scholarly journals Semi-Automatic Calibration Method for a Bed-Monitoring System Using Infrared Image Depth Sensors

Sensors ◽  
2019 ◽  
Vol 19 (20) ◽  
pp. 4581 ◽  
Author(s):  
Komagata ◽  
Kakinuma ◽  
Ishikawa ◽  
Shinoda ◽  
Kobayashi
Keyword(s):  
Monitoring System ◽  
Infrared Image ◽  
Calibration Method ◽  
Spatial Position ◽  
Depth Sensor ◽  
Depth Sensors ◽  
Care Facilities ◽  
Set Up ◽  
Automated Methods ◽  
Image Depth

With the aging of society, the number of fall accidents has increased in hospitals and care facilities, and some accidents have happened around beds. To help prevent accidents, mats and clip sensors have been used in these facilities but they can be invasive, and their purpose may be misinterpreted. In recent years, research has been conducted using an infrared-image depth sensor as a bed-monitoring system for detecting a patient getting up, exiting the bed, and/or falling; however, some manual calibration was required initially to set up the sensor in each instance. We propose a bed-monitoring system that retains the infrared-image depth sensors but uses semi-automatic rather than manual calibration in each situation where it is applied. Our automated methods robustly calculate the bed region, surrounding floor, sensor location, and attitude, and can recognize the spatial position of the patient even when the sensor is attached but unconstrained. Also, we propose a means to reconfigure the spatial position considering occlusion by parts of the bed and also accounting for the gravity center of the patient’s body. Experimental results of multi-view calibration and motion simulation showed that our methods were effective for recognition of the spatial position of the patient.

scholarly journals Innovative passive reinforcements for the gradual stabilization of a landslide according with the observational method

Landslides ◽  
2021 ◽  
Author(s):  
Lorenzo Brezzi ◽  
Alberto Bisson ◽  
Davide Pasa ◽  
Simonetta Cola
Keyword(s):  
Monitoring System ◽  
Low Cost ◽  
Economic Losses ◽  
Fe Model ◽  
Site Conditions ◽  
Observational Method ◽  
Rainy Period ◽  
Sustainable Solutions ◽  
Before And After ◽  
Set Up

AbstractA large number of landslides occur in North-Eastern Italy during every rainy period due to the particular hydrogeological conditions of this area. Even if there are no casualties, the economic losses are often significant, and municipalities frequently do not have sufficient financial resources to repair the damage and stabilize all the unstable slopes. In this regard, the research for more economically sustainable solutions is a crucial challenge. Floating composite anchors are an innovative and low-cost technique set up for slope stabilization: it consists in the use of passive sub-horizontal reinforcements, obtained by coupling a traditional self-drilling bar with some tendons cemented inside it. This work concerns the application of this technique according to the observational method described within the Italian and European technical codes and mainly recommended for the design of geotechnical works, especially when performed in highly uncertain site conditions. The observational method prescribes designing an intervention and, at the same time, using a monitoring system in order to correct and adapt the project during realization of the works on the basis of new data acquired while on site. The case study is the landslide of Cischele, a medium landslide which occurred in 2010 after an exceptional heavy rainy period. In 2015, some floating composite anchors were installed to slow down the movement, even if, due to a limited budget, they were not enough to ensure the complete stabilization of the slope. Thanks to a monitoring system installed in the meantime, it is now possible to have a comparison between the site conditions before and after the intervention. This allows the evaluation of benefits achieved with the reinforcements and, at the same time, the assessment of additional improvements. Two stabilization scenarios are studied through an FE model: the first includes the stabilization system built in 2015, while the second evaluates a new solution proposed to further increase the slope stability.

scholarly journals BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2144
Author(s):  
Stefan Reitmann ◽  
Lorenzo Neumann ◽  
Bernhard Jung
Keyword(s):  
Point Clouds ◽  
Training Data ◽  
Sensor Data ◽  
Generation Process ◽  
Data Generation ◽  
Depth Sensor ◽  
Depth Sensing ◽  
Depth Sensors ◽  
3D Point Clouds ◽  
Wide Range

Common Machine-Learning (ML) approaches for scene classification require a large amount of training data. However, for classification of depth sensor data, in contrast to image data, relatively few databases are publicly available and manual generation of semantically labeled 3D point clouds is an even more time-consuming task. To simplify the training data generation process for a wide range of domains, we have developed the BLAINDER add-on package for the open-source 3D modeling software Blender, which enables a largely automated generation of semantically annotated point-cloud data in virtual 3D environments. In this paper, we focus on classical depth-sensing techniques Light Detection and Ranging (LiDAR) and Sound Navigation and Ranging (Sonar). Within the BLAINDER add-on, different depth sensors can be loaded from presets, customized sensors can be implemented and different environmental conditions (e.g., influence of rain, dust) can be simulated. The semantically labeled data can be exported to various 2D and 3D formats and are thus optimized for different ML applications and visualizations. In addition, semantically labeled images can be exported using the rendering functionalities of Blender.

Using transfer learning for diabetic retinopathy stage classification

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Enas M.F. El Houby
Keyword(s):  
Diabetic Retinopathy ◽  
Transfer Learning ◽  
Grade Level ◽  
Design Methodology ◽  
Content Type ◽  
Stage Classification ◽  
Set Up ◽  
Retinal Fundus ◽  
Automated Methods

PurposeDiabetic retinopathy (DR) is one of the dangerous complications of diabetes. Its grade level must be tracked to manage its progress and to start the appropriate decision for treatment in time. Effective automated methods for the detection of DR and the classification of its severity stage are necessary to reduce the burden on ophthalmologists and diagnostic contradictions among manual readers.Design/methodology/approachIn this research, convolutional neural network (CNN) was used based on colored retinal fundus images for the detection of DR and classification of its stages. CNN can recognize sophisticated features on the retina and provides an automatic diagnosis. The pre-trained VGG-16 CNN model was applied using a transfer learning (TL) approach to utilize the already learned parameters in the detection.FindingsBy conducting different experiments set up with different severity groupings, the achieved results are promising. The best-achieved accuracies for 2-class, 3-class, 4-class and 5-class classifications are 86.5, 80.5, 63.5 and 73.7, respectively.Originality/valueIn this research, VGG-16 was used to detect and classify DR stages using the TL approach. Different combinations of classes were used in the classification of DR severity stages to illustrate the ability of the model to differentiate between the classes and verify the effect of these changes on the performance of the model.

scholarly journals Graph Cut-Based Human Body Segmentation in Color Images Using Skeleton Information from the Depth Sensor

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 393 ◽  
Author(s):  
Jonha Lee ◽  
Dong-Wook Kim ◽  
Chee Won ◽  
Seung-Won Jung
Keyword(s):  
Human Body ◽  
Color Image ◽  
Depth Image ◽  
Body Region ◽  
Reasonable Accuracy ◽  
Depth Sensor ◽  
Complicated Shape ◽  
Depth Sensors ◽  
Body Segmentation ◽  
Human Body Segmentation

Segmentation of human bodies in images is useful for a variety of applications, including background substitution, human activity recognition, security, and video surveillance applications. However, human body segmentation has been a challenging problem, due to the complicated shape and motion of a non-rigid human body. Meanwhile, depth sensors with advanced pattern recognition algorithms provide human body skeletons in real time with reasonable accuracy. In this study, we propose an algorithm that projects the human body skeleton from a depth image to a color image, where the human body region is segmented in the color image by using the projected skeleton as a segmentation cue. Experimental results using the Kinect sensor demonstrate that the proposed method provides high quality segmentation results and outperforms the conventional methods.

scholarly journals Intra-catchment variability of surface saturation – insights from physically based simulations in comparison with biweekly thermal infrared image observations

2020 ◽  
Vol 24 (3) ◽  
pp. 1393-1413 ◽  
Author(s):  
Barbara Glaser ◽  
Marta Antonelli ◽  
Luisa Hopp ◽  
Julian Klaus
Keyword(s):  
Infrared Image ◽  
Thermal Infrared ◽  
Riparian Areas ◽  
Physically Based ◽  
Simulated Surface ◽  
Surface Saturation ◽  
Spatio Temporal ◽  
Combined Simulation ◽  
Set Up ◽  
Topographic Depressions

Abstract. In this study, we explored the spatio-temporal variability of surface saturation within a forested headwater catchment using a combined simulation–observation approach. We simulated the occurrence of surface saturation in the Weierbach catchment (Luxembourg) with the physically based model HydroGeoSphere. We confronted the simulation with thermal infrared images that we acquired during a 2-year mapping campaign for seven distinct riparian areas with weekly to biweekly recurrence frequency. Observations and simulations showed similar saturation dynamics across the catchment. The observed and simulated relation of surface saturation to catchment discharge resembled a power law relationship for all investigated riparian areas but varied to a similar extent, as previously observed between catchments of different morphological and topographical characteristics. The observed spatial patterns and frequencies of surface saturation varied between and within the investigated areas and the model reproduced these spatial variations well. The good performance of the simulation suggested that surface saturation in the Weierbach catchment is largely controlled by exfiltration of groundwater into local topographic depressions. However, the simulated surface saturation contracted faster than observed, the simulated saturation dynamics were less variable between the investigated areas than observed, and the match of simulated and observed saturation patterns was not equally good in all investigated riparian areas. These mismatches between observations and simulation highlight that the intra-catchment variability of surface saturation must also result from factors that were not considered in the model set-up, such as differing subsurface structures or a differing persistence of surface saturation due to local morphological features like perennial springs.

scholarly journals Approximate Depth Shape Reconstruction for RGB-D Images Captured from HMDs for Mixed Reality Applications

2020 ◽  
Vol 6 (3) ◽  
pp. 11
Author(s):  
Naoyuki Awano
Keyword(s):  
Mixed Reality ◽  
Signal To Noise Ratio ◽  
Low Cost ◽  
Real Space ◽  
Shape Reconstruction ◽  
Human Vision ◽  
Depth Image ◽  
Depth Sensor ◽  
Depth Sensors ◽  
Object Shapes

Depth sensors are important in several fields to recognize real space. However, there are cases where most depth values in a depth image captured by a sensor are constrained because the depths of distal objects are not always captured. This often occurs when a low-cost depth sensor or structured-light depth sensor is used. This also occurs frequently in applications where depth sensors are used to replicate human vision, e.g., when using the sensors in head-mounted displays (HMDs). One ideal inpainting (repair or restoration) approach for depth images with large missing areas, such as partial foreground depths, is to inpaint only the foreground; however, conventional inpainting studies have attempted to inpaint entire images. Thus, under the assumption of an HMD-mounted depth sensor, we propose a method to inpaint partially and reconstruct an RGB-D depth image to preserve foreground shapes. The proposed method is comprised of a smoothing process for noise reduction, filling defects in the foreground area, and refining the filled depths. Experimental results demonstrate that the inpainted results produced using the proposed method preserve object shapes in the foreground area with accurate results of the inpainted area with respect to the real depth with the peak signal-to-noise ratio metric.

SU-E-T-258: Development of a New Patient Set-Up Monitoring System Using Force Sensing Resistor (FSR) Sensor for the Radiation Therapy

2015 ◽  
Vol 42 (6Part16) ◽  
pp. 3392-3392
Author(s):  
M Cho ◽  
T Kim ◽  
S Kang ◽  
D Kim ◽  
K Kim ◽  
...  
Keyword(s):  
Radiation Therapy ◽  
Monitoring System ◽  
Force Sensing ◽  
Set Up

scholarly journals Finger Gesture Spotting from Long Sequences Based on Multi-Stream Recurrent Neural Networks

Sensors ◽  
2020 ◽  
Vol 20 (2) ◽  
pp. 528 ◽  
Author(s):  
Gibran Benitez-Garcia ◽  
Muhammad Haris ◽  
Yoshiyuki Tsuda ◽  
Norimichi Ukita
Keyword(s):  
Neural Network ◽  
Semantic Information ◽  
State Of The Art ◽  
Spatial Location ◽  
Depth Sensor ◽  
Stream Network ◽  
Neural Architecture ◽  
Network Merging ◽  
Automated Methods ◽  
Gesture Spotting

Gesture spotting is an essential task for recognizing finger gestures used to control in-car touchless interfaces. Automated methods to achieve this task require to detect video segments where gestures are observed, to discard natural behaviors of users’ hands that may look as target gestures, and be able to work online. In this paper, we address these challenges with a recurrent neural architecture for online finger gesture spotting. We propose a multi-stream network merging hand and hand-location features, which help to discriminate target gestures from natural movements of the hand, since these may not happen in the same 3D spatial location. Our multi-stream recurrent neural network (RNN) recurrently learns semantic information, allowing to spot gestures online in long untrimmed video sequences. In order to validate our method, we collect a finger gesture dataset in an in-vehicle scenario of an autonomous car. 226 videos with more than 2100 continuous instances were captured with a depth sensor. On this dataset, our gesture spotting approach outperforms state-of-the-art methods with an improvement of about 10% and 15% of recall and precision, respectively. Furthermore, we demonstrated that by combining with an existing gesture classifier (a 3D Convolutional Neural Network), our proposal achieves better performance than previous hand gesture recognition methods.

scholarly journals Time response of a landslide to meteorological events

2006 ◽  
Vol 6 (2) ◽  
pp. 179-184 ◽  
Author(s):  
G. Lollino ◽  
M. Arattano ◽  
P. Allasia ◽  
D. Giordan
Keyword(s):  
Ground Water ◽  
Monitoring System ◽  
Present Report ◽  
Time Lag ◽  
Slope Movements ◽  
Landslide Body ◽  
Italian Apennines ◽  
Complex Monitoring ◽  
Set Up ◽  
Year 2000

Abstract. A landslide affecting two small villages located on the Northwestern Italian Apennines has been investigated since the year 2000 through the use of different equipment. A complex monitoring system has been installed in the area. The system includes several inclinometers, piezometers and a raingauge. An Automatic Inclinometric System (AIS) has been also installed that automatically performs measurements, twice a day, along the entire length of a pipe that is 45 m deep. This monitoring system has been set up to identify a methodology that allowed to deal with landslides, trying to predict their behaviour beforehand for warning purposes. Previous researches carried out in the same area for a period of about 7 months, in the year 2000, have allowed to identify a correlation between deep slope movements and rainfalls. In particular, it has been possible to determine the time lag needed for a rainfall peak to produce a corresponding peak of the landslide movements; this time lag was of 9 days. This result was possible because the AIS allows to obtain, as mentioned, daily inclinometric measurements that can be correlated with the recorded rainfalls. In the present report we have extended the analysis of the correlation between deep slope movements and rainfalls to a greater period of observation (2 years) to verify over this period the consistency of the time lag mentioned above. The time lag previously found has been confirmed. We have also examined the possibility to extend to the entire landslide body the correlation that has been found locally, analyzing the results of the remaining inclinometric tubes with traditional reading installed on the landslide and comparing them with the results of the AIS. The output of the tubes equipped with piezometric cells has also been analyzed. The relations existing among rainfalls, ground water level oscillations and the related slope movements have been explored

Sign in / Sign up

Export Citation Format

Share Document