Performance of a low-cost field re-configurable real-time GPS/INS integrated system in urban navigation

In order to facilitate applications such as environment detection or disaster monitoring, developing a quickly and low cost system to collect near real time spatial information is very important. Such a rapid spatial information collection capability has become an emerging trend in the technology of remote sensing and mapping application. In this study, a fixed-wing UAV based spatial information acquisition platform is developed and evaluated. The proposed UAV based platform has a direct georeferencing module including an low cost INS/GPS integrated system, low cost digital camera as well as other general UAV modules including immediately video monitoring communication system. This direct georeferencing module is able to provide differential GPS processing with single frequency carrier phase measurements to obtain sufficient positioning accuracy. All those necessary calibration procedures including interior orientation parameters, the lever arm and boresight angle are implemented. In addition, a flight test is performed to verify the positioning accuracy in direct georeferencing mode without using any ground control point that is required for most of current UAV based photogrammetric platforms. In other word, this is one of the pilot studies concerning direct georeferenced based UAV photogrammetric platform. The preliminary results in term of positioning accuracy in direct georeferenced mode without using any GCP illustrate horizontal positioning accuracies in x and y axes are both less than 20 meters, respectively. On the contrary, the positioning accuracy of z axis is less than 50 meters with 600 meters flight height above ground. Such accuracy is good for near real time disaster relief. Therefore, it is a relatively safe and cheap platform to collect critical spatial information for urgent response such as disaster relief and assessment applications where ground control points are not available.

Download Full-text

An Integrated System for Real-Time Water Monitoring Based on Low Cost Unmanned Surface Vehicles

2019 IEEE Sensors Applications Symposium (SAS) ◽

10.1109/sas.2019.8706040 ◽

2019 ◽

Cited By ~ 1

Author(s):

Simone Garuglieri ◽

Dario Madeo ◽

Alessandro Pozzebon ◽

Roberto Zingone ◽

Chiara Mocenni ◽

...

Keyword(s):

Real Time ◽

Low Cost ◽

Integrated System ◽

Water Monitoring ◽

Unmanned Surface Vehicles

Download Full-text

Smartphone aided real-time blood vein detection system

Bulletin of Electrical Engineering and Informatics ◽

10.11591/eei.v8i3.1514 ◽

2019 ◽

Vol 8 (3) ◽

pp. 1096-1107

Author(s):

Kazi Istiaque Ahmed ◽

Mohamed Hadi Habaebi ◽

Md. Rafiqul Islam

Keyword(s):

Real Time ◽

Detection System ◽

Low Cost ◽

Histogram Equalization ◽

Mobile App ◽

Integrated System ◽

Frame Rate ◽

Infrared Light ◽

Emergency Rooms ◽

Light Spectrum

This paper aims to develop a real-time integrated system for the detection of the blood vein utilizing an Android Mobile App. The system is intended to be a low cost solution for medical teams at clinics, emergency rooms and hosptials. The system reduces the enjuries incurred due to inaccuracies during the process of frequent needle injection when blood vein is not visible during patient’s skin inspection. Illuminated infrared light in the blood cells of the vein is absorbed due to the manifestation of the Haemoglobin in blood and the IR non-blocking camera can capture the vein patterns in the IR light spectrum. Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm was used to enhance the pattern of the vein in the Android application developed using OpenCV3. Developed system can detect the veins up to 7mm underneath of human skin in real time with a frame rate of 25fps. This is a far better improvement than commercial systems that can detect veins only below 10mm underneath the skin. Moreover, this system not only focused on needle infusion but also it can be used to indicate the place of bleeding for the clots from the human body strokes, etc. in the upper layer of skin. It can also be used to detect measure liquids in encapsulated in confined dark bottles, for example, liquid chemical pouring into the bottles in the chemical companies, liquid medicine pouring to bottles, etc. The system can be further developed to detect skin infection and other dermatological diseases underneath the skin.

Download Full-text

LOW COST REAL TIME ROCKET TELEMETRY SYSTEM DESIGN

10.26678/abcm.cobem2019.cob2019-1585 ◽

2019 ◽

Author(s):

Gabriel de Almeida Souza ◽

Larissa Barbosa ◽

Glênio Ramalho ◽

Alexandre Zuquete Guarato

Keyword(s):

System Design ◽

Real Time ◽

Low Cost ◽

Telemetry System

Download Full-text

Low-Cost High-Speed Techniques for Real-Time Simulation of Power Electronic Systems

10.21236/ada485330 ◽

2007 ◽

Author(s):

R. E. Crosbie ◽

J. J. Zenor ◽

R. Bednar ◽

D. Word ◽

N. G. Hingorani

Keyword(s):

Real Time ◽

High Speed ◽

Low Cost ◽

Electronic Systems ◽

Power Electronic ◽

Real Time Simulation ◽

Time Simulation

Download Full-text

Application of Deep Learning in Integrated Pest Management: A Real-Time System for Detection and Diagnosis of Oilseed Rape Pests

Mobile Information Systems ◽

10.1155/2019/4570808 ◽

2019 ◽

Vol 2019 ◽

pp. 1-14 ◽

Cited By ~ 2

Author(s):

Yong He ◽

Hong Zeng ◽

Yangyang Fan ◽

Shuaisheng Ji ◽

Jianjian Wu

Keyword(s):

Deep Learning ◽

Integrated Pest Management ◽

Pest Management ◽

Real Time ◽

Oilseed Rape ◽

Data Augmentation ◽

Low Cost ◽

Response Speed ◽

Original Model ◽

Real Time System

In this paper, we proposed an approach to detect oilseed rape pests based on deep learning, which improves the mean average precision (mAP) to 77.14%; the result increased by 9.7% with the original model. We adopt this model to mobile platform to let every farmer able to use this program, which will diagnose pests in real time and provide suggestions on pest controlling. We designed an oilseed rape pest imaging database with 12 typical oilseed rape pests and compared the performance of five models, SSD w/Inception is chosen as the optimal model. Moreover, for the purpose of the high mAP, we have used data augmentation (DA) and added a dropout layer. The experiments are performed on the Android application we developed, and the result shows that our approach surpasses the original model obviously and is helpful for integrated pest management. This application has improved environmental adaptability, response speed, and accuracy by contrast with the past works and has the advantage of low cost and simple operation, which are suitable for the pest monitoring mission of drones and Internet of Things (IoT).

Download Full-text

Real-Time Low-Cost Drift Compensation for Chemical Sensors Using a Deep Neural Network with Hadamard Transform and Additive Layers

IEEE Sensors Journal ◽

10.1109/jsen.2021.3084220 ◽

2021 ◽

pp. 1-1

Author(s):

Diaa Badawi ◽

Agamyrat Agambayev ◽

Sule Ozev ◽

A. Enis Cetin

Keyword(s):

Neural Network ◽

Real Time ◽

Chemical Sensors ◽

Deep Neural Network ◽

Low Cost ◽

Hadamard Transform ◽

Drift Compensation

Download Full-text

A Low-Cost, Mobile Real-Time Kinematic Geolocation Service for Engineering and Research Applications

HardwareX ◽

10.1016/j.ohx.2021.e00203 ◽

2021 ◽

pp. e00203

Author(s):

André Broekman ◽

Petrus Johannes Gräbe

Keyword(s):

Real Time ◽

Low Cost ◽

Real Time Kinematic

Download Full-text

Low-Cost Embedded System Using Convolutional Neural Networks-Based Spatiotemporal Feature Map for Real-Time Human Action Recognition

Applied Sciences ◽

10.3390/app11114940 ◽

2021 ◽

Vol 11 (11) ◽

pp. 4940

Author(s):

Jinsoo Kim ◽

Jeongho Cho

Keyword(s):

Embedded System ◽

Real Time ◽

Action Recognition ◽

Processing Speed ◽

Recognition Accuracy ◽

Low Cost ◽

Human Action Recognition ◽

Human Action ◽

Video Data ◽

Feature Maps

The field of research related to video data has difficulty in extracting not only spatial but also temporal features and human action recognition (HAR) is a representative field of research that applies convolutional neural network (CNN) to video data. The performance for action recognition has improved, but owing to the complexity of the model, some still limitations to operation in real-time persist. Therefore, a lightweight CNN-based single-stream HAR model that can operate in real-time is proposed. The proposed model extracts spatial feature maps by applying CNN to the images that develop the video and uses the frame change rate of sequential images as time information. Spatial feature maps are weighted-averaged by frame change, transformed into spatiotemporal features, and input into multilayer perceptrons, which have a relatively lower complexity than other HAR models; thus, our method has high utility in a single embedded system connected to CCTV. The results of evaluating action recognition accuracy and data processing speed through challenging action recognition benchmark UCF-101 showed higher action recognition accuracy than the HAR model using long short-term memory with a small amount of video frames and confirmed the real-time operational possibility through fast data processing speed. In addition, the performance of the proposed weighted mean-based HAR model was verified by testing it in Jetson NANO to confirm the possibility of using it in low-cost GPU-based embedded systems.

Download Full-text