorporate the particle swarm optimization algorithm to track the person movement. When a person leaves the area covered by a camera and enters an area covered by another camera, these cameras can exchange relevant information for uninterrupted tracking. The motion smoothness (MS) metrics is proposed for evaluating the tracking quality of multi-camera networking system. We used a three-camera system for two persons tracking in overlapping scene for experimental evaluation. Most tracking person offsets at different frames were lower than 30 pixels. Only 0.15% of the frames showed abrupt increases in offsets pixel. The experiment results reveal that our multi-camera system achieves robust, smooth tracking performance.

Moving People Tracking and False Track Removing with Infrared Thermal Imaging by a Multirotor

Infrared (IR) thermal imaging can detect the warm temperature of the human body regardless of the light conditions, thus small drones equipped with the IR thermal camera can be utilized to recognize human activity for smart surveillance, road safety, and search and rescue missions. However, the unpredictable motion of the drone poses more challenges than a fixed camera. This paper addresses the detection and tracking of people through IR thermal video captured by a multirotor. For object detection, each frame is first registered with a reference frame to compensate for its coordinates. Then, the objects in each frame are segmented through k-means clustering and morphological operations. Falsely detected objects are removed considering the actual size and the shape of the object. The centroid of the segmented area is considered the measured position for target tracking. The track is initialized with two-point differencing initialization, and the target states are continuously estimated by the interacting multiple model (IMM) filter. The nearest neighbor association rule assigns the measurement to the track. Tracks that move slower than the minimum speed are terminated at the proposed criteria. In the experiments, three videos were captured with a long-wave IR band thermal imaging camera mounted on a multirotor. In the first and second videos, eight pedestrians on a pavement and three hikers on a mountain on winter nights were captured, respectively. In the third video, two walking people with complex backgrounds were captured on a windy summer day. The image characteristics vary between videos depending on the climate and surrounding objects, but the proposed scheme shows the robust performance in all cases; the average root mean squared errors in position and velocity are obtained as 0.08 m and 0.53 m/s, respectively for the first video, 0.06 m and 0.58 m/s, respectively for the second video, and 0.18 m and 1.84 m/s, respectively for the third video. The proposed method reduces false tracks from 10 to 1 in the third video.

Privacy-preserving AI-enabled video surveillance for social distancing: responsible design and deployment for public spaces

PurposeThe paper proposes a privacy-preserving artificial intelligence-enabled video surveillance technology to monitor social distancing in public spaces.Design/methodology/approachThe paper proposes a new Responsible Artificial Intelligence Implementation Framework to guide the proposed solution's design and development. It defines responsible artificial intelligence criteria that the solution needs to meet and provides checklists to enforce the criteria throughout the process. To preserve data privacy, the proposed system incorporates a federated learning approach to allow computation performed on edge devices to limit sensitive and identifiable data movement and eliminate the dependency of cloud computing at a central server.FindingsThe proposed system is evaluated through a case study of monitoring social distancing at an airport. The results discuss how the system can fully address the case study's requirements in terms of its reliability, its usefulness when deployed to the airport's cameras, and its compliance with responsible artificial intelligence.Originality/valueThe paper makes three contributions. First, it proposes a real-time social distancing breach detection system on edge that extends from a combination of cutting-edge people detection and tracking algorithms to achieve robust performance. Second, it proposes a design approach to develop responsible artificial intelligence in video surveillance contexts. Third, it presents results and discussion from a comprehensive evaluation in the context of a case study at an airport to demonstrate the proposed system's robust performance and practical usefulness.