Search results

1 – 10 of over 2000
Article
Publication date: 9 September 2014

Michael Winkler, Kai Michael Höver and Max Mühlhäuser

The purpose of this study is to present a depth information-based solution for automatic camera control, depending on the presenter’s moving positions. Talks, presentations and…

Abstract

Purpose

The purpose of this study is to present a depth information-based solution for automatic camera control, depending on the presenter’s moving positions. Talks, presentations and lectures are often captured on video to give a broad audience the possibility to (re-)access the content. As presenters are often moving around during a talk, it is necessary to steer recording cameras.

Design/methodology/approach

We use depth information from Kinect to implement a prototypical application to automatically steer multiple cameras for recording a talk.

Findings

We present our experiences with the system during actual lectures at a university. We found out that Kinect is applicable for tracking a presenter during a talk robustly. Nevertheless, our prototypical solution reveals potential for improvements, which we discuss in our future work section.

Originality/value

Tracking a presenter is based on a skeleton model extracted from depth information instead of using two-dimensional (2D) motion- or brightness-based image processing techniques. The solution uses a scalable networking architecture based on publish/subscribe messaging for controlling multiple video cameras.

Details

Interactive Technology and Smart Education, vol. 11 no. 3
Type: Research Article
ISSN: 1741-5659

Keywords

Article
Publication date: 9 September 2014

Benjamin Wulff, Alexander Fecke, Lisa Rupp and Kai-Christoph Hamborg

The purpose of this work is to present a prototype of the system and the results from a technical evaluation and a study on possible effects of recordings with active camera

Abstract

Purpose

The purpose of this work is to present a prototype of the system and the results from a technical evaluation and a study on possible effects of recordings with active camera control on the learner. An increasing number of higher education institutions have adopted the lecture recording technology in the past decade. Even though some solutions already show a very high degree of automation, active camera control can still only be realized with the use of human labor. Aiming to fill this gap, the LectureSight project is developing a free solution for active autonomous camera control for presentation recordings. The system uses a monocular overview camera to analyze the scene. Adopters can formulate camera control strategies in a simple scripting language to adjust the system’s behavior to the specific characteristics of a presentation site.

Design/methodology/approach

The system is based on a highly modularized architecture to make it easily extendible. The prototype has been tested in a seminar room and a large lecture hall. Furthermore, a study was conducted in which students from two universities prepared for a simulated exam with an ordinary lecture recording and a recording produced with the LectureSight technology.

Findings

The technical evaluation showed a good performance of the prototype but also revealed some technical constraints. The results of the psychological study give evidence that the learner might benefit from lecture videos in which the camera follows the presenter so that gestures and facial expression are easily perceptible.

Originality/value

The LectureSight project is the first open-source initiative to care about the topic of camera control for presentation recordings. This opens way for other projects building upon the LectureSight architecture. The simulated exam study gave evidence of a beneficial effect on students learning success and needs to be reproduced. Also, if the effect is proven to be consistent, the mechanism behind it is worth to be investigated further.

Details

Interactive Technology and Smart Education, vol. 11 no. 3
Type: Research Article
ISSN: 1741-5659

Keywords

Article
Publication date: 1 March 1981

Richard Baker

Hard‐wired analysers can extract position and dimension information from closed circuit television camera images, leading to the automation of both laboratory and industrial…

Abstract

Hard‐wired analysers can extract position and dimension information from closed circuit television camera images, leading to the automation of both laboratory and industrial measurement.

Details

Sensor Review, vol. 1 no. 3
Type: Research Article
ISSN: 0260-2288

Article
Publication date: 21 February 2020

Davide Schaumann, Nirit Putievsky Pilosof, Michal Gath-Morad and Yehuda E. Kalay

This study aims to use a narrative-based simulation approach to explore potential implications of including or excluding a dayroom in the design of an internal medicine ward.

Abstract

Purpose

This study aims to use a narrative-based simulation approach to explore potential implications of including or excluding a dayroom in the design of an internal medicine ward.

Design/methodology/approach

The approach involved: collecting data in facilities using field observations and experts’ interviews; modeling representative behavior patterns in the form of rule-based narratives that direct collaborative behaviors of virtual occupants; simulating the behavior patterns in two alternative design options, one of which includes a dayroom; and analyzing the simulation results with respect to selected key performance indicators of day-to-day operations and spatial occupancy, including occupant density in corridors, number and locations of staff-visitor interactions and duration of a doctors’ round procedure.

Findings

Simulation results suggest that the presence of a dayroom reduces visitors’ density in corridors and diminishes the number of staff–visitor interactions that can delay the performing of scheduled medical procedures.

Research limitations/implications

A high level of uncertainty is intrinsic to the simulation of future human behavior. Additional work is required to systematically collect large volumes of occupancy data in existing facilities, model additional narratives and develop validation protocols to assess the degree of uncertainty of the proposed model.

Originality/value

A limited number of studies explore how simulation can be used to study the impact of building design on operations. This study uses a narrative-based approach to address some of the limitations of existing methods, including discrete-event simulations. Preliminary results suggest that the lack of appropriate spaces for patients and visitors to socialize may cause potential disruptions to hospital operations.

Article
Publication date: 27 November 2017

Aqeel Farooq, Wadee Alhalabi and Sara M. Alahmadi

The purpose of this research work is to design and apply LabVIEW in the area of traffic maintenance and flow, by introducing improvements in the smart city. The objective is to…

1426

Abstract

Purpose

The purpose of this research work is to design and apply LabVIEW in the area of traffic maintenance and flow, by introducing improvements in the smart city. The objective is to introduce the automated human–machine interface (HMI) – a computer-based graphical user interface (GUI) – for measuring the traffic flow and detecting faults in poles.

Design/methodology/approach

This research paper is based on the use of LabVIEW for designing the HMI for a traffic system in a smart city. This includes considerable measures that are: smart flow of traffic, violation detection on the signal, fault measurement in the traffic pole, locking down of cars for emergency and measuring parameters inside the cars.

Findings

In this paper, the GUIs and the required circuitry for making improvements in the infrastructure of traffic systems have been designed and proposed, with their respective required hardware. Several measured conditions have been discussed in detail.

Research limitations/implications

PJRC Teensy 3.1 has been used because it contains enough general-purpose input–output (GPIO) pins required for monitoring parameters that are used for maintaining the necessary flow of traffic and monitor the proposed study case. A combination of sensors such as infrared, accelerometer, magnetic compass, temperature sensor, current sensors, ultrasonic sensor, fingerprint readers, etc. are used to create a monitoring environment for the application. Using Teensy and LabVIEW, the system costs less and is effective in terms of performance.

Practical implications

The microprocessor board shields for placing actuators and sensors and for attaching the input/output (I/O) to the LED indicators and display have been designed. A circuitry for scaling voltage, i.e. making sensor readings to read limits, has been designed. A combination of certain sensors, at different signals, will lead to a secure and more durable control of traffic. The proposed applications with its hardware and software cost less, are effective and can be easily used for making the city’s traffic services smart. For alarm levels, the desired alarm level can be set from the front panel for certain conditions from the monitoring station. For this, virtual channels can be created for allowing the operator to set any random value for limits. If the sensor value crosses the alarm value, then the corresponding alarm displays an alert. The system works by using efficient decision-making techniques and stores the data along with the corresponding time of operation, for future decisions.

Originality/value

This study is an advanced research of its category because it combines the field of electrical engineering, computer science and traffic systems by using LabVIEW.

Details

Journal of Science and Technology Policy Management, vol. 9 no. 2
Type: Research Article
ISSN: 2053-4620

Keywords

Article
Publication date: 29 March 2011

Halim Sayoud, Siham Ouamour and Salah Khennouf

The purpose of this paper is two‐fold. First, to deal with the problem of audio speaker localization and second, to deal with the problem of mobile camera control. The task of…

Abstract

Purpose

The purpose of this paper is two‐fold. First, to deal with the problem of audio speaker localization and second, to deal with the problem of mobile camera control. The task of speaker localization consists of determining the position of the active speaker and the task of camera control consists of orienting a mobile camera towards that active speaker. These steps represent the main task of speaker tracking, which is the global purpose of the research work.

Design/methodology/approach

In this approach, two‐channel‐based estimation of the speaker position is achieved by comparing the signals received by two cardioids microphones, which are placed the one against the other and separated by a fixed distance. The localization technique presented in this paper is inspired from the human ears, which act as two different sound observation points, enabling humans to estimate the direction of the speaking person with a good precision. Concerning the camera control part, the authors have conceived an automatic system for generating the command signals and controlling the rotation of the mobile camera by a stepper motor.

Findings

The off‐line experiments of speaker tracking by camera have been done in a small meeting room without echo cancelation. Results show the good performances of the proposed localization methods and a correct tracking by camera.

Practical implications

This new technique can be used for the automatic supervision of smart rooms.

Originality/value

The work described in this paper is original, since it uses only two microphones for the speaker localization.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 4 no. 1
Type: Research Article
ISSN: 1756-378X

Keywords

Article
Publication date: 15 July 2021

Nehemia Sugianto, Dian Tjondronegoro, Rosemary Stockdale and Elizabeth Irenne Yuwono

The paper proposes a privacy-preserving artificial intelligence-enabled video surveillance technology to monitor social distancing in public spaces.

Abstract

Purpose

The paper proposes a privacy-preserving artificial intelligence-enabled video surveillance technology to monitor social distancing in public spaces.

Design/methodology/approach

The 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.

Findings

The 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/value

The 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.

Details

Information Technology & People, vol. 37 no. 2
Type: Research Article
ISSN: 0959-3845

Keywords

Article
Publication date: 25 October 2022

Chen Chen, Tingyang Chen, Zhenhua Cai, Chunnian Zeng and Xiaoyue Jin

The traditional vision system cannot automatically adjust the feature point extraction method according to the type of welding seam. In addition, the robot cannot self-correct the…

Abstract

Purpose

The traditional vision system cannot automatically adjust the feature point extraction method according to the type of welding seam. In addition, the robot cannot self-correct the laying position error or machining error. To solve this problem, this paper aims to propose a hierarchical visual model to achieve automatic arc welding guidance.

Design/methodology/approach

The hierarchical visual model proposed in this paper is divided into two layers: welding seam classification layer and feature point extraction layer. In the welding seam classification layer, the SegNet network model is trained to identify the welding seam type, and the prediction mask is obtained to segment the corresponding point clouds. In the feature point extraction layer, the scanning path is determined by the point cloud obtained from the upper layer to correct laying position error. The feature points extraction method is automatically determined to correct machining error based on the type of welding seam. Furthermore, the corresponding specific method to extract the feature points for each type of welding seam is proposed. The proposed visual model is experimentally validated, and the feature points extraction results as well as seam tracking error are finally analyzed.

Findings

The experimental results show that the algorithm can well accomplish welding seam classification, feature points extraction and seam tracking with high precision. The prediction mask accuracy is above 90% for three types of welding seam. The proposed feature points extraction method for each type of welding seam can achieve sub-pixel feature extraction. For the three types of welding seam, the maximum seam tracking error is 0.33–0.41 mm, and the average seam tracking error is 0.11–0.22 mm.

Originality/value

The main innovation of this paper is that a hierarchical visual model for robotic arc welding is proposed, which is suitable for various types of welding seam. The proposed visual model well achieves welding seam classification, feature point extraction and error correction, which improves the automation level of robot welding.

Details

Industrial Robot: the international journal of robotics research and application, vol. 50 no. 2
Type: Research Article
ISSN: 0143-991X

Keywords

Article
Publication date: 20 April 2023

Vishva Payghode, Ayush Goyal, Anupama Bhan, Sailesh Suryanarayan Iyer and Ashwani Kumar Dubey

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…

Abstract

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.

Details

International Journal of Web Information Systems, vol. 19 no. 3/4
Type: Research Article
ISSN: 1744-0084

Keywords

1 – 10 of over 2000