Camera Distance Research Articles

Evaluation of Heat Distribution for the Diagnosis of the Hoof with Abscess by Infrared Thermography in Horses

Background: The study of normal temperature distribution for the diagnosis of hoof disease in horses using Infrared Thermography (IRT) is rare, therefore, the normal temperature distribution is to be investigated. In this study, we investigated the possible use of IRT in the diagnosis of hoof disease in horses. Methods: A total of 66 horses (56 healthy horses and 10 horses with hoof abscess) were used in this study. Veterinarians and farriers performed physical examinations, such as lameness examination, palpation, hoof test, and radiography, on all horses. IRT was performed in standard conditions. The plantar of the hoof was lifted upward by the owner, and the distance of the thermal camera between the plantar of the hoof was 0.3 - 0.5 m. For evaluation, the heat pattern of the plantar of the hoof was divided into seven regions of interest (ROIs), and statistical analysis was performed. Results: On performing IRT, the temperature of healthy hooves and hooves with hoof abscess was found to be 25.77 °C ± 3.87 °C (mean ± SD) and 31.94 °C ± 2.60 °C, respectively (p < 0.0001). The mean temperature of ROIs in hooves with abscesses was 6.17 °C higher than that of healthy hooves. Sole regions were found to be especially prominent. Additionally, all ROIs of hooves with hoof abscess classified IRT with high sensitivity (74.3%) and specificity (87.5%). Conclusion: The present study demonstrated the usefulness of IRT in diagnosing hoof with abscess. Moreover, this study suggests that IRT may be useful as a new temperature measurement analysis system in terms of determining differences in the heat distribution of the hoof.

A Pilot Study on Automatic Three-Dimensional Quantification of Barrett’s Esophagus for Risk Stratification and Therapy Monitoring

Barrett's epithelium measurement using widely accepted Prague C&M classification is highly operator dependent. We propose a novel methodology for measuring this risk score automatically. The method also enables quantification of the area of Barrett's epithelium (BEA) and islands, which was not possible before. Furthermore, it allows 3-dimensional (3D) reconstruction of the esophageal surface, enabling interactive 3D visualization. We aimed to assess the accuracy of the proposed artificial intelligence system on both phantom and endoscopic patient data. Using advanced deep learning, a depth estimator network is used to predict endoscope camera distance from the gastric folds. By segmenting BEA and gastroesophageal junction and projecting them to the estimated mm distances, we measure C&M scores including the BEA. The derived endoscopy artificial intelligence system was tested on a purpose-built 3D printed esophagus phantom with varying BEAs and on 194 high-definition videos from 131 patients with C&M values scored by expert endoscopists. Endoscopic phantom video data demonstrated a 97.2% accuracy with a marginal ± 0.9 mm average deviation for C&M and island measurements, while for BEA we achieved 98.4% accuracy with only ±0.4 cm2 average deviation compared with ground-truth. On patient data, the C&M measurements provided by our system concurred with expert scores with marginal overall relative error (mean difference) of 8% (3.6 mm) and 7% (2.8 mm) for C and M scores, respectively. The proposed methodology automatically extracts Prague C&M scores with high accuracy. Quantification and 3D reconstruction of the entire Barrett's area provides new opportunities for risk stratification and assessment of therapy response.

Danger, Sex, and Everything Else

Abstract. This study tests the effects of camera distance and camera angle on emotional response across four categories of pictures covering a large emotional range (positive and negative miscellanea, erotica, and threat), using the International Affective Picture System (IAPS) –a large database of emotionally evocative photographs. We content analyzed 722 images for the content category and camera framing (distance and angle), employing these as independent factors in analyses, and used the IAPS’ pre-existing normative average ratings of emotional valence, arousal, and dominance as dependent variables. As hypothesized, affective responses were generally increased by closer framing and high and low angles (compared to straight angles), but the content of the picture played an important role in determining effect strength and direction. In particular, closeness increased arousal for all picture groups but had the opposite effect on positive miscellaneous pictures, straight angles decreased the emotional response for the two miscellanea groups, and low angles increased the emotional response for threatening pictures. This study is the first to show that previously found camera framing effects apply to pictures of high emotional intensity (e.g., erotica and threat). We suggest that future work should consider formal manipulations alongside message content.

Optimization of indocyanine green angiography for colon perfusion during laparoscopic colorectal surgery.

AimThis study aims to evaluate the extrinsic effects of conditional factors affecting quantitative parameters and to establish the optimization of indocyanine green (ICG) angiography using in vitro experiments and a prospective observational study.MethodIn vitro experiments were performed to evaluate the correlation between conditional factors such as camera distance, surrounding lighting, fluorescence emission sources and ICG doses. The fluorescence intensity was measured from the ICG‐containing test tube in each condition. In the clinical study, ICG angiography was applied to patients with colorectal cancer (n = 164). The quantitative perfusion parameters were the maximal fluorescence intensity (F MAX), slope, T 1/2MAX and perfusion time ratio (TR). Camera position, distance to colon, fluorescence emission source, surrounding lighting, site of angiography and ICG specific mode were considered as conditional factors and compared with the quantitative parameters to identify the optimal condition of ICG angiography.ResultsThe fluorescence intensity had an inverse correlation with distance, and the transitional zone was shown at a distance of 4–5 cm by slope differential. F MAX, T 1/2MAX and slope were affected significantly by camera distance, site of angiography, fluorescence emission source and ICG mode as conditional factors. On multivariate analysis, F MAX was independently associated with spectral ICG mode with red inversion, laser mode and camera distance. Conversely, TR was not related to any conditional factors.ConclusionSince quantitative parameters of ICG angiography are influenced by various conditions, a standardized protocol is required. The application of ICG specific modes with a constant distance of 4–5 cm can provide optimized fluorescence images.

Detection and quantification of bolt loosening using RGB-D camera and Mask R-CNN

Bolt loosening is one of the most common types of damage for bolt-connected plates. Existing vision techniques detect bolt loosening based on the measurement of bolt rotation or the exposure of bolt threads. However, these techniques examine bolt tightness only in a qualitative manner, or require a reference measurement at the initially tightened state of the bolt for quantitative estimation. In this study, the exposed shank length of a bolt is quantitatively measured using an RGB-depth camera and a mask-region-based convolutional neural network but without requiring any measurement from the initial state of the bolt. The performance of the proposed technique is validated by conducting lab-scale experiments, in which the angle and distance of the camera are varied with respect to a target inspection area. The proposed technique successfully detects bolt loosening at exposed shank length over 3 mm with a resolution of 1 mm and 97% accuracy at different camera angles (40°–90°) and distances (up to 65 cm).

Toward quantitative assessment of deformational plagiocephaly and brachycephaly at the point-of-care.

Purpose: Develop and validate algorithms that can enable a novice user to quantitatively measure the head shape parameters associated with deformational plagiocephaly and brachycephaly (DPB) using 2D rendered images. Approach: First, the head contour is extracted semi-automatically using the intelligent scissors method. We then automatically compute two indices used in the clinical determination of the DPB from the head shape parameters: the cranial index (CI) and the cranial vault asymmetry index (CVAI). We also present methods to quantify and compensate for the user variability, including camera angle and distance from the head using 2D rendered images. We compared the results of our technology with ground-truth (GT) measurements from 53 infants with DPB and normal cranial parameters. Results: The Spearman correlation coefficient between the new 2D rendered method and the 3D GT was 0.94 ( ) and 0.96 ( ) for CI and CVAI, respectively. Different simulated camera angles and distances from the head resulted in variation in CI and CVAI in the range of and units, respectively. The limits of agreement of the Bland-Altman test were reduced from and to and for CI and CVAI, respectively, by combining results from different camera angles and positions in our method. The overall accuracy of the proposed technology for DPB detection was 100%. Conclusions: The 2D rendered images of the head can be accurately analyzed to assess DPB. Further study on 2D photos taken from human subjects is warranted.

Effect of Enhanced ADAS Camera Capability on Traffic State Estimation.

Traffic flow data, such as flow, density and speed, are crucial for transportation planning and traffic system operation. Recently, a novel traffic state estimating method was proposed using the distance to a leading vehicle measured by an advanced driver assistance system (ADAS) camera. This study examined the effect of an ADAS camera with enhanced capabilities on traffic state estimation using image-based vehicle identification technology. Considering the realistic distance error of the ADAS camera from the field experiment, a microscopic simulation model, VISSIM, was employed with multiple underlying parameters such as the number of lanes, traffic demand, the penetration rate of ADAS vehicles and the spatiotemporal range of the estimation area. Although the enhanced functions of the ADAS camera did not affect the accuracy of the traffic state estimates significantly, the ADAS camera can be used for traffic state estimation. Furthermore, the vehicle identification distance of the ADAS camera and traffic conditions with more lanes did not always ensure better accuracy of the estimates. Instead, it is recommended that transportation planners and traffic engineering practitioners carefully select the relevant parameters and their range to ensure a certain level of accuracy for traffic state estimates that suit their purposes.

Objective and Subjective Clinical Swallowing Outcomes via Telehealth: Reliability in Outpatient Clinical Practice.

Purpose The COVID-19 pandemic has drastically increased the use of telehealth. Prior studies of telehealth clinical swallowing evaluations provide positive evidence for telemanagement of swallowing. However, the reliability of these measures in clinical practice, as opposed to well-controlled research conditions, remains unknown. This study aimed to investigate the reliability of outcome measures derived from clinical swallowing tele-evaluations in real-world clinical practice (e.g., variability in devices and Internet connectivity, lack of in-person clinician assistance, or remote patient/caregiver training). Method Seven raters asynchronously judged clinical swallowing tele-evaluations of 12 movement disorders patients. Outcomes included the Timed Water Swallow Test (TWST), Test of Masticating and Swallowing Solids (TOMASS), and common observations of oral intake. Statistical analyses were performed to examine inter- and intrarater reliability, as well as qualitative analyses exploring patient and clinician-specific factors impacting reliability. Results Forty-four trials were included for reliability analyses. All rater dyads demonstrated "good" to "excellent" interrater reliability for measures of the TWST (intraclass correlation coefficients [ICCs] ≥ .93) and observations of oral intake (≥ 77% agreement). The majority of TOMASS outcomes demonstrated "good" to "excellent" interrater reliability (ICCs ≥ .84), with the exception of the number of bites (ICCs = .43-.99) and swallows (ICCs = .21-.85). Immediate and delayed intrarater reliability were "excellent" for most raters across all tasks, ranging between ICCs of .63 and 1.00. Exploratory factors potentially impacting reliability included infrequent instances of suboptimal video quality, reduced camera stability, camera distance, and obstruction of the patient's mouth during tasks. Conclusions Subjective observations of oral intake and objective measures taken from the TWST and the TOMASS can be reliably measured via telehealth in clinical practice. Our results provide support for the feasibility and reliability of telehealth for outpatient clinical swallowing evaluations during COVID-19 and beyond. Supplemental Material https://doi.org/10.23641/asha.13661378.

Multi-View Data Augmentation to Improve Wound Segmentation on 3D Surface Model by Deep Learning

Wound area segmentation really progressed with the emergence of deep learning, due to its robustness in uncontrolled lighting and no need to design hand-crafted features but two limits have still to be overcome: firstly, its performance relies on the size and quality of the training dataset in the medical field, where data annotation is costly and time-consuming; secondly the accuracy of the segmentation depends highly on the camera distance and angle and moreover perspective effects prevent measuring real surfaces in single views. To address concurrently these two issues, we propose to apply multi-view modeling: an image sequence is acquired around the wound site and enables wound 3D reconstruction. Then, a segmentation step is run to extract roughly the wound from the background in each view and to select the best view with an original strategy. This view provides the most accurate segmentation and the real wound bed area even on non planar wounds. Finally, this segmentation is backprojected in each view to generate a complete set of well annotated real images to reinforce the learning step of the neural network. In our experiments, we compare several strategies to select the best view in the image sequence. The proposed method, tested on a dataset of 270 images, outperforms standard deep learning approach based on a single view, as recorded with DICE index and IoU score which rise respectively from 36.53% to 86.3% and 29.48% to 77.09% for the wound class to achieve an overall DICE and IoU score of 93.04% and 86.61% including background class. These results attest to the robustness of our method and its improved accuracy in the wound segmentation task.

Analysing chickpea physical characteristics emphasising on count, shape and size using computer vision

Chickpeas are the food supplements which are very rich in protein, fibre and minerals. This grain affects a large percentage of Indian economy and India has the largest production and consumption of these grains. The most important quality attribute of chickpea's are size of seed, colour and taste. Based on these quality attributes chickpeas are graded into three main grades 7-8 mm, 8-9 mm, 9 mm and above. Determining seed size through sieve analysis in legumes is labour dependent, time consuming and inaccurate method. In general quality assessment of desi chickpea is done by visual inspection of small samples from the lot which is a slow and inaccurate process. The paper proposes a computer vision-based algorithm to assess the quality of chickpea on the basis of their shape, size and count. Experiment is performed for 20 sample images the results present that accuracy achieved through proposed algorithm for width calculation is 97.4%, for height calculation is 98.14%, for aspect ratio accuracy achieved is 97.3% and for chickpea count accuracy achieved is 98.6%. The proposed algorithm used concept of reference object to overcome the problem of dependency on distance of object and camera while capturing the image.

Deep High-Resolution Representation Learning for Cross-Resolution Person Re-Identification.

Person re-identification (re-ID) tackles the problem of matching person images with the same identity from different cameras. In practical applications, due to the differences in camera performance and distance between cameras and persons of interest, captured person images usually have various resolutions. This problem, named Cross-Resolution Person Re-identification, presents a great challenge for the accurate person matching. In this paper, we propose a Deep High-Resolution Pseudo-Siamese Framework (PS-HRNet) to solve the above problem. Specifically, we first improve the VDSR by introducing existing channel attention (CA) mechanism and harvest a new module, i.e., VDSR-CA, to restore the resolution of low-resolution images and make full use of the different channel information of feature maps. Then we reform the HRNet by designing a novel representation head, HRNet-ReID, to extract discriminating features. In addition, a pseudo-siamese framework is developed to reduce the difference of feature distributions between low-resolution images and high-resolution images. The experimental results on five cross-resolution person datasets verify the effectiveness of our proposed approach. Compared with the state-of-the-art methods, the proposed PS-HRNet improves the Rank-1 accuracy by 3.4%, 6.2%, 2.5%,1.1% and 4.2% on MLR-Market-1501, MLR-CUHK03, MLR-VIPeR, MLR-DukeMTMC-reID, and CAVIAR datasets, respectively, which demonstrates the superiority of our method in handling the Cross-Resolution Person Re-ID task. Our code is available at https://github.com/zhguoqing.

The effects of camera resolution and distance on suspect height analysis using PhotoModeler

The purpose of this study was to examine how camera resolution and suspect-camera distance affect the accuracy and precision of suspect height estimations using PhotoModeler software. Sixteen individuals were measured and recorded standing at 15 pre-set distances on 7 security cameras, each with a different resolution setting. A height scale was used to measure each individual’s height prior to recording and was also used as a reference height. Height estimates were taken in PhotoModeler by extracting video frames that were calibrated using 3D point model data obtained from a laser scan of the test site. Errors were calculated for the measurements and compared using the Kruskal-Wallis H-test, which indicated significant differences for errors among different resolutions and distances (p < 0.01). Interaction plots, however, demonstrated little difference in errors for most resolutions and positions. The accuracy and precision of height estimates began to decrease with resolutions under 960H and distances over 36.5 m.

Bleeding Puppets: Transmediating Genre in Pili Puppetry

Bleeding Puppets: Transmediating Genre in Pili Puppetry

Example-driven virtual cinematography by learning camera behaviors

Designing a camera motion controller that has the capacity to move a virtual camera automatically in relation with contents of a 3D animation, in a cinematographic and principled way, is a complex and challenging task. Many cinematographic rules exist, yet practice shows there are significant stylistic variations in how these can be applied. In this paper, we propose an example-driven camera controller which can extract camera behaviors from an example film clip and re-apply the extracted behaviors to a 3D animation, through learning from a collection of camera motions. Our first technical contribution is the design of a low-dimensional cinematic feature space that captures the essence of a film's cinematic characteristics (camera angle and distance, screen composition and character configurations) and which is coupled with a neural network to automatically extract these cinematic characteristics from real film clips. Our second technical contribution is the design of a cascaded deep-learning architecture trained to (i) recognize a variety of camera motion behaviors from the extracted cinematic features, and (ii) predict the future motion of a virtual camera given a character 3D animation. We propose to rely on a Mixture of Experts (MoE) gating+prediction mechanism to ensure that distinct camera behaviors can be learned while ensuring generalization. We demonstrate the features of our approach through experiments that highlight (i) the quality of our cinematic feature extractor (ii) the capacity to learn a range of behaviors through the gating mechanism, and (iii) the ability to generate a variety of camera motions by applying different behaviors extracted from film clips. Such an example-driven approach offers a high level of controllability which opens new possibilities toward a deeper understanding of cinematographic style and enhanced possibilities in exploiting real film data in virtual environments.

Artificial intelligence-empowered pipeline for image-based inspection of concrete structures

Inspection of civil infrastructure is a major challenge to engineers due to the limitations in existing practice, which are as laborious, time-consuming and prone to error. To address these issues, we have applied deep learning for image-based inspection of concrete defects of civil infrastructure, and have established an artificial intelligence-empowered inspection pipeline methodology. This innovative approach comprises anomaly detection, anomaly extraction and defect classification. The anomaly detection and extraction are used to identify defect regions from the enormous volume of image datasets, which used to be the common challenges encountered in automated visual inspections. The search space of defects is substantially reduced, i.e., at least 60% of the original volume of image datasets, with an average hit rate of ~88.7% and an average false alarm rate of ~14.2%. Following that, deep learning-based classifiers are used to categorize defects into appropriate classes. The assessment results show that the proposed inspection pipeline exhibits great capability in detecting, extracting and classifying defects subjected to various environmental and operational conditions, including lighting condition, camera distance and capturing angle, with an average testing accuracy of 95.6%.

DEEP LEARNING FOR MONOCULAR DEPTH ESTIMATION FROM UAV IMAGES

Abstract. Depth is an essential component for various scene understanding tasks and for reconstructing the 3D geometry of the scene. Estimating depth from stereo images requires multiple views of the same scene to be captured which is often not possible when exploring new environments with a UAV. To overcome this monocular depth estimation has been a topic of interest with the recent advancements in computer vision and deep learning techniques. This research has been widely focused on indoor scenes or outdoor scenes captured at ground level. Single image depth estimation from aerial images has been limited due to additional complexities arising from increased camera distance, wider area coverage with lots of occlusions. A new aerial image dataset is prepared specifically for this purpose combining Unmanned Aerial Vehicles (UAV) images covering different regions, features and point of views. The single image depth estimation is based on image reconstruction techniques which uses stereo images for learning to estimate depth from single images. Among the various available models for ground-level single image depth estimation, two models, 1) a Convolutional Neural Network (CNN) and 2) a Generative Adversarial model (GAN) are used to learn depth from aerial images from UAVs. These models generate pixel-wise disparity images which could be converted into depth information. The generated disparity maps from these models are evaluated for its internal quality using various error metrics. The results show higher disparity ranges with smoother images generated by CNN model and sharper images with lesser disparity range generated by GAN model. The produced disparity images are converted to depth information and compared with point clouds obtained using Pix4D. It is found that the CNN model performs better than GAN and produces depth similar to that of Pix4D. This comparison helps in streamlining the efforts to produce depth from a single aerial image.

Modeling standard plenoptic camera by an equivalent camera array

Postprocessing of light fields enables us to extract more information from a scene compared to traditional cameras. Plenoptic cameras and camera arrays are two common methods for light field capture. It has been long recognized that the two devices are in some ways equivalent. Practically, both techniques have important constraints. Camera arrays are unable to provide high angular sampling, and the plenoptic camera can have a limited spatial sampling. In simulation, we can easily explore both constraints by simulating two-dimensional viewpoint images and combining them into a four-dimensional light field. We present a transformation for converting between equivalent plenoptic configurations and camera arrays when they capture pristine light fields produced in simulation. We use this approach to simulate light fields of simple scenes and validate our transformation by comparing the focus distance of a standard plenoptic camera and the equivalent camera array’s light field. We also show how some simple practical effects can be added to the pristine, synthetic light field via postprocessing and their effect on refocusing distance.

3D Tracking of Human Motion Using Visual Skeletonization and Stereoscopic Vision.

The design of markerless systems to reconstruct human motion in a timely, unobtrusive and externally valid manner is still an open challenge. Artificial intelligence algorithms based on automatic landmarks identification on video images opened to a new approach, potentially e-viable with low-cost hardware. OpenPose is a library that t using a two-branch convolutional neural network allows for the recognition of skeletons in the scene. Although OpenPose-based solutions are spreading, their metrological performances relative to video setup are still largely unexplored. This paper aimed at validating a two-cameras OpenPose-based markerless system for gait analysis, considering its accuracy relative to three factors: cameras' relative distance, gait direction and video resolution. Two volunteers performed a walking test within a gait analysis laboratory. A marker-based optical motion capture system was taken as a reference. Procedures involved: calibration of the stereoscopic system; acquisition of video recordings, simultaneously with the reference marker-based system; video processing within OpenPose to extract the subject's skeleton; videos synchronization; triangulation of the skeletons in the two videos to obtain the 3D coordinates of the joints. Two set of parameters were considered for the accuracy assessment: errors in trajectory reconstruction and error in selected gait space-temporal parameters (step length, swing and stance time). The lowest error in trajectories (~20 mm) was obtained with cameras 1.8 m apart, highest resolution and straight gait, and the highest (~60 mm) with the 1.0 m, low resolution and diagonal gait configuration. The OpenPose-based system tended to underestimate step length of about 1.5 cm, while no systematic biases were found for swing/stance time. Step length significantly changed according to gait direction (p = 0.008), camera distance (p = 0.020), and resolution (p < 0.001). Among stance and swing times, the lowest errors (0.02 and 0.05 s for stance and swing, respectively) were obtained with the 1 m, highest resolution and straight gait configuration. These findings confirm the feasibility of tracking kinematics and gait parameters of a single subject in a 3D space using two low-cost webcams and the OpenPose engine. In particular, the maximization of cameras distance and video resolution enabled to achieve the highest metrological performances.

Feeding Specialization of Honey Badgers in the Sahara Desert: A Trial of Life in a Hard Environment

The honey badger (Mellivora capensis) is a medium-sized carnivore distributed throughout Africa to the Arabian Peninsula, Iran, Turkmenistan, and India. However, available information on its ecology is very scarce. We studied its feeding ecology in the remote north-western Sahara Desert, based on the contents of 125 fecal samples collected during large scale surveys. Samples were confirmed to belong to honey badgers by camera trapping and genetic analyses. Barely 18 prey species were detected. The diet primarily consisted of spiny-tailed lizards Uromastyx nigriventris and U. dispar (72% of volume in scats). Secondary prey items were arthropods (14%), small mammals (8%), other reptiles (4%), and eggs (0.8%). Some small geographic and temporal differences were related to the consumption of beetle larvae and rodents as alternative prey. Camera trapping and distance sampling surveys showed that diel activities did not overlap between honey badgers and spiny-tailed lizards, suggesting that badgers primarily dig lizards out of their burrows when inactive. Consumption of spiny lizards by other sympatric meso-carnivores was &lt; 6.1% of occurrence (223 analyzed scats); the honey badger behaved as a trophic specialist in the Sahara, probably thanks to exclusive anatomical adaptations for digging. We discuss the role of this circumstance minimizing the exploitative competition, which could allow the survival of this large mustelid in this low productive and highly competitive environment.

Vision based distance estimation from single RGB camera using field of view and magnification measurements –an AI based non triangulation technique for person distance estimation in surveillance areas

Depth data from conventional cameras in monitoring fields provides a thorough assessment of human behavior. In this context, the depth of each viewpoint must be calculated using binocular stereo, which requires two cameras to retrieve 3D data. In networked surveillance environments, this drives excess energy and also provides extra infrastructure. We launched a new computational photographic technique for depth estimation using a single camera based on the ideas of perspective projection and lens magnification property. The person to camera distance (or depth) is obtained from understanding the focal length, field of view and magnification characteristics. Prior to finding distance, initially real height is estimated using Human body anthropometrics. These metrics are given as inputs to the Gradient-Boosting machine learning algorithm for estimating Real Height. And then magnification and Field of View measurements are extracted for each sample. The depth (or distance) is predicted on the basis of the geometrical relationship between field of view, magnification and camera at object distance. Using physical distance and height measurements taken in real time as ground truth, experimental validation is performed and it is inferred that with in 3m–7 m range, both in indoor and outdoor environments, the camera to person distance (Preddist) anticipated from field of view and magnification is 91% correlated with actual depth at a confidence point of 95% with RMSE of 0.579.