Automatic fight detection in surveillance videos

2017 ◽  
Vol 13 (2) ◽  
pp. 130-156 ◽  
Author(s):  
Eugene Yujun Fu ◽  
Hong Va Leong ◽  
Grace Ngai ◽  
Stephen C.F. Chan
Keyword(s):  
Social Interaction ◽  
Signal Analysis ◽  
State Of The Art ◽  
The State ◽  
Data Sets ◽  
Bag Of Words ◽  
Content Type ◽  
Surveillance Videos ◽  
Motion Signal ◽  
Public Data

Purpose Social signal processing under affective computing aims at recognizing and extracting useful human social interaction patterns. Fight is a common social interaction in real life. A fight detection system finds wide applications. This paper aims to detect fights in a natural and low-cost manner. Design/methodology/approach Research works on fight detection are often based on visual features, demanding substantive computation and good video quality. In this paper, the authors propose an approach to detect fight events through motion analysis. Most existing works evaluated their algorithms on public data sets manifesting simulated fights, where the fights are acted out by actors. To evaluate real fights, the authors collected videos involving real fights to form a data set. Based on the two types of data sets, the authors evaluated the performance of their motion signal analysis algorithm, which was then compared with the state-of-the-art approach based on MoSIFT descriptors with Bag-of-Words mechanism, and basic motion signal analysis with Bag-of-Words. Findings The experimental results indicate that the proposed approach accurately detects fights in real scenarios and performs better than the MoSIFT approach. Originality/value By collecting and annotating real surveillance videos containing real fight events and augmenting with well-known data sets, the authors proposed, implemented and evaluated a low computation approach, comparing it with the state-of-the-art approach. The authors uncovered some fundamental differences between real and simulated fights and initiated a new study in discriminating real against simulated fight events, with very good performance.

scholarly journals A Benchmark and Evaluation of Non-Rigid Structure from Motion

2020 ◽  
Author(s):  
Sebastian Hoppe Nesgaard Jensen ◽  
Mads Emil Brix Doest ◽  
Henrik Aanæs ◽  
Alessio Del Bue
Keyword(s):  
Computer Vision ◽  
Structure From Motion ◽  
State Of The Art ◽  
The State ◽  
Quality Data ◽  
Data Set ◽  
Rigid Structure ◽  
Public Data ◽  
3D Information ◽  
Further Development

AbstractNon-rigid structure from motion (nrsfm), is a long standing and central problem in computer vision and its solution is necessary for obtaining 3D information from multiple images when the scene is dynamic. A main issue regarding the further development of this important computer vision topic, is the lack of high quality data sets. We here address this issue by presenting a data set created for this purpose, which is made publicly available, and considerably larger than the previous state of the art. To validate the applicability of this data set, and provide an investigation into the state of the art of nrsfm, including potential directions forward, we here present a benchmark and a scrupulous evaluation using this data set. This benchmark evaluates 18 different methods with available code that reasonably spans the state of the art in sparse nrsfm. This new public data set and evaluation protocol will provide benchmark tools for further development in this challenging field.

An experimental study on feature-based SLAM for multi-legged robots with RGB-D sensors

2017 ◽  
Vol 44 (4) ◽  
pp. 428-441 ◽  
Author(s):  
Michał R. Nowicki ◽  
Dominik Belter ◽  
Aleksander Kostusiak ◽  
Petr Cížek ◽  
Jan Faigl ◽  
...  
Keyword(s):  
Performance Metrics ◽  
State Of The Art ◽  
Building Blocks ◽  
Bundle Adjustment ◽  
The State ◽  
Legged Robots ◽  
Evaluation Methodology ◽  
Walking Robots ◽  
Content Type ◽  
Feature Based

Purpose This paper aims to evaluate four different simultaneous localization and mapping (SLAM) systems in the context of localization of multi-legged walking robots equipped with compact RGB-D sensors. This paper identifies problems related to in-motion data acquisition in a legged robot and evaluates the particular building blocks and concepts applied in contemporary SLAM systems against these problems. The SLAM systems are evaluated on two independent experimental set-ups, applying a well-established methodology and performance metrics. Design/methodology/approach Four feature-based SLAM architectures are evaluated with respect to their suitability for localization of multi-legged walking robots. The evaluation methodology is based on the computation of the absolute trajectory error (ATE) and relative pose error (RPE), which are performance metrics well-established in the robotics community. Four sequences of RGB-D frames acquired in two independent experiments using two different six-legged walking robots are used in the evaluation process. Findings The experiments revealed that the predominant problem characteristics of the legged robots as platforms for SLAM are the abrupt and unpredictable sensor motions, as well as oscillations and vibrations, which corrupt the images captured in-motion. The tested adaptive gait allowed the evaluated SLAM systems to reconstruct proper trajectories. The bundle adjustment-based SLAM systems produced best results, thanks to the use of a map, which enables to establish a large number of constraints for the estimated trajectory. Research limitations/implications The evaluation was performed using indoor mockups of terrain. Experiments in more natural and challenging environments are envisioned as part of future research. Practical implications The lack of accurate self-localization methods is considered as one of the most important limitations of walking robots. Thus, the evaluation of the state-of-the-art SLAM methods on legged platforms may be useful for all researchers working on walking robots’ autonomy and their use in various applications, such as search, security, agriculture and mining. Originality/value The main contribution lies in the integration of the state-of-the-art SLAM methods on walking robots and their thorough experimental evaluation using a well-established methodology. Moreover, a SLAM system designed especially for RGB-D sensors and real-world applications is presented in details.

Fast and accurate detection of surface defect based on improved YOLOv4

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Jiawei Lian ◽  
Junhong He ◽  
Yun Niu ◽  
Tianze Wang
Keyword(s):  
Feature Extraction ◽  
Real Time ◽  
Surface Defect ◽  
Steel Ingot ◽  
Industrial Applications ◽  
Data Sets ◽  
Data Set ◽  
Processing Technologies ◽  
Content Type ◽  
Public Data

Purpose The current popular image processing technologies based on convolutional neural network have the characteristics of large computation, high storage cost and low accuracy for tiny defect detection, which is contrary to the high real-time and accuracy, limited computing resources and storage required by industrial applications. Therefore, an improved YOLOv4 named as YOLOv4-Defect is proposed aim to solve the above problems. Design/methodology/approach On the one hand, this study performs multi-dimensional compression processing on the feature extraction network of YOLOv4 to simplify the model and improve the feature extraction ability of the model through knowledge distillation. On the other hand, a prediction scale with more detailed receptive field is added to optimize the model structure, which can improve the detection performance for tiny defects. Findings The effectiveness of the method is verified by public data sets NEU-CLS and DAGM 2007, and the steel ingot data set collected in the actual industrial field. The experimental results demonstrated that the proposed YOLOv4-Defect method can greatly improve the recognition efficiency and accuracy and reduce the size and computation consumption of the model. Originality/value This paper proposed an improved YOLOv4 named as YOLOv4-Defect for the detection of surface defect, which is conducive to application in various industrial scenarios with limited storage and computing resources, and meets the requirements of high real-time and precision.

Website traffic measurement and rankings: competitive intelligence tools examination

2018 ◽  
Vol 14 (4) ◽  
pp. 423-437 ◽  
Author(s):  
David Prantl ◽  
Martin Prantl
Keyword(s):  
Design Methodology ◽  
State Of The Art ◽  
Competitive Intelligence ◽  
Data Sets ◽  
Traffic Data ◽  
Content Type ◽  
Traffic Measurement ◽  
Data Estimation ◽  
Research Studies

PurposeThe purpose of this paper is to examine and verify the competitive intelligence tools Alexa and SimilarWeb, which are broadly used for website traffic data estimation. Tested tools belong to the state of the art in this area.Design/methodology/approachThe authors use quantitative approach. Research was conducted on a sample of Czech websites for which there are accurate traffic data values, against which the other data sets (less accurate) provided by Alexa and SimilarWeb will be compared.FindingsThe results show that neither tool can accurately determine the ranking of websites on the internet. However, it is possible to approximately determine the significance of a particular website. These results are useful for another research studies which use data from Alexa or SimilarWeb. Moreover, the results show that it is still not possible to accurately estimate website traffic of any website in the world.Research limitations/implicationsThe limitation of the research lies in the fact that it was conducted solely in the Czech market.Originality/valueSignificant amount of research studies use data sets provided by Alexa and SimilarWeb. However, none of these research studies focus on the quality of the website traffic data acquired by Alexa or SimilarWeb, nor do any of them refer to other studies that would deal with this issue. Furthermore, authors describe approaches to measuring website traffic and based on the analysis, the possible usability of these methods is discussed.

A new correlation-based approach for ensemble selection in random forests

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Mostafa El Habib Daho ◽  
Nesma Settouti ◽  
Mohammed El Amine Bechar ◽  
Amina Boublenza ◽  
Mohammed Amine Chikh
Keyword(s):  
State Of The Art ◽  
Ensemble Methods ◽  
The State ◽  
Ensemble Classifiers ◽  
Content Type ◽  
Pruning Method ◽  
Ensemble Selection ◽  
Small Ensemble ◽  
Short Time ◽  
Pruning Techniques

PurposeEnsemble methods have been widely used in the field of pattern recognition due to the difficulty of finding a single classifier that performs well on a wide variety of problems. Despite the effectiveness of these techniques, studies have shown that ensemble methods generate a large number of hypotheses and that contain redundant classifiers in most cases. Several works proposed in the state of the art attempt to reduce all hypotheses without affecting performance.Design/methodology/approachIn this work, the authors are proposing a pruning method that takes into consideration the correlation between classifiers/classes and each classifier with the rest of the set. The authors have used the random forest algorithm as trees-based ensemble classifiers and the pruning was made by a technique inspired by the CFS (correlation feature selection) algorithm.FindingsThe proposed method CES (correlation-based Ensemble Selection) was evaluated on ten datasets from the UCI machine learning repository, and the performances were compared to six ensemble pruning techniques. The results showed that our proposed pruning method selects a small ensemble in a smaller amount of time while improving classification rates compared to the state-of-the-art methods.Originality/valueCES is a new ordering-based method that uses the CFS algorithm. CES selects, in a short time, a small sub-ensemble that outperforms results obtained from the whole forest and the other state-of-the-art techniques used in this study.

Process-oriented disaster response management: a structured literature review

2015 ◽  
Vol 21 (5) ◽  
pp. 966-987 ◽  
Author(s):  
Marlen Hofmann ◽  
Hans Betke ◽  
Stefan Sackmann
Keyword(s):  
Literature Review ◽  
Business Process ◽  
Disaster Response ◽  
State Of The Art ◽  
The State ◽  
Wide Field ◽  
Content Type ◽  
Process Oriented ◽  
Disaster Response Management ◽  
Structured Literature Review

Purpose – The application of business process methods in the domain of disaster response management (DRM) is seen as promising approach due to the similarity of business processes and disaster response processes at the general structure and goals. But up to now only a few approaches were able to handle the special characteristics of the DRM domain. Thus, the purpose of this paper is to identify the existing approaches and analyze them for the discussion of general requirements for applying methods and tools from business process management to DRM. Design/methodology/approach – A structured literature review covering a wide field of information system-related publications (conferences and journals) is used to identify and classify general requirements discussed as the state of the art. Findings – The work in this paper resulted in a suitable classification of requirements for the development of process-oriented DRM approaches deduced from the existing work. This was used to outline and analyze the current research landscape of this topic and identify research gaps as well as existing limitations. Research limitations/implications – Although the review of the state of the art is based on a wide set of publication databases, there may exist relevant research papers which have not been taken into consideration. Originality/value – The elaborated requirements provide value for both the research community and practitioners. They can be considered to develop new or improve existing DRM systems and, thus, to exploit the potentials of process-oriented IT in supporting DRM in the case of disaster.

The role of sustainability in the relationship between migration and smart cities: a bibliometric review

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ali Mohamad Mouazen ◽  
Ana Beatriz Hernández-Lara
Keyword(s):  
State Of The Art ◽  
Smart Cities ◽  
Developed Countries ◽  
The State ◽  
Social Dimension ◽  
Content Type ◽  
Bibliometric Review ◽  
And Migration ◽  
The Relationship

Purpose Smart cities attract efficient and profitable economic activities, contribute to the societal welfare of their citizens and foster the efficient use and conservation of natural resources. Developing smart cities has become a priority for many developed countries, but as they are preferred destinations for migrants, this raises sustainability issues. They attract people who are seeking a better quality of life, smart services and solutions, a better environment and business activities. The purpose of this paper is to review the state of the art on the relationship between smart cities and migration, with a view to determining sustainability. Design/methodology/approach A bibliometric review and text mining analyses were conducted on publications between 2000 and 2019. Findings The results determined the main parameters of this research topic in terms of its growth, top journals and articles. The role of sustainability in the relationship between smart cities and migration is also identified, highlighting the special interest of its social dimension. Originality/value A bibliometric approach has not been used previously to investigate the link between smart cities and migration. However, given the current relevance of both phenomena, their emergence and growth, this approach is appropriate in determining the state of the art and its main descriptors, with special emphasis on the sustainability implications.

Debunking the myth of industry 4.0 in health care: insights from a systematic literature review

2020 ◽  
Vol 32 (4) ◽  
pp. 849-868 ◽  
Author(s):  
Mauro Cavallone ◽  
Rocco Palumbo
Keyword(s):  
Artificial Intelligence ◽  
Health Care ◽  
Health Services ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Industry 4.0 ◽  
Services Quality ◽  
State Of The Art ◽  
The State ◽  
Content Type

PurposeIndustry 4.0, artificial intelligence and digitalization have got a momentum in health care. However, scholars and practitioners do not agree on their implications on health services' quality and effectiveness. The article aims at shedding light on the applications, aftermaths and drawbacks of industry 4.0 in health care, summarizing the state of the art.Design/methodology/approachA systematic literature review was undertaken. We arranged an ad hoc research design, which was tailored to the study purposes. Three citation databases were queried. We collected 1,194 scientific papers which were carefully considered for inclusion in this systematic literature review. After three rounds of analysis, 40 papers were taken into consideration.FindingsIndustry 4.0, artificial intelligence and digitalization are revolutionizing the design and the delivery of care. They are expected to enhance health services' quality and effectiveness, paving the way for more direct patient–provider relationships. In addition, they have been argued to allow a more appropriate use of available resources. There is a dark side of health care 4.0 involving both management and ethical issues.Research limitations/implicationsIndustry 4.0 in health care should not be conceived as a self-nourishing innovation; rather, it needs to be carefully steered at both the policy and management levels. On the one hand, comprehensive governance models are required to realize the full potential of health 4.0. On the other hand, the drawbacks of industry 4.0 should be timely recognized and thoroughly addressed.Originality/valueThe article contextualizes the state of the art of industry 4.0 in the health care context, providing some insights for further conceptual and empirical developments.

Open innovation actions and innovation performance

2015 ◽  
Vol 18 (2) ◽  
pp. 150-171 ◽  
Author(s):  
Marco Greco ◽  
Michele Grimaldi ◽  
Livio Cricelli
Keyword(s):  
Open Innovation ◽  
State Of The Art ◽  
The State ◽  
Innovation Performance ◽  
European Countries ◽  
Future Directions ◽  
Content Type ◽  
Process Innovations ◽  
Product And Process Innovation ◽  
Product And Process

Purpose – The purpose of this paper is to identify the recurrences in the empirical evidences that link open innovation (OI) actions and innovation performance in European countries. It provides managers with useful strategic suggestions, emphasizes the limitations of the state of the art, and recommends future directions of research. Design/methodology/approach – The authors systematically reviewed empirical articles linking OI actions and innovation performance in European countries, published on peer reviewed journals from January 2003 until May 2013. The authors organized the evidences according to a novel taxonomy grounded in the literature. Findings – The paper shows an increasing interest in the research of empirical evidence regarding OI and innovation performance. Nonetheless, evidence of the role played by outbound OI activities are extremely rare. The authors found that process innovations are more likely to benefit from coupled OI activities rather than inbound activities. Moreover, the effect of coupled depth actions on both product and process innovation performance was always positive in the reviewed articles. The authors also discuss how scholars measure innovation performance, pointing out the criticalities. Research limitations/implications – The paper allows analysing the empirical evidences found in the literature, emphasizing the limitations of the state of the art and recommending future directions of research. Practical implications – The systematization of the empirical evidences found in the European literature provides managers with useful strategic suggestions to improve their organizations’ innovation performances. Originality/value – The paper contains a complete and extensive analysis of empirical OI literature with respect to European countries. The articles and their findings are organized according to a novel taxonomy useful to identify evidences and recurrences in a synoptic manner.

scholarly journals Strategies for Prevention and Treatment of Trichomonas vaginalis Infections

2017 ◽  
Vol 30 (3) ◽  
pp. 811-825 ◽  
Author(s):  
Kawthar Bouchemal ◽  
Christian Bories ◽  
Philippe M. Loiseau
Keyword(s):  
Treatment Outcomes ◽  
Critical Review ◽  
Trichomonas Vaginalis ◽  
State Of The Art ◽  
Topical Administration ◽  
The State ◽  
Annual Incidence ◽  
Content Type ◽  
Treatment And Prevention ◽  
Prevention And Treatment

SUMMARY The last estimated annual incidence of Trichomonas vaginalis worldwide exceeds that of chlamydia and gonorrhea combined. This critical review updates the state of the art on advances in T. vaginalis diagnostics and strategies for treatment and prevention of trichomoniasis. In particular, new data on treatment outcomes for topical administration of formulations are reviewed and discussed.

Sign in / Sign up

Export Citation Format

Share Document