Video Camera Research Articles

The Detection System for a Danger State of a Collision between Construction Equipment and Workers Using Fixed CCTV on Construction Sites.

According to data from the Ministry of Employment and Labor in Korea, a significant portion of fatal accidents on construction sites occur due to collisions between construction workers and equipment, with many of these collisions being attributed to worker negligence. This study introduces a method for accurately localizing construction equipment and workers on-site, delineating areas prone to collisions as 'a danger area of a collision', and defining collision risk states. Utilizing advanced deep learning models which specialize in object detection, video footage obtained from strategically placed closed-circuit television (CCTV) cameras across the construction site is analyzed. The positions of each detected object are determined using transformation or homography matrices representing the conversion relationship between a sufficiently flat reference plane and image coordinates. Additionally, 'a danger area of a collision' is proposed for evaluating equipment collision risk based on the moving equipment's speed, and the validity of this area is verified. Through this, the paper presents a system designed to preemptively identify potential collision risks, particularly when workers are located within the 'danger area of a collision', thereby mitigating accident risks on construction sites.

A Choice-Based Design Approach to Influence Beneficial Use of a Green Space by Family Caregivers at a Tertiary Care Hospital in India.

Principles of behavioral economics are now being used across fields in changing human behavior toward perceived benefit. We studied the effectiveness of simple, cost-effective design cues based on these principles, in encouraging use of a neglected outdoor space in a hospital. Benefits of access to nature and green spaces are established in healthcare; however, we found utilization of an outdoor space to be suboptimal. Presenting choices in different ways is known to influence user choice. We designed four design interventions based to nudge relative-caregivers waiting outside the operation theater toward utilizing an adjoining outdoor balcony. These included making the terrace prominent, reducing indoor sensory stimulation, adding stereotypical elements, and improving usability. We measured usage via video camera data and satisfaction using questionnaires. The number of users and average time per person spent on the balcony increased over the consecutive intervention periods as compared to baseline (trend p < .01 for both), mainly driven by the addition of stereotypical elements. There were no adverse events in the balcony. There was no difference in the satisfaction related outcomes on questionnaire; a larger percentage of positive comments tended to be related to the balcony in the final intervention. Cost-effective design cues nudged patient-caregivers toward spending more time with nature, thus changing behavior toward that with perceived benefits.

Propulsive fractions of joint work during maximal sprint running

PurposeThe purpose of the study was to determine which of the ankle, knee or hip joint is the most important contributor to horizontal velocity during maximal sprint running. Furthermore, it was undertaken to quantify the fraction of propulsive power and work produced at each of the three joints.MethodsSeven athletes of national class served as subjects for the study. One running cycle of each subject was recorded by four video cameras (240 f/s) and a recessed force platform. Inverse dynamics in 3D was calculated as well as an angle between joint moment and angular velocity to express propulsive power and propulsive joint work.ResultsPrevious studies indicating the hip joint being the most important joint could not be confirmed by the present results due to large inter-individual differences for the hip joint. Averaged across all subjects, 64% of the normalized positive ankle joint work and 71% of the knee joint work were propulsive, while for the hip joint, four athletes showed 0%, one athlete 8%, and two athletes 96% and 97% propulsive work, respectively. For the whole leg, the propulsive fraction was 70% of the total positive work (range 40–87%). Normalized propulsive work was significantly correlated with maximal running velocity.ConclusionThe whole leg should be considered as one functional unit in which one or more of the joints may dominate generation of propulsive joint work.

Indentation and Detachment in Adhesive Contacts between Soft Elastomer and Rigid Indenter at Simultaneous Motion in Normal and Tangential Direction: Experiments and Simulations.

In reported experiments, a steel indenter was pressed into a soft elastomer layer under varying inclination angles and subsequently was detached under various inclination angles too. The processes of indentation and detachment were recorded with a video camera, and the time dependences of the normal and tangential components of the contact force and the contact area, as well as the average contact pressure and average tangential stresses, were measured as functions of the inclination angle. Based on experimental results, a simple theoretical model of the indentation process is proposed, in which tangential and normal contacts are considered independently. Both experimental and theoretical results show that at small indentation angles (when the direction of motion is close to tangential), a mode with elastomer slippage relative to the indenter is observed, which leads to complex dynamic processes-the rearrangement of the contact boundary and the propagation of elastic waves (similar to Schallamach waves). If the angle is close to the normal angle, there is no slipping in the contact plane during the entire indentation (detachment) phase.

BeeLive: The IoT platform of Beemon monitoring and alerting system for beehives

Monitoring honey beehives is mainly done manually by beekeepers to evaluate the health of their hives and determine their growth and yield. With the emergence of Internet of Things (IoT) devices and tools, there have been some efforts in recent years to automate such monitoring. This can significantly benefit beekeepers as they can obtain critical data and insight into their hives' health and performance more regularly. In this paper, we use IoT devices and the Thingsboard dashboard to track the status of 28 honey beehives installed in the Western region of North Carolina as part of the Appalachian Multi-Apiary Informatics System (AppMAIS) project. In order to acquire data from a beehive, humidity and temperature sensors, as well as a microphone, have been placed inside the hives. In addition, a video camera has been placed at the top of the hive's entrance to obtain video recordings of the bees entering and leaving the hives, and a scale is placed under the hive to report the weight. The data collected from the sensors and peripherals installed in each of the AppMAIS hives are sent to the Thingsboard dashboard for management and visualization. In this paper, we report on our success with Thingsboard IoT tool to monitor honey beehives and take advantage of their capabilities to interact with the devices as needed to adjust operational parameters.

A Temporal Learning Approach to Inpainting Endoscopic Specularities and Its Effect on Image Correspondence

Video streams are utilised to guide minimally-invasive surgery and diagnosis in a wide range of procedures, and many computer-assisted techniques have been developed to automatically analyse them. These approaches can provide additional information to the surgeon such as lesion detection, instrument navigation, or anatomy 3D shape modelling. However, the necessary image features to recognise these patterns are not always reliably detected due to the presence of irregular light patterns such as specular highlight reflections. In this paper, we aim at removing specular highlights from endoscopic videos using machine learning. We propose using a temporal generative adversarial network (GAN) to inpaint the hidden anatomy under specularities, inferring its appearance spatially and from neighbouring frames, where they are not present in the same location. This is achieved using in-vivo data from gastric endoscopy (Hyper Kvasir) in a fully unsupervised manner that relies on the automatic detection of specular highlights. System evaluations show significant improvements to other methods through direct comparison and ablation studies that depict the importance of the network’s temporal and transfer learning components. The generalisability of our system to different surgical setups and procedures was also evaluated qualitatively on in-vivo data of gastric endoscopy and ex-vivo porcine data (SERV-CT, SCARED). We also assess the effect of our method in comparison to other methods on computer vision tasks that underpin 3D reconstruction and camera motion estimation, namely stereo disparity, optical flow, and sparse point feature matching. These are evaluated quantitatively and qualitatively and results show a positive effect of our specular inpainting method on these tasks in a novel comprehensive analysis. Our code and dataset are made available at https://github.com/endomapper/Endo-STTN.

Detecting Volcano Thermal Activity in Night Images Using Machine Learning and Computer Vision

One of the most important tasks when studying volcanic activity is to monitor their thermal radiation. To fix and assess the evolution of thermal anomalies in areas of volcanoes, specialized hardware-thermal imagers are usually used, as well as specialized instruments of modern satellite systems. The data obtained with their help contain information that makes it relatively easy to track changes in temperature and the size of a thermal anomaly. At the same time, due to the high cost of such complexes and other limitations, thermal imagers sometimes cannot be used to solve scientific problems related to the study of volcanoes. In the current paper, day/night video cameras with an infrared-cut filter are considered as an alternative to specialized tools for monitoring volcanoes’ thermal activity. In the daytime, a camera operated in the visible range, and at night the filter was removed, increasing the camera’s light sensitivity by allowing near-infrared light to hit the sensor. In that mode, a visible thermal anomaly could be registered on images, as well as other bright glows, flares, and other artifacts. The purpose of this study is to detect thermal anomalies on night images, separate them from other bright areas, and find their characteristics, which could be used for volcano activity monitoring. Using the image archive of the Sheveluch volcano as an example, this article presents the results of developing a computer algorithm that makes it possible to find and classify thermal anomalies on video frames with an accuracy of 98%. The test results are presented, along with their validation based on thermal activity data obtained from satellite systems.

Finding and Tracking Automobiles on Roads for Self-Driving Car Systems

Road-object detection, recognition, and tracking are vital tasks that must be performed reliably and accurately by self-driving car systems in order to achieve the automation/autonomy goal. Other vehicles are one of the main objects that the egocar must accurately detect and track on the road. However, deep-learning approaches proved their effectiveness at the expense of very demanding computational power and low throughput. They must be deployed on expensive CPUs and GPUs. Thus, in this work, a lightweight vehicle detection and tracking technique (LWVDT) is suggested to fit low-cost CPUs without sacrificing robustness, speed, or comprehension. The LWVDT is suitable for deployment in both advanced driving assistance systems (ADAS) functions and autonomous-car subsystems. The implementation is a sequence of computer-vision techniques fused together and merged with machine-learning procedures to strengthen each other and streamline execution. The algorithm details and their execution are revealed in detail. The LWVDT processes raw RGB camera pictures to generate vehicle boundary boxes and tracks them from frame to frame. The performance of the proposed pipeline is assessed using real road camera images and video recordings under different circumstances and lighting/shading conditions. Moreover, it is also tested against the well-known KITTI database, achieving an average accuracy of 87%.

Conjuring Up a King

Conjuring Up a King

Fast Rolling Shutter Correction in the Wild.

This paper addresses the problem of rolling shutter correction (RSC) in uncalibrated videos. Existing works remove rolling shutter (RS) distortion by explicitly computing the camera motion and depth as intermediate products, followed by motion compensation. In contrast, we first show that each distorted pixel can be implicitly rectified back to the corresponding global shutter (GS) projection by rescaling its optical flow. Such a point-wise RSC is feasible with both perspective and non-perspective cases without the pre-knowledge of the camera used. Besides, it allows a pixel-wise varying direct RS correction (DRSC) framework that handles locally varying distortion caused by various sources, such as camera motion, moving objects, and even highly varying depth scenes. More importantly, our approach is an efficient CPU-based solution that enables undistorting RS videos in real-time (40fps for 480p). We evaluate our approach across a broad range of cameras and video sequences, including fast motion, dynamic scenes, and non-perspective lenses, demonstrating the superiority of our proposed approach over state-of-the-art methods in both effectiveness and efficiency. We also evaluated the ability of the RSC results to serve for downstream 3D analysis, such as visual odometry and structure-from-motion, which verifies preference for the output of our algorithm over other existing RSC methods.

Reliability and Concurrent Validity of a Markerless, Single Camera, Portable 3D Motion Capture System for Assessment of Glenohumeral Mobility.

Recent technological advancements have enabled medical, sport, and fitness professionals to utilize digital tools that assist with conducting movement examinations and screenings. One such advancement has been the implementation of a single camera, markerless, and portable 3D motion capture system designed to obtain ROM measurements for multiple body parts simultaneously. However, the reliability and validity of a markerless 3D motion capture system that uses a single camera has not been established. The purpose of this study was to investigate the reliability and concurrent validity of this 3D motion capture system compared to a goniometer in assessing ROM of the glenohumeral joint. Quasi-experimental reliability, convenience sampling. Forty healthy volunteers (mean ± SD, age 27.4 ± 12.4 years, height 173.4 ± 11.1 cm, weight 72.1 ± 16.2 kg) participated in this study. Intrarater reliability was analyzed by ICC(2,k) with a 95% CI using two repeated trials for each shoulder movement (flexion, abduction, external rotation, internal rotation) that were recorded simultaneously via two methods: a standard goniometer and a 3D motion capture system. Concurrent validity was analyzed using Pearson Correlation Coefficient (r). The intrarater reliability between the two instruments for glenohumeral motions yielded an overall ICC of 0.82 (95% CI: 0.74-0.88) indicating good reliability for both instruments.The 3D motion capture system demonstrated strong correlations with goniometry for shoulder flexion (r = 0.67), abduction (r = 0.63), and external rotation (r = 0.76), and very strong correlation for shoulder internal rotation (r = 0.84). Results from this study indicated that a markerless, single camera, portable 3D motion capture system can be a reliable and valid tool to assess glenohumeral joint ROM in comparison to a standard goniometer. 3.

High-speed observation of bubble and droplet dynamics under irradiation of 1-MHz ultrasound

Simulation techniques have resulted in significant progress in elucidating phenomena that are too fast and small for direct observation; however, there has also been considerable progress in the legacy techniques of direct observation. We have been studying applications of microbubbles for ultrasonically enhanced drug delivery, and in this presentation, we will introduce our results of high-speed observations carried out to elucidate the roles of microbubbles injected into the capillaries of living tissues. Micron-sized bubbles stabilized by a lipid shell were introduced into a limen of 10 microns in diameter created in acrylamide gel, and their dynamics under the conditions of exposure to 1-MHz short-pulsed ultrasound was observed using a high-speed video camera (HPV-X2, Shimadzu, Japan) equipped in a microscope (ECLIPSE Ti, Nikon, Japan) with an objective lens (Plan APO IR 40x, Nikon, Japan). The camera captured 256 frames at a framing rate up to 10 Mfps to visualize bubble dynamics inside a narrow capillary that will lead to ultrasound-enhanced extravasation. Oscillation of a water droplet of a few millimeters in size in air, which is the opposite situation of bubble oscillation in water, will also be discussed in this presentation.

Measurement of live shrimp carapace length and its swimming speed in the cage culture using Multiple Object Tracking

The carapace length of live shrimp is one of the important parameters to monitor the growth of the shrimp from time to time in cage culture, while its swimming speed is one of the key indicators to understanding the behavior and health of the shrimp. To estimate live shrimp carapace length and its swimming speed, we recorded a live shrimp in the cage culture using an underwater video camera. The collected datasets then being preprocessed and labeled. Before measuring the carapace length of the shrimp, we used the You Only Look Once (YOLO) v5 algorithm with K-fold cross-validation to detect shrimp heads. The accuracy value obtained is 85.6%, recall 85.4%, precision 77.3%, and F1-score 81.1%. Then the multiple object tracking (MOT) DeepSORT method was used to measure the shrimp’s carapace length and its swimming speed. The measurement results showed that the average length of the shrimp was 13.5-14.8 pixels, and the average speed of the shrimp was 62-78 pixels/second. We obtained that there is a strong linear relationship between carapace length and swimming speed of shrimp, namely SS = 11.864 CL + 43.419, where CL and SS are carapace length and swimming speed, respectively, with R-square = 0.9095. In conclusion, the live shrimp carapace length and its swimming speed can be measured using YOLO v5 and MOT DeepSORT directly and accurately.

Mid-frequency acoustic localization of breaking waves.

During an experiment in deep water off the coast of Southern California, wind speeds ranged from 10 to 15 m/s and wind forcing produced large breaking waves. A mid-frequency vertical planar hydrophone array recorded underwater ambient noise while an airplane equipped with a high-resolution video camera captured images of the sea surface above the array. Beams of ambient noise between 5 and 6 kHz were projected onto the sea surface and synchronized in space and time with the aerial images. Despite the array's limited azimuthal resolution of the surface, due to its modest 1 m horizontal aperture and relatively deep 130 m deployment depth, concentrated areas of high intensity in the acoustic surface projection were observed to match visible breaking events in the aerial images.

Biodiversity and big data to investigate the link between biosonar sensing and flight control in bats

Any animal with dexterous mobility in complex natural environments needs powerful systems for sensing and mobility that also have to be well-integrated with each other. Echolocating bats that hunt in dense vegetation rely on biosonar integrated with flapping flight to accomplish this. The low-dimensional nature of the biosonar inputs together with the complexity of the bats' flight apparatus make this coupling a fundamental scientific challenge. To understand how bats can control the many degrees of freedom of their wings based on external information that is conveyed by only two one-dimensional echo trains, a flight tunnel has been instrumented with synchronized high-speed video cameras and ultrasonic microphones. The array recordings can provide data volumes that are large enough to enable deep-learning analyses of the biosonar echoes and the flight kinematics. These analyses will be applied to reducing the dimensionality of ultrasonic inputs, the kinematic outputs, and discovering the relationship between the essential dimensions of biosonar and flight. The tunnel has been installed on the island of Borneo to take advantage of the local bat biodiversity as a source of variability that can be exploited in a comparative approach to identify functional traits that are essential to sensorimotor integration in echolocating bats.

Transitioning concert hall soundscapes to vehicle interiors based on psychoacoustic evaluations

In this study, in line with the paradigm shift in the design of interior spaces for future autonomous vehicles, the vehicle interior spaces were categorized according to their suitability for music appreciation and a design for an optimal soundscape design to that of a concert hall was proposed. Based on the sound field investigation conducted with 360-deg camera video and binaural audio recorded inside the vehicle, audibilized computer models were created in a virtual reality environment for comparison with conventional rectangular halls. These models' auralization audio files were subject to a psychoacoustic evaluation experiment of the soundscape. Evaluation indicators were selected based on the collected data, and through a comparative analysis of these indicators, parameters for transitioning the soundscape of a concert hall into a vehicle interior were proposed.

Mechanical properties of atherosclerotic plaques, caps and walls of arterial vessels: a mobile test bench experiments

Within the framework of this study, a methodology and a prototype of a test bench for conducting experiments on compression of biological tissue samples have been developed. The test bench for the implementation of the technique consists of high–precision scales (measuring accuracy up to 0.01 g, maximum weight - 5 kg), an electronic caliper (measuring accuracy up to 0.01 mm) with 3D-printer pads that are attached to grips, as well as video cameras. Thanks to such a mobile stand, it was possible to conduct a series of experiments (a total of 99 tests) to determine the Young's modulus of atherosclerotic plaques and areas of vascular walls removed from the body no later than a few hours. This made it possible to collect a database of the mechanical characteristics of the plaques as close as possible to the real properties. In addition, regression dependences were constructed between the Hounsfield numbers corresponding to dense atherosclerotic deposits discernible on a CT scan and the Young modules obtained during experiments. Such dependencies will further allow determining the mechanical properties of plaques in vivo based on computed tomography data. The technique was verified by mechanical experiments on the universal testing machine Instron 3342 and on a mobile test bench on samples of hard (with pronounced calcification) and soft plaques. 7 experiments were conducted for each type of samples. The results differed by no more than 4.3 % for soft plaques and no more than 9.5 % for hard plaques. To test the inter-expert reliability of the methodology, a number of experiments were conducted with the involvement of two independent participants. Each of the three mobile stand operators performed 5 tests on soft rubber samples. The study of inter-expert reliability allowed us to show the independence of the methodology from the skills and qualifications of the operator.

Discrepancy between subjective and objective health indicators when performing monotonous operator activities against the background of chronic sleep deprivation

The aim of the study was to investigate various psychophysiological predictors of the quality of monotonous activity performance against the background of sleep deprivation. Fourteen subjects aged 18–22 years took part in the experiments. Each subject participated in four experimental sessions with partially automated control scenarios in a computerized driving simulator: the first experiment (15 minutes) – training session in the simulator without sleep deprivation; the second experiment – sleep deprivation (90 minutes); the third experiment – sleep deprivation and periodic exposure to a massage seat cover (90 minutes); the fourth experiment – sleep deprivation and periodic spraying of peppermint oil from an aroma diffuser (90 minutes). Every 3–7 minutes, subjects were asked to respond to two types of stimuli: 1) gradually changing; 2) appearing unexpectedly and requiring maneuvering. Stimulus intervals and stimulus order were varied randomly. Car driving simulator data, electroencephalogram using the standard 10–20 system with a sampling rate of 1000 Hz, electrocardiogram and skin-galvanic response were recorded. A three-dimensional video camera was mounted on a monitor in front of the subject to track head position and changes of the subject's facial expressions throughout the experiment. Subjects completed questionnaires on sleepiness and general well-being, and reaction time was also tested before the experiment. According to the results of the questionnaires and test performance, the subjects were in a state of chronic sleep deprivation and chronic stress. No statistically significant differences between the experiments after partial sleep deprivation without additional stimulation, with the use of a massage seat cover and periodic spraying of peppermint oil every 10 minutes were seen. The eye closure rate (PERCLOS) and spectral index of heart rate variability showed a significant statistically reliable increase before errors. The values of physiological indices before errors indicate different causes of errors in experiments without and with exposure to peppermint oil or massage seat cover.

Results from an effectiveness evaluation of anti-bias training on police behavior and public perceptions of discrimination

PurposeThe authors evaluated the impact of an anti-bias training intervention for improving police behavior during interactions with community members and public perceptions of discrimination.Design/methodology/approachFifty patrol officers from a diverse municipal agency were randomly selected to participate in an anti-bias intervention. Before and after the intervention, a random selection of Body Worn Camera (BWC) videos from the intervention group as well as from a control group of officers was coded using a validated tool for coding police “performance” during interactions with the public. Discrimination-based community member complaints were also collected before and after the intervention for treatment and control group officers.FindingsThe treatment group had a small but significant increase in performance scores compared to control group officers, F = 4.736, p = 0.009, R2ß < 0.01. They also had a small but significantly reduced number of discrimination-based complaints compared to control group officers, F = 3.042, p = 0.049, p2 = 0.015. These results suggest that anti-bias training could have an impact on officer behaviors during interactions with public and perceptions of discrimination.Originality/valueAlthough these results are from a single municipal police department, this is the first study to suggest that anti-bias trainings may have a positive behavioral impact on police officers as well as the first to illustrate the potential for their impact on community members' perceptions of biased treatment by officers.

SPSVO: a self-supervised surgical perception stereo visual odometer for endoscopy

AbstractAccurate tracking and reconstruction of surgical scenes is a critical enabling technology toward autonomous robotic surgery. In endoscopic examinations, computer vision has provided assistance in many aspects, such as aiding in diagnosis or scene reconstruction. Estimation of camera motion and scene reconstruction from intra-abdominal images are challenging due to irregular illumination and weak texture of endoscopic images. Current surgical 3D perception algorithms for camera and object pose estimation rely on geometric information (e.g., points, lines, and surfaces) obtained from optical images. Unfortunately, standard hand-crafted local features for pose estimation usually do not perform well in laparoscopic environments. In this paper, a novel self-supervised Surgical Perception Stereo Visual Odometer (SPSVO) framework is proposed to accurately estimate endoscopic pose and better assist surgeons in locating and diagnosing lesions. The proposed SPSVO system combines a self-learning feature extraction method and a self-supervised matching procedure to overcome the adverse effects of irregular illumination in endoscopic images. The framework of the proposed SPSVO includes image pre-processing, feature extraction, stereo matching, feature tracking, keyframe selection, and pose graph optimization. The SPSVO can simultaneously associate the appearance of extracted feature points and textural information for fast and accurate feature tracking. A nonlinear pose graph optimization method is adopted to facilitate the backend process. The effectiveness of the proposed SPSVO framework is demonstrated on a public endoscopic dataset, with the obtained root mean square error of trajectory tracking reaching 0.278 to 0.690 mm. The computation speed of the proposed SPSVO system can reach 71ms per frame.