Webcam Research Articles

Development of a Test Bench to Solve a Simple Labyrinth

This paper deals with building an automatic test bench for detecting and solving a simple maze. There are many suitable sensors for detecting walls and ball, as find quick and stabile algorithm for deliver the ball to the target. Two servo motor are used to tilt the table of the maze. The first part of the paper shows the experiences of using OV7076 camera with Arduino Nano which was used for the first time to solve the problem. The final version of the maze solver contains a USB camera, an Arduino UNO platform, OpenCV and PyCharm software. Furthermore, paper reveals possibilities of decision-making-process and the direction of following research work.

Pupil Dynamics-derived Sleep Stage Classification of a Head-fixed Mouse Using a Recurrent Neural Network.

The standard method for sleep state classification is thresholding the amplitudes of electroencephalography (EEG) and electromyography (EMG) data, followed by manual correction by an expert. Although popular, this method has some shortcomings: (1) the time-consuming manual correction by human experts is sometimes a bottleneck hindering sleep studies, (2) EEG electrodes on the skull interfere with wide-field imaging of the cortical activity of a head-fixed mouse under a microscope, (3) invasive surgery to fix the electrodes on the thin mouse skull risks brain tissue injury, and (4) metal electrodes for EEG and EMG recording are difficult to apply to some experimental apparatus such as that for functional magnetic resonance imaging. To overcome these shortcomings, we propose a pupil dynamics-based vigilance state classification method for a head-fixed mouse using a long short-term memory (LSTM) model, a variant of a recurrent neural network, for multi-class labeling of NREM, REM, and WAKE states. For supervisory hypnography, EEG and EMG recording were performed on head-fixed mice. This setup was combined with left eye pupillometry using a USB camera and a markerless tracking toolbox, DeepLabCut. Our open-source LSTM model with feature inputs of pupil diameter, pupil location, pupil velocity, and eyelid opening for 10 s at a 10 Hz sampling rate achieved vigilance state estimation with a higher classification performance (macro F1 score, 0.77; accuracy, 86%) than a feed-forward neural network. Findings from a diverse range of pupillary dynamics implied possible subdivision of the vigilance states defined by EEG and EMG. Pupil dynamics-based hypnography can expand the scope of alternatives for sleep stage scoring of head-fixed mice.

Preparation of a Flow Single-drop Extraction System for Educational Use Capable of the Simultaneous and Continuous Observation of Extraction Behavior and Absorbance Change

A portable flow single-drop extraction system was prepared as an educational tool for facilitating the connection between actual extraction behavior and theory. In this system, an aqueous dye solution is circulated through a ring-shaped extraction cell equipped with a droplet introduction unit and a flow cell for absorbance detection. The dye is extracted into a droplet in the extraction cell. This system enables simultaneous and continuous observation of the image of the droplet in the extraction cell and changes in absorption spectrum or absorbance over time on the same screen by using a USB camera. It was suggested that the material balance in the extraction can be calculated from the decrease in absorbance of the circulating dye solution and the absorbance of the droplet after the extraction.

An accurate identification method for network devices based on spatial attention mechanism

With the metaverse being the development direction of the next generation Internet, the popularity of intelligent devices, and the maturity of various emerging technologies, more and more intelligent devices try to connect to the Internet, which poses a major threat to the management and security protection of network equipment. At present, the mainstream method of network equipment identification in the metaverse is to obtain the network traffic data generated in the process of device communication, extract the device features through analysis and processing, and identify the device based on a variety of learning algorithms. Such methods often require manual participation, and it is difficult to capture the small differences between similar devices, leading to identification errors. Therefore, we propose a deep learning device recognition method based on a spatial attention mechanism. Firstly, we extract the required feature fields from the acquired network traffic data. Then, we normalize the data and convert it into grayscale images. After that, we add a spatial attention mechanism to CNN and MLP respectively to increase the difference between similar network devices and further improve the recognition accuracy. Finally, we identify devices based on the deep learning model. A large number of experiments were carried out on 31 types of network devices such as web cameras, wireless routers, and smartwatches. The results show that the accuracy of the proposed recognition method based on the spatial attention mechanism is increased by 0.8% and 2.0%, respectively, compared with the recognition method based only on the deep learning model under the CNN and MLP models. The method proposed in this paper is significantly superior to the existing method of device-type recognition based only on a deep learning model.

Investigation of You Only Look Once Networks for Vision-based Small Object Detection

Small object detection is a challenging issue in computer vision-based algorithms. Although various methods have been investigated for common objects including person, car and others, small object are not addressed in this issue. Therefore, it is necessary to conduct more researches on them. This paper is focused on small object detection especially jewellery as current object detection methods suffer from low accuracy in this domain. This paper introduces a new dataset whose images were taken by a web camera from a jewellery store and data augmentation procedure. It comprises three classes, namely, ring, earrings, and pendant. In view of the small target of jewellery and the real-time detection, this study adopted the You Only Look Once (Yolo) algorithms. Different Yolo based model including eight versions are implemented and train them using our dataset to address most effective one. Evaluation criteria, including accuracy, F1 score, recall, and mAP, are used to evaluate the performance of the various YOLOv5, YOLOv6, and YOLOv7 versions. According to the experimental findings, utilizing YOLOv6 is significantly superior to YOLOv7 and marginally superior to YOLOv5.

Measurement of 6D face pose and iris location using web camera

Measurement of 6D face pose and iris location using web camera

放射線の可視化とその効果について

There are some ways to visualize radiations. In this paper, we use a neon hodoscope, a cloud chamber and a web camera. We take a questionnaire from students and analyze it to make vectors. To improve this method, we take an almost same but slightly different questionnaire from the other students. We evaluate the effect of the visualization of radiation on students.

An efficient novel paradigm for object detection through web camera using deep learning (YOLOv5’s object detection model)

Object detection, a fundamental duty in computer vision that has a wide range of practical applications, they are surveillance, robotics, and autonomous driving. Recent developments of deep learning have got gradual improvemenrts in detection accuracy and speed. One of the most popular and effective deep learning models for object detection is YOLOv5. In this discussion, we an object detection model through YOLOv5 and its implementation for object detection tasks. We discuss the model’s architecture, training process, and evaluation metrics. Furthermore, we present experimental results on popular object detection benchmarks to demonstrate the efficacy and efficiency of YOLOv5 in detecting various objects in complex scenes. Our experiments states that YOLOv5 out performs other state of the art object detection models case of accuracy of detected image and speed of detection, making it a promising approach for real-world applications. Our work contributes to the growing body of research on deep learning-based object detection and provides valuable insights into the capabilities and limitations of YOLOv5. By improving accuracy, speed of object detection models, we have enabled a wide range of applications that can benefit society in countless ways.

Portable immuno nano biosensor for multiple disease detection using 3D printed SPR technologies

The role of biosensors as point-of-care devices is well explored in recent years and their usage in the current market has been highly increased after the outbreak of the COVID pandemic. The point-of-care devices generally use sensing principles of electrochemical, immune fluorescence, microbial and electromagnetic. The sensor we developed uses the phenomenon of Surface Plasmon resonance with optic fiber technology which is a novel design to implement in point-of-care devices. With the latest innovations and improvements in 3D printing technologies the development and prototyping of these POC devices have been accelerated to the greatest potential. Here the entire device was prototyped using Creality Upgraded Ender 3 2021 model 3D printer where the 3D files were sliced in Ultimaker Cura software and printed with PLA filament by fused filament deposition modeling (FFDM). The device has a USB light and camera source on either side of the sensing chamber and a cassette with optic fiber coated with respective antibodies as a sensing platform. The device is connected to respective USB ports and introduced with the sample over a cassette and placed in the reaction chamber. The reaction occurs spontaneously which is captured by the webcam and recorded by the software. We tested the bare sensor with increased concentrations of glycerol after coating it with a silver mirror by a standard reproducible method of Tollens silver mirror. The sensor showed the best sensitivity with increasing concentrations of glycerol. The sensor also immobilized with target antibodies of pLDH parasite lactate dehydrogenase by non-specific binders just by adding target bio-analyte and receptor over silver mirror functionalized surface and tested with positive control antigen of malaria parasite antigen. The sensor showed the highest sensitivity at 50X concentration of antigen and least at 10x concentration stating maximum and minimum values for a limit of detection. This device using this principle could has wide functionalities to detect multiple biological samples by changing the antibodies to our respective analyte over the reaction chip for multiple times with low cost.

Txt2Vid: Ultra-Low Bitrate Compression of Talking-Head Videos via Text

Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure. In addition, the recent COVID-19 pandemic fueled a surge in the use of video conferencing tools. Since videos take up considerable bandwidth ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim 100$ </tex-math></inline-formula> Kbps to a few Mbps), improved video compression can have a substantial impact on network performance for live and pre-recorded content, providing broader access to multimedia content worldwide. We present a novel video compression pipeline, called Txt2Vid, which dramatically reduces data transmission rates by compressing webcam videos (“talking-head videos”) to a text transcript. The text is transmitted and decoded into a realistic reconstruction of the original video using recent advances in deep learning based voice cloning and lip syncing models. Our generative pipeline achieves two to three orders of magnitude reduction in the bitrate as compared to the standard audio-video codecs (encoders-decoders), while maintaining equivalent Quality-of-Experience based on a subjective evaluation by users ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n=242$ </tex-math></inline-formula> ) in an online study. The Txt2Vid framework opens up the potential for creating novel applications such as enabling audio-video communication during poor internet connectivity, or in remote terrains with limited bandwidth. The code for this work is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/tpulkit/txt2vid.git</uri> .

Music recommender system using facial feature recognition

Facial expressions convey a lot of information about the emotional state of a person and even a small change in it can help to detect changes in an individual's mood. Researchers have conducted numerous studies in the fields of machine learning and computer vision, training ML models to detect various human emotions or moods based on captured facial features. In this research, a system was proposed which is capable of identifying the user's emotions and moods and suggesting a list of appropriate songs to improve their mood. Incorporating mood detection offers significant benefits to customers' mental health and personal satisfaction. The objective of this system is to capture the user's image, detect their mood and create a music player system that recommends music based on the user's real-time mood, utilizing a web camera and deep learning algorithms.

Immediate Effect of an Intervention Using a Head-mounted Display with a Modified Pitch Angle on Spatial Awareness and Standing Balance in Stroke Hemiparesis.

This study aimed to clarify the effect of an intervention using a head-mounted display with a web camera set at a modified pitch angle on spatial awareness, sit-to-stand movement, and standing balance in patients with left and right hemisphere damage. The participants were 12 patients with right hemisphere damage and 12 patients with left hemisphere damage. The line bisection test, a sit-to-stand movement, and balance assessment were performed before and after the intervention. The intervention task involved pointing at targets 48 times in an upward bias condition. Significant upward deviation on the line bisection test was noted in patients with right hemisphere damage. The load on the forefoot during the sit-to-stand movement was significantly increased. The range of anterior-posterior sway during forward movement in the balance assessment was reduced. An adaptation task performed in an upward bias condition may produce an immediate effect on upward localization, sit-to-stand movement, and balance performance in patients with right hemisphere stroke.

Intelligent synthesis of hyperspectral images from arbitrary web cameras in latent sparse space reconstruction

&lt;abstract&gt;&lt;p&gt;Synthesizing hyperspectral images (HSI) from an ordinary camera has been accomplished recently. However, such computation models require detailed properties of the target camera, which can only be measured in a professional lab. This prerequisite prevents the synthesizing model from being installed on arbitrary cameras for end-users. This study offers a calibration-free method for transforming any camera into an HSI camera. Our solution requires no controllable light sources and spectrometers. Any consumer installing the program should produce high-quality HSI without the assistance of optical laboratories. Our approach facilitates a cycle-generative adversarial network (cycle-GAN) and sparse assimilation method to render the illumination-dependent spectral response function (SRF) of the underlying camera at the first part of the setup stage. The current illuminating function (CIF) must be identified for each image and decoupled from the underlying model. The HSI model is then integrated with the static SRF and dynamic CIF in the second part of the stage. The estimated SRFs and CIFs have been double-checked with the results by the standard laboratory method. The reconstructed HSIs have errors under 3% in the root mean square.&lt;/p&gt;&lt;/abstract&gt;

Development of a Saccade Measurement System Using a High-Speed Imaging Method with Multiple Web Cameras

Development of a Saccade Measurement System Using a High-Speed Imaging Method with Multiple Web Cameras

EnGauge: Engagement Gauge of Meeting Participants Estimated by Facial Expression and Deep Neural Network

Measuring the level of engagement among participants in a meeting is crucial for evaluating collective understanding. While previous studies have utilized multiple sensors, such as wearable devices, to gauge engagement levels in offline environments, the shift to remote meetings due to the COVID-19 pandemic presents new challenges. In this study, we propose a method for measuring student engagement during online meetings using only the built-in web cameras on their devices. We collect high, middle, and low engagement level recording data from 24 students. We decided to collect data using the role-acting approach instead of conventional self-reporting or post-experiment annotation. With the feature extraction based approach, we achieved a classification rate of 46.7%. With a deep learning based approach, we achieved a classification rate of 89.5% using MobileNetV2 for leave-one-participant-out cross-validation, which demonstrated higher accuracy than previous studies. From the model, we implement an application <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">EnGauge</i> and conduct a pilot study. The results demonstrate a new approach to data collection, an optimal engagement level recognition model, and application scenarios.

An End‐To‐End Flood Stage Prediction System Using Deep Neural Networks

AbstractThe use of automated methods for detecting and classifying different types of labels in flood images have important applications in hydrologic prediction. In this research, we propose a fully automated end‐to‐end image detection system to predict flood stage data using deep neural networks across two US Geological Survey (USGS) gauging stations, that is, the Columbus and the Sweetwater Creek, Georgia, USA. The images were driven from the USGS live river web cameras, which were strategically located nearby the monitoring stations and refreshed roughly every 30 s. To estimate the flood stage, a U‐Net Convolutional Neural Network (U‐Net CNN) was first stacked on top of a segmentation model for noise and feature reduction that diminished the number of images needed for training. A Long Short‐Term Memory (LSTM), a dense model, and a CNN were then trained to predict the flood stage time series data in near real‐time (6, 12, 24, and 48 hr). The results revealed that the U‐Net CNN has a higher accuracy for image segmentation if the algorithm is stacked in front of the network. The absolute error with the U‐Net was 0.0654 feet at the Columbus while it was 0.0035 feet at the Sweetwater Creek, which were practically low for flood stage estimation. For time series prediction, among three models, the LSTM predicted the flood stage values more accurately during both historical (2015–2022) as well as real‐time forecasts, particularly for 24 and 48 hr timescales. We extensively evaluated the proposed flood stage prediction system against current state‐of‐the‐art methodologies partly crowd‐sourced and mined in real‐time.

Supporting Live Production Using Precision Time Protocol Over 5G Systems With Dedicated Time Synchronization Support

The article explores the possibility of using IEEE 1588 Precision Time Protocol (PTP) over a 5G system for media production applications. The article describes lab sessions performed by the 5G RECORDS consortium members, testing the performance of PTP over 5G with and without the dedicated time synchronization support. A trial with a real camera supporting SMPTE ST 2110–22 with JPEG- XS was conducted to experiment with synchronization and packet pacing precision. The 5G system used in these experiments features additional functionalities from the 3rd Generation Partnership Program (3GPP) Release 16, including specific time synchronization support for time-sensitive networks (TSNs), that is, acting as a time-aware system, and Release 17 in which the support for IEEE 1588 is extended with several additional features. The article also describes the testing setup based on the open-source software used by the team and the methodology developed. The article concludes on the performance and synchronization quality when using PTP over various 5G systems and analyzes the results from the lab trials. This new approach with the experimental setup allows using PTP according to the SMPTE ST 2059–2 PTP profile reliably over 5G for media device synchronization, which is not usually done in the context of the 5G networks.

태블릿 PC를 통해 구현된 증강현실 영상 속 이동하는 시표와 카메라를 통해 실시간 시표가 이동하는 영상 관찰시 나타나는 눈의 조절력 변화에 관한 연구

태블릿 PC를 통해 구현된 증강현실 영상 속 이동하는 시표와 카메라를 통해 실시간 시표가 이동하는 영상 관찰시 나타나는 눈의 조절력 변화에 관한 연구

Bare PCB (Printed Circuit Board) Fault Detection in Real-time Using YOLOv5

With the continuous development of object detection technology, the YOLO series of algorithms with high precision and speed has been used in various fault detection tasks. This paper aims to establish a real-time quality control framework for PCB fault detection that can be adopted by industries. The development of more automized testing method by using YOLOv5. Detection of imperfections despite misalignment and incorrect orientation is required in the industry. Decreases quality check time and human examiner cost for quality control and auditing the product (as it might be slow and error-prone). Computer Camera is used of real-time fault detection in this prototype, however any digital camera integration would be possible and might improve the performance. Ultimately, increased revenue generation followed by better quality production and supply that meets the market demand.

Product Assembly Assistance System Based on Pick-To-Light and Computer Vision Technology

Product assembly is often one of the last steps in the production process. Product assembly is often carried out by workers (assemblers) rather than robots, as it is generally challenging to adapt automation to any product. When assembling complex products, it can take a long time before the assembler masters all the steps and can assemble the product independently. Training time has no added value; therefore, it should be reduced as much as possible. This paper presents a custom-developed system that enables the guided assembly of complex and diverse products using modern technologies. The system is based on pick-to-light (PTL) modules, used primarily in logistics as an additional aid in the order picking process, and Computer Vision technology. The designed system includes a personal computer (PC), several custom-developed PTL modules and a USB camera. The PC with a touchscreen visualizes the assembly process and allows the assembler to interact with the system. The developed PC application guides the operator through the assembly process by showing all the necessary assembly steps and parts. Two-step verification is used to ensure that the correct part is picked out of the bin, first by checking that the correct pushbutton on the PTL module has been pressed and second by using a camera with a Computer Vision algorithm. The paper is supported by a use case demonstrating that the proposed system reduces the assembly time of the used product. The presented solution is scalable and flexible as it can be easily adapted to show the assembly steps of another product.