Single Camera Approach Research Articles

Vision‐based monitoring system for in‐plan seismic tests conducted on a shaking table: The case study of prefabricated concrete shells

AbstractComputer vision enables a much more efficient monitoring system of structural behavior, compared to traditional methods. This derives from the fact that it allows the assessment of displacements in a vast number of points that can be processed to the estimate deformations, accelerations, and other key parameters at relevant cross‐sections. This paper proposes a computer vision‐based methodology, specifically designed for monitoring seismic tests conducted on a shaking table with a reduced‐scale model, using a single camera approach. This innovative methodology uses artificial targets with predefined color and geometry to optimize their detection and tracking. These targets are positioned at key points of the reduced model—“Moving Targets”—and at reference points of the seismic table—“Control Targets.” Videos are recorded during the seismic tests and the coordinates (in pixels) of the targets' centers are automatically detected and captured. Then, transformations are applied to each frame to compute the targets coordinates in millimeters and based on the differences between frames, to calculate the displacements of each target. The methodology was first calibrated with dynamic tests performed on a reduced‐scale model (1:33) of a prefabricated concrete shell, printed in acrylonitrile butadiene styrene (ABS), conducted on an educational shaking table. Afterwards, the methodology was validated with seismic tests performed on a 1:3 reduced model of a prefabricated concrete shell, produced according to the similitude theory to best reproduce the behavior of the corresponding prototype. It was demonstrated the ability of the methodology to monitoring seismic tests, enabling continuous tracking of the targets placed on a structure with complex geometry.

Phone cam array – An open-source, modular photogrammetry system made of Android phones

Photogrammetry is a 3D reconstruction technique using photographs of the target from multiple angles. Taking pictures around a static object with a single camera can yield high-quality models, but if the subject moves between images, 3D reconstruction might fail. One way to mitigate this is to use multiple cameras.This project aimed to develop a tool for fast and precise wound documentation for clinical forensic medicine.This paper describes a simple, low-cost modular system, where smartphones of different manufacturers are used as networked cameras. Exposure is initiated at the same time in all the phones with a simple circuit emulating a headset button press.A proof-of-concept device was built, where four phones (Huawei nova 8i (2 pcs), Samsung Galaxy S7 Edge, Oukitel K4000 Pro) were attached to a curved, 3D-printed, handheld frame.The average delay of image capture was 636 ms between the quickest and the slowest phones. When compared to the single-camera approach, the use of different cameras did not reduce the quality of the 3D model. The phone cam array was less susceptible to movement artefacts caused by breathing. Wound assessment was possible based on the 3D models created with this device.

Progress Towards Full-Scale (In Situ) Flow Measurements

Recent advances in tracer, illumination, and camera technology, paired with new processing algorithms, have been pushing the limit of scale for three-dimensional flow measurements. The present study reflects on the state-of-the-art and discusses the required steps to enable full-scale, in situ flow measurements in very large measurement volumes. In particular, we focus on industrial and environmental applications, where the measurement time, the processing time, and the costs all have to be minimized. A single-camera approach that enables measurements with natural illumination in very large volumes is presented. The required infrastructure is discussed along with experiments to quantify the experimental errors of the proposed single-camera approach.

On the determination of 3D position and orientation of spheroidal particles using defocusing and deep learning

Tracking the 3D position of tracer particles or small objects like cells or unicellular organisms in miniaturized lab-on-a-chip or biomedical devices is complicated since it is often not possible in these setups to use multi-camera approaches. Most successful single-camera approaches for these applications are based on holography or defocusing. Holographic methods have been used to track complex objects such has bacteria (Bianchi et al. (2019)) and even to estimate their orientation (Wang et al. (2016)). However, these methods require a complex and expensive experimental setup which is not always available in research laboratories. On the other hand, defocusing methods work with conventional microscopic optics, are easy to implement, and have shown excellent results in 3D PTV experiments (Qiu et al. (2019)). One main drawback is that they normally work only with spherical and mono-dispersed tracer particles. A defocusing method that has potential to measure non-spherical particles is the General Defocusing Particle Tracking (Barnkob and Rossi (2020)) which is based on pattern recognition and can be conceptually extended to more complex tasks by extending the reference library of particle images, including not only spherical particles at different depth positions, but also non-spherical particles at different orientations. However, whether this approach could work in practice is still unknown. First, is the information contained in simple defocused images sufficient to reconstruct depth and orientation of non-spherical particles, and eventually under which circumstances? Second, how to practically collect the labelled reference images?

Robust approach to monitoring Lagrangian transport in very large volume

State-of-the-art flow measurements utilize four or more high-speed cameras to perform highly-accurate Lagrangian particle tracking (LPT) in small to medium-sized measurement volumes (Schanz et al., 2016). Hou et al. (2021) suggested a novel approach to allow measurements in significantly larger measurement volumes (O(10m3 )) while reducing the experimental effort. A single camera is used to track centimeter-sized soap bubbles in three dimensions by not only evaluating the bubble-center location but also the bubbleimage size. Possible applications of the suggested approach include - but are not limited to - measurements in industrial wind tunnels (Hou et al., 2021), full-scale measurements in the atmospheric boundary layer (Rosi et al., 2014; Toloui et al., 2014), and the characterization of airflow in indoor spaces, such as offices or classrooms (Kahler et al., 2020). In the context of the recent pandemic, the latter application could ¨help to reduce infection risk by designing appropriate air circulation. Hereby, frequent air exchange is recommended, while direct airflow from individual to individual should be avoided (WHO, 2020). The present study strives to optimize and simplify the experimental set-up as well as to characterize the accuracy of the novel single-camera approach. Figure 1(a) shows the set-up used to characterize the novel approach.

A novel single-camera approach to large-scale, three-dimensional particle tracking based on glare-point spacing

A novel method for three-dimensional particle tracking velocimetry (PTV) is proposed that enables flow measurements in large volumes [ $$V=\mathcal {O}(10$$ m $${^3}$$ )] using a single camera. Flow is seeded with centimeter-sized soap bubbles, when combined with suitable illumination, produce multiple glare points. The spacing between the two brightest glare points for each bubble is then utilized to reconstruct its depth. While the use of large soap bubbles comes at the expense of non-Stokesian behaviour, the excellent ray optics allow for large volume illumination when coupled with for instance pulsed LED banks. Possible error sources and the out-of-plane accuracy are discussed before the feasibility of the method is tested in an industrial-scale wind tunnel facility (test section of cross section 9.1 m $$\times$$ 9.1 m). In particular, the vortical structure in the wake of a 30%-scale tractor-trailer model at a $$9^{\circ }$$ yaw angle is captured in a 4.0 m $$\times$$ 1.5 m $$\times$$ 1.5 m measurement volume. Long tracks of up to 80 time steps are extracted in three-dimensional space via a single perspective. The successful proof-of-concept confirms the potential of the novel approach for three-dimensional measurements in volumes of industrial scale.

Underwater 3D Rigid Object Tracking and 6-DOF Estimation: A Case Study of Giant Steel Pipe Scale Model Underwater Installation

The Zengwen desilting tunnel project installed an Elephant Trunk Steel Pipe (ETSP) at the bottom of the reservoir that is designed to connect the new bypass tunnel and reach downward to the sediment surface. Since ETSP is huge and its underwater installation is an unprecedented construction method, there are several uncertainties in its dynamic motion changes during installation. To assure construction safety, a 1:20 ETSP scale model was built to simulate the underwater installation procedure, and its six-degrees-of-freedom (6-DOF) motion parameters were monitored by offline underwater 3D rigid object tracking and photogrammetry. Three cameras were used to form a multicamera system, and several auxiliary devices—such as waterproof housing, tripods, and a waterproof LED—were adopted to protect the cameras and to obtain clear images in the underwater environment. However, since it is difficult for the divers to position the camera and ensure the camera field of view overlap, each camera can only observe the head, middle, and tail parts of ETSP, respectively, leading to a small overlap area among all images. Therefore, it is not possible to perform a traditional method via multiple images forward intersection, where the camera’s positions and orientations have to be calibrated and fixed in advance. Instead, by tracking the 3D coordinates of ETSP and obtaining the camera orientation information via space resection, we propose a multicamera coordinate transformation and adopted a single-camera relative orientation transformation to calculate the 6-DOF motion parameters. The offline procedure is to first acquire the 3D coordinates of ETSP by taking multiposition images with a precalibrated camera in the air and then use the 3D coordinates as control points to perform the space resection of the calibrated underwater cameras. Finally, we calculated the 6-DOF of ETSP by using the camera orientation information through both multi- and single-camera approaches. In this study, we show the results of camera calibration in the air and underwater environment, present the 6-DOF motion parameters of ETSP underwater installation and the reconstructed 4D animation, and compare the differences between the multi- and single-camera approaches.

Contactless Monitoring of Breathing Patterns and Respiratory Rate at the Pit of the Neck: A Single Camera Approach

Vital signs monitoring is pivotal not only in clinical settings but also in home environments. Remote monitoring devices, systems, and services are emerging as tracking vital signs must be performed on a daily basis. Different types of sensors can be used to monitor breathing patterns and respiratory rate. However, the latter remains the least measured vital sign in several scenarios due to the intrusiveness of most adopted sensors. In this paper, we propose an inexpensive, off-the-shelf, and contactless measuring system for respiration signals taking as region of interest the pit of the neck. The system analyses video recorded by a single RGB camera and extracts the respiratory pattern from intensity variations of reflected light at the level of the collar bones and above the sternum. Breath-by-breath respiratory rate is then estimated from the processed breathing pattern. In addition, the effect of image resolution on monitoring breathing patterns and respiratory rate has been investigated. The proposed system was tested on twelve healthy volunteers (males and females) during quiet breathing at different sensor resolution (i.e., HD 720, PAL, WVGA, VGA, SVGA, and NTSC). Signals collected with the proposed system have been compared against a reference signal in both the frequency domain and time domain. By using the HD 720 resolution, frequency domain analysis showed perfect agreement between average breathing frequency values gathered by the proposed measuring system and reference instrument. An average mean absolute error (MAE) of 0.55 breaths/min was assessed in breath-by-breath monitoring in the time domain, while Bland-Altman showed a bias of −0.03 ± 1.78 breaths/min. Even in the case of lower camera resolution setting (i.e., NTSC), the system demonstrated good performances (MAE of 1.53 breaths/min, bias of −0.06 ± 2.08 breaths/min) for contactless monitoring of both breathing pattern and breath-by-breath respiratory rate over time.

Optimizing Detection Rate and Characterization of Subtle Paroxysmal Neonatal Abnormal Facial Movements with Multi-Camera Video-Electroencephalogram Recordings.

Objectives We retrospectively analyze the diagnostic accuracy for paroxysmal abnormal facial movements, comparing one camera versus multi-camera approach. Background Polygraphic video-electroencephalogram (vEEG) recording is the current gold standard for brain monitoring in high-risk newborns, especially when neonatal seizures are suspected. One camera synchronized with the EEG is commonly used. Methods Since mid-June 2012, we have started using multiple cameras, one of which point toward newborns' faces. We evaluated vEEGs recorded in newborns in the study period between mid-June 2012 and the end of September 2014 and compared, for each recording, the diagnostic accuracies obtained with one-camera and multi-camera approaches. Results We recorded 147 vEEGs from 87 newborns and found 73 episodes of paroxysmal facial abnormal movements in 18 vEEGs of 11 newborns with the multi-camera approach. By using the single-camera approach, only 28.8% of these events were identified (21/73). Ten positive vEEGs with multicamera with 52 paroxysmal facial abnormal movements (52/73, 71.2%) would have been considered as negative with the single-camera approach. Conclusions The use of one additional facial camera can significantly increase the diagnostic accuracy of vEEGs in the detection of paroxysmal abnormal facial movements in the newborns.

Fuzzy qualitative human model for viewpoint identification

The integration of advance human motion analysis techniques in low-cost video cameras has emerged for consumer applications, particularly in video surveillance systems. These smart and cheap devices provide the practical solutions for improving the public safety and homeland security with the capability of understanding the human behaviour automatically. In this sense, an intelligent video surveillance system should not be constrained on a person viewpoint, as in natural, a person is not restricted to perform an action from a fixed camera viewpoint. To achieve the objective, many state-of-the-art approaches require the information from multiple cameras in their processing. This is an impractical solution by considering its feasibility and computational complexity. First, it is very difficult to find an open space in real environment with perfect overlapping for multi-camera calibration. Secondly, the processing of information from multiple cameras is computational burden. With this, a surge of interest has sparked on single camera approach with notable work on the concept of view specific action recognition. However in their work, the viewpoints are assumed in a priori. In this paper, we extend it by proposing a viewpoint estimation framework where a novel human contour descriptor namely the fuzzy qualitative human contour is extracted from the fuzzy qualitative Poisson human model for viewpoint analysis. Clustering algorithms are used to learn and classify the viewpoints. In addition, our system is also integrated with the capability to classify front and rear views. Experimental results showed the reliability and effectiveness of our proposed viewpoint estimation framework by using the challenging IXMAS human action dataset.

Standardizing the analysis of conditioned fear in rodents: a multidimensional software approach

Data comparability between different laboratories strongly depends on the individually applied analysis method. This factor is often a critical source of variation in rodent phenotyping and has never been systematically investigated in Pavlovian fear conditioning paradigms. In rodents, fear is typically quantified in terms of freezing duration via manual observation or automated systems. While manual analysis includes biases such as tiredness or inter-personal scoring variability, computer-assisted systems are unable to distinguish between freezing and immobility. Consequently, the novel software called MOVE follows a semi-automatized approach that prefilters video sequences of interest for the final human judgment. Furthermore, MOVE allows integrating additional data sources (e.g. force-sensitive platform, EEG) to reach the most accurate and precise results. MOVE directly supports multi-angle video recordings with webcams or standard laboratory equipment. The integrated manual key logger and internal video player complement this all-in-one software solution. Calculating the interlaboratory variability of manual freezing evaluation revealed significantly different freezing scores in two out of six laboratories. This difference was minimized when all experiments were analyzed with MOVE. Applied to a genetically modified mouse model, MOVE revealed higher fear responses of CB1 deficient mice compared to their wild-type littermates after foreground context fear conditioning. Multi-angle video analysis compared to the single-camera approach reached up to 15% higher accuracy and two fold higher precision. Multidimensional analysis provided by integration of additional data sources further improved the overall result. We conclude that the widespread usage of MOVE could substantially improve the comparability of results from different laboratories.

MONTE-CARLO- SIMULATION FOR ACCURACY ASSESSMENT OF A SINGLE CAMERA NAVIGATION SYSTEM

Abstract. The paper describes a simulation-based optimization of an optical tracking system that is used as a 6DOF navigation system for neurosurgery. Compared to classical system used in clinical navigation, the presented system has two unique properties: firstly, the system will be miniaturized and integrated into an operating microscope for neurosurgery; secondly, due to miniaturization a single camera approach has been designed. Single camera techniques for 6DOF measurements show a special sensitivity against weak geometric configurations between camera and object. In addition, the achievable accuracy potential depends significantly on the geometric properties of the tracked objects (locators). Besides quality and stability of the targets used on the locator, their geometric configuration is of major importance. In the following the development and investigation of a simulation program is presented which allows for the assessment and optimization of the system with respect to accuracy. Different system parameters can be altered as well as different scenarios indicating the operational use of the system. Measurement deviations are estimated based on the Monte-Carlo method. Practical measurements validate the correctness of the numerical simulation results.

Three-Dimensional Structural Translation and Rotation Measurement Using Monocular Videogrammetry

Measuring displacement for large-scale structures has always been an important yet challenging task. In most applications, it is not feasible to provide a stationary platform at the location where its displacements need to be measured. Recently, image-based technique for three-dimensional (3D) displacement measurement has been developed and proven to be applicable to civil engineering structures. Most of these developments, however, use two or more cameras and require sophisticated calibration using a total station. In this paper, we present a single-camera approach that can simultaneously measure both 3D translation and rotation of a planar target attached on a structure. The intrinsic parameters of the camera are first obtained using a planar calibration board arbitrarily positioned around the target location. The obtained intrinsic parameters establish the relationship between the 3D camera coordinates and the two-dimensional image coordinates. These parameters can then be used to extract the rotation and translation of the planar target using recorded image sequence. The proposed technique is illustrated using two laboratory tests and one field test. Results show that the proposed monocular videogrammetric technique is a simple and effective alternative method to measure 3D translation and rotation for civil engineering structures. It should be noted that the proposed technique cannot measure translation along the direction perpendicular to the image plane. Hence, proper caution should be taken when placing target and camera.

A video and acoustic methodology to map bite placement at the patch scale

Bite placement plays an important role in determining the mean weight of bites removed from a patch, and hence intake rate. This paper describes a video and acoustic methodology to map the sequential placement of bites on the sward surface. The methodology was evaluated for dairy heifers grazing small (0.34 m 2) patches of alfalfa ( Medicago sativa L.) to three levels of depletion (6, 18 and 30 bites). Grazing was recorded by a single video camera positioned 0.9 m in front of the animal and on average 1.67 m above the ground. Acoustic monitoring enabled the precise timing of biting jaw movements (bite or chew-bite). For each bite, a single video frame showing the position of the animal's head in the sward canopy was selected at the point in time corresponding to bite severance. Custom image-processing software was used to extract the image (apparent) coordinates of the tip of the muzzle, which was then converted geometrically to world (true) coordinates on the sward surface. A fixed displacement of 8 cm was applied to the world coordinates in order to determine the bite centre. The pattern of grazing impact across the sward surface was predicted by assuming a radius of impact around each bite centre. This pattern was compared with the measured status (grazed or un-grazed) of the herbage beneath each cell of a grid placed over the patch after grazing. Bite placement on the sward surface, as defined by the bite-centre coordinates, followed a progressing, side-to-side pathway. The median distance between the centres of consecutive bites was 12.1 cm, and was significantly less than expected by random bite placement. The orientation of consecutive bite pairs differed significantly from random, consistent with the side-to-side pathway of bite placement. Nevertheless, based on nearest neighbour analysis, the overall pattern of bite spacing on the surface of the sward did not differ significantly from random. These results suggest that the observed declining trend in mean effective bite area with increasing depletion ( P = 0.06) derived from inefficient exploitation of the sward surface. The assumption of a radius of impact of 6 cm revealed a broad correspondence between the measured and predicted patterns of grazing impact across the sward surface. Discrepancies most likely reflected sweeping actions of the tongue during bite formation, lateral head movements during bite severance and simplifying assumptions required by the single-camera approach. The results indicate that the methodology is potentially useful for investigating the rules governing bite placement in the horizontal plane.