Search

In this study a 3-dimensional (3D) camera system was set up to measure individual feed intake of dairy cows in a commercial in-house setting. The system was developed to identify the cows while eating, predict body weight based on the curvature of the back of the cow, and quantify the amount of feed eaten by the cow at each visit of eating. The identification of the cow was based on recognizing the patterns, colors, and curvatures of the back from a reference database obtained in a corridor after milking, where images were taken of all cows with a simultaneous reading of the electronic ear tag. Body weight is predicted using the curvatures of the back of the cow. Feed intake is quantified as the difference in surface of the feed a cow can reach before and after a visit is initiated. This estimate is in liters but converted to kilograms, using the density of the feed in the specific herd. A total of 9,142 cows were measured in 19 herds across 3 breeds: Jersey (2,513 cows), Red Dairy Cattle (2,813 cows), and Holstein (3,816 cows). Mean daily feed intake was higher for Red Dairy Cattle (61.72 kg) and Holstein (64.59 kg) than for Jersey (55.74 kg). Repeatability estimates for daily feed intake as a weekly average was 0.62, 0.65, and 0.63 for Jersey, Red Dairy, and Holstein cattle, respectively. Mean body weight was higher for Red Dairy (647.9 kg) and Holstein (683.8 kg) than for Jersey (469.6 kg). Repeatability estimates for body weight as a weekly average was 0.83, 0.85, and 0.88 for Jersey, Red Dairy, and Holstein, respectively. The perspectives in having such records available is huge both for the farmer and for the dairy industry. The records can both be used for improving management in farms on an individual cow level and herd level, but also for genetic evaluation and selection as well as testing feeding regimens. Feed intake can be measured on an individual level using a 3D camera system. [ABSTRACT FROM AUTHOR]

Models of the human body representing digital twins of patients have attracted increasing interest in clinical research for the delivery of personalized diagnoses and treatments to patients. For example, noninvasive cardiac imaging models are used to localize the origin of cardiac arrhythmias and myocardial infarctions. The precise knowledge of a few hundred electrocardiogram (ECG) electrode positions is essential for their diagnostic value. Smaller positional errors are obtained when extracting the sensor positions, along with the anatomical information, for example, from X-ray Computed Tomography (CT) slices. Alternatively, the amount of ionizing radiation the patient is exposed to can be reduced by manually pointing a magnetic digitizer probe one by one to each sensor. An experienced user requires at least 15 min. to perform a precise measurement. Therefore, a 3D depth-sensing camera system was developed that can be operated under adverse lighting conditions and limited space, as encountered in clinical settings. The camera was used to record the positions of 67 electrodes attached to a patient's chest. These deviate, on average, by 2.0 mm ± 1.5 mm from manually placed markers on the individual 3D views. This demonstrates that the system provides reasonable positional precision even when operated within clinical environments. [ABSTRACT FROM AUTHOR]

Simple Summary: Dairy calves' welfare is rapidly gaining long-deserved attention from science and dairy farmers' communities. However, the elevated morbidity and mortality rates referred to in the literature reflect that there are still major problems in calves' husbandry despite the advances already made in recent years. The development of technologies may assist the traditional time-consuming welfare evaluations and improve calves' health and welfare on dairy farms. This review presents the state-of-the-art of technological advances related to dairy calves' management and welfare. Precision livestock farming (PLF) research is rapidly increasing and has improved farmers' quality of life, animal welfare, and production efficiency. PLF research in dairy calves is still relatively recent but has grown in the last few years. Automatic milk feeding systems (AMFS) and 3D accelerometers have been the most extensively used technologies in dairy calves. However, other technologies have been emerging in dairy calves' research, such as infrared thermography (IRT), 3D cameras, ruminal bolus, and sound analysis systems, which have not been properly validated and reviewed in the scientific literature. Thus, with this review, we aimed to analyse the state-of-the-art of technological applications in calves, focusing on dairy calves. Most of the research is focused on technology to detect and predict calves' health problems and monitor pain indicators. Feeding and lying behaviours have sometimes been associated with health and welfare levels. However, a consensus opinion is still unclear since other factors, such as milk allowance, can affect these behaviours differently. Research that employed a multi-technology approach showed better results than research focusing on only a single technique. Integrating and automating different technologies with machine learning algorithms can offer more scientific knowledge and potentially help the farmers improve calves' health, performance, and welfare, if commercial applications are available, which, from the authors' knowledge, are not at the moment. [ABSTRACT FROM AUTHOR]

In this work, we have designed a miniaturized dual focus module using a piezo-electric actuator for application in mobile. The device mainly consists of two lens mounts for holding the Alvarez-Lohmann lens. One of the lens mounts is stationary while another is rotated with the help of a piezoelectric actuator. The materials used for the development of the device are combinations of aluminum for chassis and lead zirconate titanate as piezo material for actuator. The movement of the actuator tip is an elliptical shape which used to facilitate the force to the lens. Mainly the mathematical modeling and finite element simulation of the device are carried out using COMSOL Multiphysics. The actuator rotates the mounted lens for 0.12° in one elliptical cycle at the applied voltage of 100 V with the resonance frequency. The device has a scope of applications in medical equipment such as a 3 D camera which is required mainly for disease diagnosis and medical operation purposes. [ABSTRACT FROM AUTHOR]

This paper proposes a time-series deep-learning 3D Kinect camera scheme to classify the respiratory phases with a lung tumor and predict the lung tumor displacement. Specifically, the proposed scheme is driven by two time-series deep-learning algorithmic models: the respiratory-phase classification model and the regression-based prediction model. To assess the performance of the proposed scheme, the classification and prediction models were tested with four categories of datasets: patient-based datasets with regular and irregular breathing patterns; and pseudopatient-based datasets with regular and irregular breathing patterns. In this study, 'pseudopatients' refer to a dynamic thorax phantom with a lung tumor programmed with varying breathing patterns and breaths per minute. The total accuracy of the respiratory-phase classification model was 100%, 100%, 100%, and 92.44% for the four dataset categories, with a corresponding mean squared error (MSE), mean absolute error (MAE), and coefficient of determination (R2) of 1.2–1.6%, 0.65–0.8%, and 0.97–0.98, respectively. The results demonstrate that the time-series deep-learning classification and regression-based prediction models can classify the respiratory phases and predict the lung tumor displacement with high accuracy. Essentially, the novelty of this research lies in the use of a low-cost 3D Kinect camera with time-series deep-learning algorithms in the medical field to efficiently classify the respiratory phase and predict the lung tumor displacement. [ABSTRACT FROM AUTHOR]

Background: Stereophotogrammetry (SPG) provides a more objective measurement of burn wound area than traditional clinical assessments. The recently developed Intel® RealSense™ D415/Wound Measure SPG system has yet to undergo formal evaluation in a paediatric population.Methods: A pilot study comparing the Intel® RealSense™ D415/Wound Measure to the previously validated LifeVizII®/DermaPix® SPG system, for burn assessment was conducted at a tertiary paediatric burn centre. Both systems were used to photograph and analyse the same acute wounds for each patient. Three independent raters measured wound area and perimeter. Level of agreement between systems and raters was estimated by calculating the intra-class correlation coefficient.Results: Wound area measurements were completed in both systems for 25 burns from 13 patients (median age, 2 years). The participants were mainly female (n = 9), with a median TBSA-B of 9% (IQR 3-20%). There was strong agreement between the systems 0.757 (95% CI 0.521, 0.885, p < 0.001). Within each SPG system, there was excellent inter-rater reliability.Conclusion: The Intel® RealSense™ D415/Wound Measure system may be a viable addition to the clinician's toolkit in the assessment of paediatric burn wound area. As with other SPG systems, there were significant challenges measuring wounds to highly contoured surfaces. [ABSTRACT FROM AUTHOR]

Objective: To compare three-dimensional (3D) with standard two-dimensional (2D) laparoscopic partial nephrectomy (LPN) with respect to intra- and postoperative outcomes. Material and methods: Data from 112 patients who underwent transperitoneal LPN from 2012 to 2014 by a single experienced surgeon were collected. Sixty patients (group 1) underwent conventional 2D LPN and 52 patients (group 2) 3D LPN. Perioperative patient, procedure, and tumor data were recorded. The follow-up period was 1-5 years. Results: The two groups had similar patient age (p=0.834) and body mass index (p=0.141). The total laparoscopy time (LT) was shorter in group 2 (119.0 vs. 106.0 min; p=0.009). Warm ischemia times (WITs) were also shorter in group 2 (11.5 vs. 10.0 min; p=0.032). The estimated blood loss (EBL) (350.0 vs. 250.0 mL; p<0.001) and hemoglobin (Hb) decrease (1.55 vs. 1.35 g/dL; p=0.536) were lower in the 3D LPN group. Creatinine (0 vs. 0 g/dL; p=0.610) increase and estimated glomerular filtration rate (eGFR) decrease (0 vs. 0 mL/min/1.73 m²; p=0.553) did not demonstrate statistically significant differences. Duration of hospitalization (7 vs. 7 days; p=0.099) and complication rates (p=0.559) were similar between the two groups. Conclusion: The new-generation 3D laparoscope has a great impact on significant LPN intraoperative parameters, mainly LT, WIT, and EBL. Hb decrease is also in favor of 3D vision, although not dramatically altered. Therefore, 3D LPN appears to be superior to conventional 2D LPNs. [ABSTRACT FROM AUTHOR]

Clinical application of a swallowing function evaluation system that is minimally invasive and enables an objective evaluation is necessary. We constructed a system that can synchronise and analyse lip motion with a three‐dimensional (3D) camera and swallowing dynamics with videofluoroscopy (VF) and clarified the relationship between lip movement and swallowing dynamics. A compact 3D camera was adapted to Microsoft XBox One Kinect Sensor®. We examined Kinect's accuracy and repeatability and analysed the highest measurement accuracy and repeatability of the distance between anguli oris muscles. The constructed system simultaneously measured, synchronised and analysed lip motion by Kinect and swallowing dynamics by VF. Fourteen elderly men without dysphagia were included. Barium turbid solution (5, 10, 15 and 20 mL) was used for swallowing. Measurement parameters were the 3D distance between angulus oris displacement (TDDD), swallowing quantity (SQ), oral transit time (OTT), stage transit duration (STD), pharyngeal transit time (PTT) and total swallowing duration (TSD). Statistical analyses were performed. The measurement accuracy and reproducibility were optimum within a 10° horizontal imaging angle at a 120‐cm measurement distance. SQ, TDDD, OTT, STD, PTT and TSD showed significant differences, and correlation was found between TDDD and OTT. SQ affected TDDD, OTT, STD, PTT and TSD; OTT could be predicted from TDDD. Improvement in the system and analysis method was considered to enable prediction of swallowing dynamics from body surface movement of the head and neck, including realisation of measurement conditions with higher precision and reproducibility, and from lip motion. [ABSTRACT FROM AUTHOR]

• A novel imaging system was developed for sow estrus detection. • Imagery data collected from rare view of individual sows. • Deep learning models were optimized to classify postures. • Posture pattern was used to detect estrus of gilts and sows. Posture patterns of sows or gilts could reflect their welfare, estrus, and health status. However, due to the large animal-to-staff ratio at sow farms, there is not yet a solution to closely monitor individual sows' posture patterns to determine their estrus status and make other managemental decisions. This study aimed to evaluate the performance of the convolutional neural network (CNN) models in recognizing sows' posture patterns using images of a LiDAR camera. The camera equipped on a wall-mounted robotic platform was used to take images of 21 sows from the back view at a 5-minute interval. Four types of images (IR: infrared image, DI: depth image, PCI: point cloud image, PCI_IR: point cloud image with IR as the alpha channel) were used to identify the postures of individual sows. Five CNN models were evaluated in this study, including SP_CNN (5 layers), VGG16 , MobileNet , Xception, and DenseNet121. Results showed that the image types had no significant impact on the validation accuracy of posture recognition (99.8 ± 0.2%, p > 0.1). Statistical results indicate that VGG16 required significantly more time (t = 2,218 ms) than the other four models in processing single images without significantly improving identification accuracy. The SP_CNN model had a significantly lower validation accuracy (99.6%) and used significantly less image processing time (t = 91 ms) than the rest of the models. It was found that for SP_CNN , DI images outperformed the other three types of images. Although no significant difference was found in validation accuracy (99.91% ± 0.04%) among MobileNet , Xception , and Densnet121. The MobileNet required significantly less time to process single images (t = 210 ms). The Xception model with PCI_IR images showed the highest test accuracy (98.6%). The results also show that both hourly and daily activity levels (standing or sitting) were significantly higher on the day of the onset of estrus than the values on the previous days. Meanwhile, the daily idle level (lateral lying) decreased significantly from two days prior to the onset of estrus. The decrease in daily idle level was drastic on the day of onset of estrus (12.9 ± 7.1%) and before (15.0 ± 12.0%). The study also found that monitoring intervals should not exceed 15 min for accurately quantifying sows' activity levels. The study concluded that posture patterns derived from the robotic imaging system could help detect sows' estrus status. [ABSTRACT FROM AUTHOR]

Abstract This study aims to use computational methods for elucidating the effect of limb shape on subgarment and subcutaneous pressures, stresses and strains. A framework was built that generates computational models from 3D arm scans using a depth sensing camera. Finite Element Analysis (FEA) was performed on the scans taken from 23 lymphoedema patients. Subgarment pressures were calculated based on local curvature for each patient and showed a large variability of pressure across each arm. Across the cohort an average maximum subgarment pressure of 5100 Pa was found as opposed to an intended garment pressure of 2500 Pa. Subcutaneous results show that stresses/strains in the adipose tissues more closely follow the subgarment pressures than in the stiffer skin tissues. Another novel finding was that a negative axial gradient in subgarment pressure (from wrist to elbow) consistently led to positive axial gradients for the Von Mises stresses in the adipose tissues; a phenomenon caused by a combination of arm shape and the stiffness ratio between skin and adipose tissues. In conclusion, this work fills a knowledge gap in compression therapy in clinical practice and can inform garment design or lead to optimal treatment strategies. [ABSTRACT FROM AUTHOR]

Introduction: Laparoscopic pyeloplasty is becoming the gold standard procedure for pelviureteric junction obstruction. The outcome of pyeloplasty depends on precise pyeloureteral anastomosis. Though in open pyeloplasty interrupted or continuous suture are practiced, in most of the laparoscopic or laparoscopy-assisted robotic pyeloplasty continuous suturing is practiced. After acquiring a 3-dimensional (3D) camera, we prospectively analyzed the suturing time, complication rate, and success rate between interrupted and continuous suturing in laparoscopic pyeloplasty.Objective: To prospectively review the outcome difference between interrupted suturing (group A) and continuous suturing (group B) while using a 3D camera.Materials and Methods: Out of 93 patients who underwent laparoscopic pyeloplasty, 6 patients who underwent retro-peritoneoscopic approach, 7 patients who had nondismembered technique, 7 patients with secondary renal calculi, and 3 patients with grossly dilated pelvis were excluded from the study to reduce bias. Hence, the remaining 70 patients who underwent transperitoneal pyeloplasty from 2012 to 2017 were prospectively analyzed, comparing 35 cases of interrupted suturing with 35 cases of continuous suturing using 3D camera in an alternating manner. The primary aim was to know the difference in suturing time. The secondary outcomes were success of pyeloplasty, complications, and drain volume. The statistical analysis was done using SPSS 2.0 software.Results: Of the 70 cases, with 35 in each arm studied, the mean suturing time, success rate, and complications were not significantly different. The total drain quantity during the hospital stay was observed to be more in the interrupted suturing group.Conclusion: The usage of a 3D camera and experience of the surgeon reduced the time difference between continuous and interrupted suturing in laparoscopic pyeloplasty. The outcome between interrupted and continuous suturing groups were the same. Though the drainage volume was more with interrupted suturing group the outcome was not altered. [ABSTRACT FROM AUTHOR]

Each year 152,000 people in the UK have a stroke. Almost all have an initial facial weakness. Many resolve in the first few days but it is estimated that 26,000 people experience some kind of long-term paralysis in their face. A survey of 107 United Kingdom based clinicians found that routine treatment of facial weakness was provision of exercises with a written instruction sheet. A multidisciplinary team, which includes patients, researchers and therapists have produced a working prototype system to improve facial weakness. It is called Face to Face and includes a Kinect sensor, a small form PC and a monitor. Patients follow exercises given by a therapist on the screen; the system records and simultaneously gives feedback, with a facial recognition algorithm providing tracking data for each captured frame of the user's face. Results from our small clinical trial indicate that the system is more successful at getting patients to complete their exercises than using a mirror, patients liked it, and they said it had helped improve their facial symmetry. Therapists said Face to Face encouraged patients to exercise daily, they liked the fact that it could be individually programmed and could record how much the patient had exercised. Based on the initial project work and positive outcomes Face to Face aims to help patients practice their facial muscle exercises to speed their recovery, providing direct benefits in terms of costs and time, and offering patients significant improvements. [ABSTRACT FROM AUTHOR]

In this paper, a new fully automated scanning laser Doppler vibrometer (LDV) measurement technique is presented. In contrast to existing scanning LDV techniques which use a 2D camera for the manual selection of sample points, we use a 3D Time-of-Flight camera in combination with a CAD file of the test object to automatically obtain measurements at pre-defined locations. The proposed procedure allows users to test prototypes in a shorter time because physical measurement locations are determined without user interaction. Another benefit from this methodology is that it incorporates automatic mapping between a CAD model and the vibration measurements. This mapping can be used to visualize measurements directly on a 3D CAD model. The proposed method is illustrated with vibration measurements of an unmanned aerial vehicle [ABSTRACT FROM AUTHOR]

• Two Time-of-Flight technologies have been tested to develop a yield monitor. • Two algorithms have been developed for weight estimation by volume measurement. • Some factors such as illumination or acceleration affect the accuracy. • The developed systems are more stable than load cells under field conditions. • The systems developed are a valid alternative to weighing with load cells. The introduction of fruit tree harvesters on the market allows the opportunity to incorporate new yield monitors. Traditionally, yield has been measured by in-the-field fruit batch weighing systems that employ load cells, which present certain problems as well as oscillations and outliers. We propose the development and evaluation of two distance measurement systems (an experimental one using an array of sensors with low-cost, Time-of-Flight technology and another, commercial system, with a 3D camera) to estimate the volume of fruit harvested in a big box and correlate the volume with its weight. To this end, two algorithms were developed to estimate the volume of fruit filling. Several tests were conducted to determine the field of view of the sensors and the influence of illumination, reflectivity of different surfaces, and vibrations in transit on the measurements they give. Illumination was a limiting factor on the accuracy of the experimental system and required mitigating actions to operate with it. The mean relative error of sensor distance measurement was less than 0.8 % and 1.6 % for the commercial and experimental systems, respectively, which decreased as distance from the measurement target increased. Measurements on matte surfaces showed a lower measurement error than those on glossy surfaces, with error being twice as high in the commercial system than in the experimental system. The error in volume estimation was lower in the commercial system and could be reduced to less than 1.6 % with pre-calibration. In general, with the accelerations typical of agricultural traffic, in dynamic operation the distance sensors provided less variation in results than the load cells, which would require processing of the recorded signals. In the range of filling a box over 150 kg, the absolute error in weight estimation was 5.4 kg for the experimental system and 11.0 kg for the commercial system. However, this error may increase with the use of the experimental system if filling occurs from the center or from the corner. In general, the systems offer acceptable results for using this technology if extreme accuracy is not required. This work establishes the basics of a technology that can be an alternative to load cells and be applied to harvesting machinery to record continuous real-time production. [ABSTRACT FROM AUTHOR]

Microsoft Kinect systems have already been used for detecting lameness and determining body condition in dairy cattle. A combination of six Kinect cameras was used with the goal of measuring linear descriptive traits. To access the precision of measurements gathered with a fixed installed recording unit, front teats and ischial tuberosities were marked manually in the recordings. Teat lengths and heights of ischial tuberosities were then calculated from the 3D coordinates. Recorded with cattle standing still and walking, teat lengths showed a standard error range from 0.7 mm to 1.5 mm and 1.8 mm–3.2 mm, respectively. The standard errors regarding the heights of the ischial tuberosities ranged between 2.4 mm and 4.0 mm in standstill and between 14.0 mm and 22.5 mm when measured on a walking cow. [ABSTRACT FROM AUTHOR]

Camera based systems in dairy cattle have been intensively studied over the last years. Past studies have concentrated on single camera systems with a limited range of applications. Here the development of a camera system comprising multiple 3D cameras (six Microsoft Kinect cameras) for monitoring purposes in dairy cows is presented. A recording unit was constructed, and software for recording, synchronising, sorting and segmenting images, and transforming the 3D data in a joint coordinate system was implemented. The latter is called extrinsic calibration and was dealt with in this study using a 3D calibration object. The internal estimations of acceleration data and coefficients for the parametrised plane describing the floor of the scenery obtained by the Kinect camera were tested and discussed with regard to their usage in the calibration process. The presented approach accurately determined whether a Kinect device was a side view camera or one of two types of top view cameras (accuracy 92.9%) and specified its mounting position in the system (accuracy 95.8%). Furthermore, rotations and translations between the cameras and a reference coordinate system were estimated from 3D point clouds of the calibration object. For cameras in upright position (side view cameras) the rotational accuracies were satisfactory, showing 4.4° (±2.9°) deviation from the reference. For the cameras in top view position larger errors (25.5° ± 6.4°) were measured due to them being mounted in an inclined way. Nevertheless, a basis for registration methods was achieved. [ABSTRACT FROM AUTHOR]

A method of increased measurement accuracy is proposed, along with the corresponding hardware for determining the size of objects and distances to them by analyzing digital photographic imagery. The results of experimental studies are presented. [ABSTRACT FROM AUTHOR]

Simple Summary: The aim of this study was to implement a commercially available automated body condition scoring (ABCS) camera system to collect data for developing a predictive equation of body condition dynamics throughout the lactation period. The body condition score can vary depending on many factors relative to a specific cow. Lactation number, DIM, disease status, and 305d-predicted-milk-yield (305PMY) were significant factors to create a multivariate prediction model for automatic body condition scores throughout lactation. Body condition scoring (BCS) is a traditional visual technique often using a five-point scale to non-invasively assess fat reserves in cattle. However, recent studies have highlighted the potential in automating body condition scoring using imaging technology. Therefore, the objective was to implement a commercially available automated body condition scoring (ABCS) camera system to collect data for developing a predictive equation of body condition dynamics throughout the lactation period. Holstein cows (n = 2343, parity = 2.1 ± 1.1, calving BCS = 3.42 ± 0.24), up to 300 days in milk (DIM), were scored daily using two ABCS cameras mounted on sort-gates at the milk parlor exits. Scores were reported on a 1 to 5 scale in 0.1 increments. Lactation number, DIM, disease status, and 305d-predicted-milk-yield (305PMY) were used to create a multivariate prediction model for body condition scores throughout lactation. The equation derived from the model was: ABCSijk = 1.4838 − 0.00452 × DIMi − 0.03851 × Lactation numberj + 0.5970 × Calving ABCSk + 0.02998 × Disease Status(neg)l − 1.52 × 10−6 × 305PMYm + eijklm. We identified factors which are significant for predicting the BCS curve during lactation. These could be used to monitor deviations or benchmark ABCS in lactating dairy cows. The advantage of BCS automation is that it may provide objective, frequent, and accurate BCS with a higher degree of sensitivity compared with more sporadic and subjective manual BCS. Applying ABCS technology in future studies on commercial dairies may assist in providing improved dairy management protocols based on more available BCS. [ABSTRACT FROM AUTHOR]

Simple Summary: Body condition scoring is a valuable tool used to assess the changes in subcutaneous body tissue reserves of dairy cows throughout the lactation. A visual method is typically used to assign a body condition score (BCS) to a cow following a standardized scale based on an assessment of tissue cover in the hind quarters of the animal. This method is subject to operator bias and is labor intensive, limiting the number of animals that can be scored and frequency of measurement. The objective of this study was to evaluate the suitability of an automated 3D body condition scoring camera system with capability to measure BCS daily as an alternative to visual body condition scoring for research applications. We found that the camera system using raw data greatly increased precision and ability to detect changes in BCS within dairy cows over time compared with the visual method assessed weekly. For research applications, the precision and sensitivity were further improved by a proposed refinement of the camera's daily BCS data. Body condition scoring is a valuable tool used to assess the changes in subcutaneous tissue reserves of dairy cows throughout the lactation resulting from changes to management or nutritional interventions. A subjective visual method is typically used to assign a body condition score (BCS) to a cow following a standardized scale, but this method is subject to operator bias and is labor intensive, limiting the number of animals that can be scored and frequency of measurement. An automated three-dimensional body condition scoring camera system is commercially available (DeLaval Body Condition Scoring, BCS DeLaval International AB, Tumba, Sweden), but the reliability of the BCS data for research applications is still unknown, as the system's sensitivity to change in BCS over time within cows has yet to be investigated. The objective of this study was to evaluate the suitability of an automated body condition scoring system for dairy cows for research applications as an alternative to visual body condition scoring. Thirty-two multiparous Holstein-Friesian cows (9 ± 6.8 days in milk) were body condition scored visually by three trained staff weekly and automatically twice each day by the camera for at least 7 consecutive weeks. Measurements were performed in early lactation, when the greatest differences in BCS of a cow over the lactation are normally present, and changes in BCS occur rapidly compared with later stages, allowing for detectable changes in a short timeframe by each method. Two data sets were obtained from the automatic body condition scoring camera: (1) raw daily BCS camera values and (2) a refined data set obtained from the raw daily BCS camera data by fitting a robust smooth loess function to identify and remove outliers. Agreement, precision, and sensitivity properties of the three data sets (visual, raw, and refined camera BCS) were compared in terms of the weekly average for each cow. Sensitivity was estimated as the ratio of response to precision, providing an objective performance criterion for independent comparison of methods. The camera body condition scoring method, using raw or refined camera data, performed better on this criterion compared with the visual method. Sensitivities of the raw BCS camera method, the refined BCS camera method, and the visual BCS method for changes in weekly mean score were 3.6, 6.2, and 1.7, respectively. To detect a change in BCS of an animal, assuming a decline of about 0.2 BCS (1–8 scale) per month, as was observed on average in this experiment, it would take around 44 days with the visual method, 21 days with the raw camera method, or 12 days with the refined camera method. This represents an increased capacity of both camera methods to detect changes in BCS over time compared with the visual method, which improved further when raw camera data were refined as per our proposed method. We recommend the use of the proposed refinement of the camera's daily BCS data for research applications. [ABSTRACT FROM AUTHOR]

Highlights: [•] A novel method for identifying pruning branches in tall spindle apple trees. [•] Pruning rules were defined based on observation of human pruning. [•] These pruning rules were applied to 3D skeletons of apple trees. [•] With optimization of pruning parameters, automatic identification results closely matched desired pruning level. [ABSTRACT FROM AUTHOR]

Detailed 3D plant architectural data have numerous applications in plant science, but many existing approaches for 3D data collection are time-consuming and/or require costly equipment. Recently, there has been rapid growth in the availability of low-cost, 3D cameras and related open source software applications. 3D cameras may provide measurements of key components of plant architecture such as stem diameters and lengths, however, few tests of 3D cameras for the measurement of plant architecture have been conducted. Here, we measured Salix branch segments ranging from 2-13 mm in diameter with an Asus Xtion camera to quantify the limits and accuracy of branch diameter measurement with a 3D camera. By scanning at a variety of distances we also quantified the effect of scanning distance. In addition, we also test the sensitivity of the program KinFu for continuous 3D object scanning and modeling as well as other similar software to accurately record stem diameters and capture plant form (<3 m in height). Given its ability to accurately capture the diameter of branches >6 mm, Asus Xtion may provide a novel method for the collection of 3D data on the branching architecture of woody plants. Improvements in camera measurement accuracy and available software are likely to further improve the utility of 3D cameras for plant sciences in the future. [ABSTRACT FROM AUTHOR]

Mostly, 3D cameras having depth sensing capabilities employ active depth estimation techniques, such as stereo, the triangulation method or time-of-flight. However, these methods are expensive. The cost can be reduced by applying optical passive methods, as they are inexpensive and efficient. In this paper, we suggest the use of one of the passive optical methods named shape from focus (SFF) for 3D cameras. In the proposed scheme, first, an adaptive window is computed through an iterative process using a criterion. Then, the window is divided into four regions. In the next step, the best focused area among the four regions is selected based on variation in the data. The effectiveness of the proposed scheme is validated using image sequences of synthetic and real objects. Comparative analysis based on statistical metrics correlation, mean square error (MSE), universal image quality index (UIQI) and structural similarity (SSIM) shows the effectiveness of the proposed scheme. [ABSTRACT FROM AUTHOR]

Most industrial robots perform a periodically repeating choreography. Our aim is to detect disturbances of such a periodic process by a visual inspection system that can be trained with a minimum of human effort and interaction. We present a solution that monitors the robot with a time-of-flight 3D camera. Our system can be trained using a few unperturbed cycles of the periodic process. More specifically, principal components are used to find a low-dimensional approximation of each frame, and a One-Class Support Vector Machine is used for one-class learning. We propose a novel scheme for automatic parameter tuning, which exploits the fact that successive images of the training class should be close in feature space. We present exemplary results for a miniature robot setup. The proposed strategy does not require prior information on the dimensions of the machine or its maneuvering range. The entire system is appearance-based and hence does not need access to the robot's internal coordinates. [ABSTRACT FROM AUTHOR]

In this paper, we propose an efficient method for 3D model retrieval using a single depth image. Unlike existing algorithms that use a complete 3D model or a user sketch as input queries, a single depth image is used as an input query, which can be captured easily with an off-the-shelf lowcost 3D camera, such as a Kinect camera. 3D models in the database are represented by multiple depth images acquired from adaptively sampled viewpoints. The proposed algorithm can retrieve relevant 3D models while considering local 3D geometric characteristics using a rotation-invariant feature descriptor. The proposed method consists of three steps: preprocessing, multiple depth image based representation (M-DIBR), and description of 3D models, and similarity measurement and comparison. Experimental results demonstrate that the proposed algorithm is convenient to use and its performance is comparable to recent algorithms in terms of retrieval accuracy and speed. [ABSTRACT FROM AUTHOR]

Indirect Time-of-Flight (I-TOF) cameras can be implemented in a number of ways, each with specific characteristics and performances. In this paper a comprehensive analysis of the implementation possibilities is developed in order to model the main performances with a high level of abstraction. After the extraction of the main characteristics for the high-level model, several figures of merit (FoM) are defined with the purpose of obtaining a common metric: noise equivalent distance, correlated and uncorrelated power responsivity, and background light rejection ratio. The obtained FoMs can be employed for the comparison of different implementations of range cameras based on the I-TOF method: specifically, they are applied for several different sensors developed by the authors in order to compare their performances. [ABSTRACT FROM AUTHOR]

A successful application of low-cost 3D cameras in combination with artificial intelligence (AI)-based 3D object detection algorithms to outdoor mobile mapping would offer great potential for numerous mapping, asset inventory, and change detection tasks in the context of smart cities. This paper presents a mobile mapping system mounted on an electric tricycle and a procedure for creating on-street parking statistics, which allow government agencies and policy makers to verify and adjust parking policies in different city districts. Our method combines georeferenced red-green-blue-depth (RGB-D) imagery from two low-cost 3D cameras with state-of-the-art 3D object detection algorithms for extracting and mapping parked vehicles. Our investigations demonstrate the suitability of the latest generation of low-cost 3D cameras for real-world outdoor applications with respect to supported ranges, depth measurement accuracy, and robustness under varying lighting conditions. In an evaluation of suitable algorithms for detecting vehicles in the noisy and often incomplete 3D point clouds from RGB-D cameras, the 3D object detection network PointRCNN, which extends region-based convolutional neural networks (R-CNNs) to 3D point clouds, clearly outperformed all other candidates. The results of a mapping mission with 313 parking spaces show that our method is capable of reliably detecting parked cars with a precision of 100% and a recall of 97%. It can be applied to unslotted and slotted parking and different parking types including parallel, perpendicular, and angle parking. [ABSTRACT FROM AUTHOR]

Depth estimation is an active area of research for 3-dimensional (3D) shape recovery. In this paper, we present a passive depth estimation method. Since the 3-dimensional (3D) cameras currently available are quite expensive, we propose the passive method as a means to decrease the high cost associated with 3D cameras. Our algorithm is based on the Fuzzy-Neuro approach. A Fuzzy Inference System (FIS) is designed and trained using the neural network for the calculation of the depth map. The proposed approximation technique yields good results when it is tested with several 3D objects. [ABSTRACT FROM AUTHOR]

In this paper, the scanning response of the photocurrent emitted by a large area avalanche photodiode (APD) is studied for a 3D laser camera. This 3D camera is based on a phase-shift laser range-finder to measure distance from 1 to 20 m. To obtain a large field of view of the optical head, a large area APD working as an optoelectronic mixer is used. Photocurrent response versus light spot position above the APD active area is analysed for high frequency measurements. Optoelectronic mixing permits to measure the scanning response phase of the internal photoelectric current. Moreover, it is demonstrated that the signal phase depends on the photoelectric gain. Signal-to-noise ratio and distance measurement error for the 3D camera are then discussed. [Copyright &y& Elsevier]

Detecting characteristics of 3D scenes is considered one of the biggest challenges for visually impaired people. This ability is nonetheless crucial for orientation and navigation in the natural environment. Although there are several Electronic Travel Aids aiming at enhancing orientation and mobility for the blind, only a few of them combine passing both 2D and 3D information, including colour. Moreover, existing devices either focus on a small part of an image or allow interpretation of a mere few points in the field of view. Here, we propose a concept of visual echolocation with integrated colour sonification as an extension of Colorophone—an assistive device for visually impaired people. The concept aims at mimicking the process of echolocation and thus provides 2D, 3D and additionally colour information of the whole scene. Even though the final implementation will be realised by a 3D camera, it is first simulated, as a proof of concept, by using VIRCO—a Virtual Reality training and evaluation system for Colorophone. The first experiments showed that it is possible to sonify colour and distance of the whole scene, which opens up a possibility to implement the developed algorithm on a hardware-based stereo camera platform. An introductory user evaluation of the system has been conducted in order to assess the effectiveness of the proposed solution for perceiving distance, position and colour of the objects placed in Virtual Reality. [ABSTRACT FROM AUTHOR]

The Body Condition Score (BCS) for cows indicates their energy reserves, the scoring for which ranges from very thin to overweight. These measurements are especially useful during calving, as well as early lactation. Achieving a correct BCS helps avoid calving difficulties, losses and other health problems. Although BCS can be rated by experts, it is time-consuming and often inconsistent when performed by different experts. Therefore, the aim of our system is to develop a computerized system to reduce inconsistencies and to provide a time-saving solution. In our proposed system, the automatic body condition scoring system is introduced by using a 3D camera, image processing techniques and regression models. The experimental data were collected on a rotary parlor milking station on a large-scale dairy farm in Japan. The system includes an application platform for automatic image selection as a primary step, which was developed for smart monitoring of individual cows on large-scale farms. Moreover, two analytical models are proposed in two regions of interest (ROI) by extracting 3D surface roughness parameters. By applying the extracted parameters in mathematical equations, the BCS is automatically evaluated based on measurements of model accuracy, with one of the two models achieving a mean absolute percentage error (MAPE) of 3.9%, and a mean absolute error (MAE) of 0.13. [ABSTRACT FROM AUTHOR]

The educational value of stereoscopic imaging in neurosurgical training has increasingly been appreciated and its use increased during the last decade. We describe a technique that we developed to acquire and reproduce intra-operative stereoscopic images. [ABSTRACT FROM AUTHOR]