scholarly journals Deep Abnormality Detection in Video Data

2017 ◽  
Author(s):  
Hung Vu
Keyword(s):  
Detection System ◽  
Automated Detection ◽  
Video Data ◽  
Feature Representation ◽  
Training Data ◽  
Surveillance Systems ◽  
Abnormality Detection ◽  
Probabilistic Framework ◽  
Detection Systems ◽  
Multiple Levels

Automated detection of anomalous events plays an important role in video surveillance systems in practice. This task, however, requires to deal with three challenging problems of the lack of annotated training data, the inexact description of what to be "abnormal" and the expensive feature engineering procedure. Most anomaly detection systems are only able to satisfy some of these challenges. In this work, we propose a deep abnormality detection system to handle all of them simultaneously. Deep abnormality detection is a deep generative network that is an unsupervised probabilistic framework to model the normality and learn feature representation automatically. Furthermore, unlike other existing methods, our system can detect abnormality at multiple levels and be used as a powerful tool for video analysis and scene understanding.

scholarly journals The Use of Closed-Circuit Television and Video in Suicide Prevention: Narrative Review and Future Directions

10.2196/27663 ◽  
2021 ◽  
Vol 8 (5) ◽  
pp. e27663
Author(s):  
Sandersan Onie ◽  
Xun Li ◽  
Morgan Liang ◽  
Arcot Sowmya ◽  
Mark Erik Larsen
Keyword(s):  
Computer Vision ◽  
Early Intervention ◽  
Suicide Attempt ◽  
Detection System ◽  
Automated Detection ◽  
Video Data ◽  
Narrative Review ◽  
Closed Circuit ◽  
Closed Circuit Television ◽  
Area Of Interest

Background Suicide is a recognized public health issue, with approximately 800,000 people dying by suicide each year. Among the different technologies used in suicide research, closed-circuit television (CCTV) and video have been used for a wide array of applications, including assessing crisis behaviors at metro stations, and using computer vision to identify a suicide attempt in progress. However, there has been no review of suicide research and interventions using CCTV and video. Objective The objective of this study was to review the literature to understand how CCTV and video data have been used in understanding and preventing suicide. Furthermore, to more fully capture progress in the field, we report on an ongoing study to respond to an identified gap in the narrative review, by using a computer vision–based system to identify behaviors prior to a suicide attempt. Methods We conducted a search using the keywords “suicide,” “cctv,” and “video” on PubMed, Inspec, and Web of Science. We included any studies which used CCTV or video footage to understand or prevent suicide. If a study fell into our area of interest, we included it regardless of the quality as our goal was to understand the scope of how CCTV and video had been used rather than quantify any specific effect size, but we noted the shortcomings in their design and analyses when discussing the studies. Results The review found that CCTV and video have primarily been used in 3 ways: (1) to identify risk factors for suicide (eg, inferring depression from facial expressions), (2) understanding suicide after an attempt (eg, forensic applications), and (3) as part of an intervention (eg, using computer vision and automated systems to identify if a suicide attempt is in progress). Furthermore, work in progress demonstrates how we can identify behaviors prior to an attempt at a hotspot, an important gap identified by papers in the literature. Conclusions Thus far, CCTV and video have been used in a wide array of applications, most notably in designing automated detection systems, with the field heading toward an automated detection system for early intervention. Despite many challenges, we show promising progress in developing an automated detection system for preattempt behaviors, which may allow for early intervention.

scholarly journals The Use of Closed-Circuit Television and Video in Suicide Prevention: Narrative Review and Future Directions (Preprint)

2021 ◽  
Author(s):  
Sandersan Onie ◽  
Xun Li ◽  
Morgan Liang ◽  
Arcot Sowmya ◽  
Mark Erik Larsen
Keyword(s):  
Computer Vision ◽  
Early Intervention ◽  
Suicide Attempt ◽  
Detection System ◽  
Automated Detection ◽  
Video Data ◽  
Narrative Review ◽  
Closed Circuit ◽  
Closed Circuit Television ◽  
Area Of Interest

BACKGROUND Suicide is a recognized public health issue, with approximately 800,000 people dying by suicide each year. Among the different technologies used in suicide research, closed-circuit television (CCTV) and video have been used for a wide array of applications, including assessing crisis behaviors at metro stations, and using computer vision to identify a suicide attempt in progress. However, there has been no review of suicide research and interventions using CCTV and video. OBJECTIVE The objective of this study was to review the literature to understand how CCTV and video data have been used in understanding and preventing suicide. Furthermore, to more fully capture progress in the field, we report on an ongoing study to respond to an identified gap in the narrative review, by using a computer vision–based system to identify behaviors prior to a suicide attempt. METHODS We conducted a search using the keywords “suicide,” “cctv,” and “video” on PubMed, Inspec, and Web of Science. We included any studies which used CCTV or video footage to understand or prevent suicide. If a study fell into our area of interest, we included it regardless of the quality as our goal was to understand the scope of how CCTV and video had been used rather than quantify any specific effect size, but we noted the shortcomings in their design and analyses when discussing the studies. RESULTS The review found that CCTV and video have primarily been used in 3 ways: (1) to identify risk factors for suicide (eg, inferring depression from facial expressions), (2) understanding suicide after an attempt (eg, forensic applications), and (3) as part of an intervention (eg, using computer vision and automated systems to identify if a suicide attempt is in progress). Furthermore, work in progress demonstrates how we can identify behaviors prior to an attempt at a hotspot, an important gap identified by papers in the literature. CONCLUSIONS Thus far, CCTV and video have been used in a wide array of applications, most notably in designing automated detection systems, with the field heading toward an automated detection system for early intervention. Despite many challenges, we show promising progress in developing an automated detection system for preattempt behaviors, which may allow for early intervention.

scholarly journals Three Ways to Improve the Performance of Real-Life Camera-Based Fall Detection Systems

2017 ◽  
Vol 2017 ◽  
pp. 1-15 ◽  
Author(s):  
Glen Debard ◽  
Marc Mertens ◽  
Toon Goedemé ◽  
Tinne Tuytelaars ◽  
Bart Vanrumste
Keyword(s):  
False Alarm ◽  
Detection System ◽  
Real Life ◽  
Fall Detection ◽  
Training Data ◽  
False Alarms ◽  
Detection Systems ◽  
Number Of False Alarms ◽  
Real Life Data ◽  
Precision Recall Curve

More than thirty percent of persons over 65 years fall at least once a year and are often not able to get up again. Camera-based fall detection systems can help by triggering an alarm when falls occur. Previously we showed that real-life data poses significant challenges, resulting in high false alarm rates. Here, we show three ways to tackle this. First, using a particle filter combined with a person detector increases the robustness of our foreground segmentation, reducing the number of false alarms by 50%. Second, selecting only nonoccluded falls for training further decreases the false alarm rate on average from 31.4 to 26 falls per day. But, most importantly, this improvement is also shown by the doubling of the AUC of the precision-recall curve compared to using all falls. Third, personalizing the detector by adding several days containing only normal activities, no fall incidents, of the monitored person to the training data further increases the robustness of our fall detection system. In one case, this reduced the number of false alarms by a factor of 7 while in another one the sensitivity increased by 17% for an increase of the false alarms of 11%.

LSO-AdaBoost Based Face Detection for IP-CAM Video

2013 ◽  
Vol 284-287 ◽  
pp. 3543-3548 ◽  
Author(s):  
Chuang Jan Chang ◽  
Shu Lin Hwang
Keyword(s):  
Video Surveillance ◽  
Face Detection ◽  
Motion Detection ◽  
Detection Rate ◽  
Detection System ◽  
Training Data ◽  
Surveillance Systems ◽  
High Detection Rate ◽  
Data Set ◽  
Adaboost Algorithm

The IP-CAM plays a major role in the context of digital video surveillance systems. The function of face detection can add extra value and can contribute towards an intelligent video surveillance system. The cascaded AdaBoost-based face detection system proposed by Viola can support real-time detection with a high detection rate. The performance of the Alt2 cascade (from OpenCV) in an IP-CAM video is worse than that with regard to static images because the training data set in the Alt2 cannot consider the localized characters in the special IP-CAM video. Therefore, this study presents an enhanced training method using the Adaboost algorithm which is capable of obtaining the localized sampling optimum (LSO) from a local IP-CAM video. In addition, we use an improved motion detection algorithm that cooperates with the former face detector to speed up processing time and achieve a better detection rate on video-rate processing speed. The proposed solution has been developed around the cascaded AdaBoost approach, using the open-CV library, with a LSO from a local IP-CAM video. An efficient motion detection model is adopted for practical applications. The overall system performance using 30% local samples can be improved to a 97.9% detection rate and reduce detection time by 54.5% with regard to the Alt2 cascade.

scholarly journals A Deep Learning Using DenseNet201 to Detect Masked or Non-masked Face

2021 ◽  
Vol 9 (1) ◽  
pp. 115
Author(s):  
Faisal Dharma Adhinata ◽  
Diovianto Putra Rakhmadani ◽  
Merlinda Wibowo ◽  
Akhmad Jayadi
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Face Detection ◽  
Detection System ◽  
Video Data ◽  
Training Data ◽  
Public Places ◽  
Learning Techniques ◽  
The Face ◽  
F Measure

The use of masks on the face in public places is an obligation for everyone because of the Covid-19 pandemic, which claims victims. Indonesia made 3M policies, one of which is to use masks to prevent coronavirus transmission. Currently, several researchers have developed a masked or non-masked face detection system. One of them is using deep learning techniques to classify a masked or non-masked face. Previous research used the MobileNetV2 transfer learning model, which resulted in an F-Measure value below 0.9. Of course, this result made the detection system not accurate enough. In this research, we propose a model with more parameters, namely the DenseNet201 model. The number of parameters of the DenseNet201 model is five times more than that of the MobileNetV2 model. The results obtained from several up to 30 epochs show that the DenseNet201 model produces 99% accuracy when training data. Then, we tested the matching feature on video data, the DenseNet201 model produced an F-Measure value of 0.98, while the MobileNetV2 model only produced an F-measure value of 0.67. These results prove the masked or non-masked face detection system is more accurate using the DenseNet201 model.

Infill Defective Detection System Augmented by Semi-Supervised Learning

2020 ◽  
Author(s):  
Jinwoo Song ◽  
Young B. Moon
Keyword(s):  
Feature Extraction ◽  
Additive Manufacturing ◽  
Supervised Learning ◽  
Network Model ◽  
Detection System ◽  
Cyber Attacks ◽  
Training Data ◽  
Detection Accuracy ◽  
Data Sets ◽  
Detection Systems

Abstract In an effort to identify cyber-attacks on infill structures, detection systems based on supervised learning have been attempted in Additive Manufacturing (AM) security investigations. However, supervised learning requires a myriad of training data sets to achieve acceptable detection accuracy. Besides, since it is impossible to train for unprecedented defective types, the detection systems cannot guarantee robustness against unforeseen attacks. To overcome such disadvantages of supervised learning, This paper presents infill defective detection system (IDDS) augmented by semi-supervised learning. Semi-supervised learning allows classifying a sheer volume of unlabeled data sets by training a comparably small number of labeled data sets. Additionally, IDDS exploits self-training to increase the robustness against various defective types that are not pre-trained. IDDS consists of the feature extraction, pre-training, self-training. To validate the usefulness of IDDS, five defective types were designed and tested with IDDS, which was trained by only normal labeled data sets. The results are compared with the basis accuracy from the perceptron network model with supervised learning.

scholarly journals Transcription Alignment of Historical Vietnamese Manuscripts without Human-Annotated Learning Samples

2021 ◽  
Vol 11 (11) ◽  
pp. 4894
Author(s):  
Anna Scius-Bertrand ◽  
Michael Jungo ◽  
Beat Wolf ◽  
Andreas Fischer ◽  
Marc Bui
Keyword(s):  
Object Detection ◽  
State Of The Art ◽  
Positive Impact ◽  
Detection System ◽  
Training Data ◽  
Detection Accuracy ◽  
Current State ◽  
Alignment Task ◽  
Scanned Image ◽  
Automatic Transcription

The current state of the art for automatic transcription of historical manuscripts is typically limited by the requirement of human-annotated learning samples, which are are necessary to train specific machine learning models for specific languages and scripts. Transcription alignment is a simpler task that aims to find a correspondence between text in the scanned image and its existing Unicode counterpart, a correspondence which can then be used as training data. The alignment task can be approached with heuristic methods dedicated to certain types of manuscripts, or with weakly trained systems reducing the required amount of annotations. In this article, we propose a novel learning-based alignment method based on fully convolutional object detection that does not require any human annotation at all. Instead, the object detection system is initially trained on synthetic printed pages using a font and then adapted to the real manuscripts by means of self-training. On a dataset of historical Vietnamese handwriting, we demonstrate the feasibility of annotation-free alignment as well as the positive impact of self-training on the character detection accuracy, reaching a detection accuracy of 96.4% with a YOLOv5m model without using any human annotation.

scholarly journals Design of a Microwave Power Detection System in the 5G-Communication Frequency Band

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2674
Author(s):  
Qingying Ren ◽  
Wen Zuo ◽  
Jie Xu ◽  
Leisheng Jin ◽  
Wei Li ◽  
...  
Keyword(s):  
Frequency Band ◽  
Microwave Power ◽  
Communication Systems ◽  
Detection System ◽  
Measurement Sensitivity ◽  
Detection Range ◽  
Detection Systems ◽  
Detection Frequency ◽  
Communication Frequency ◽  
5G Communication

At present, the proposed microwave power detection systems cannot provide a high dynamic detection range and measurement sensitivity at the same time. Additionally, the frequency band of these detection systems cannot cover the 5G-communication frequency band. In this work, a novel microwave power detection system is proposed to measure the power of the 5G-communication frequency band. The detection system is composed of a signal receiving module, a power detection module and a data processing module. Experiments show that the detection frequency band of this system ranges from 1.4 GHz to 5.3 GHz, the dynamic measurement range is 70 dB, the minimum detection power is −68 dBm, and the sensitivity is 22.3 mV/dBm. Compared with other detection systems, the performance of this detection system in the 5G-communication frequency band is significantly improved. Therefore, this microwave power detection system has certain reference significance and application value in the microwave signal detection of 5G communication systems.

scholarly journals Gait Phase Detection Based on Muscle Deformation with Static Standing-Based Calibration

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1081
Author(s):  
Tamon Miyake ◽  
Shintaro Yamamoto ◽  
Satoshi Hosono ◽  
Satoshi Funabashi ◽  
Zhengxue Cheng ◽  
...  
Keyword(s):  
Learning Algorithm ◽  
Detection System ◽  
Calibration Method ◽  
Detection Algorithm ◽  
Video Data ◽  
Detection Accuracy ◽  
Phase Detection ◽  
Gait Phase ◽  
Logistic Regression Algorithm ◽  
Short Time

Gait phase detection, which detects foot-contact and foot-off states during walking, is important for various applications, such as synchronous robotic assistance and health monitoring. Gait phase detection systems have been proposed with various wearable devices, sensing inertial, electromyography, or force myography information. In this paper, we present a novel gait phase detection system with static standing-based calibration using muscle deformation information. The gait phase detection algorithm can be calibrated within a short time using muscle deformation data by standing in several postures; it is not necessary to collect data while walking for calibration. A logistic regression algorithm is used as the machine learning algorithm, and the probability output is adjusted based on the angular velocity of the sensor. An experiment is performed with 10 subjects, and the detection accuracy of foot-contact and foot-off states is evaluated using video data for each subject. The median accuracy is approximately 90% during walking based on calibration for 60 s, which shows the feasibility of the static standing-based calibration method using muscle deformation information for foot-contact and foot-off state detection.

Sign in / Sign up

Export Citation Format

Share Document