scholarly journals LOW COST EMBEDDED STEREO SYSTEM FOR UNDERWATER SURVEYS

2017 ◽  
Vol XLII-2/W8 ◽  
pp. 179-186
Author(s):  
M. M. Nawaf ◽  
J.-M. Boï ◽  
D. Merad ◽  
J.-P. Royer ◽  
P. Drap
Keyword(s):  
Embedded System ◽  
Real Time ◽  
Low Cost ◽  
Visual Odometry ◽  
Movement Speed ◽  
Underwater Imaging ◽  
Lighting Conditions ◽  
Computational Resources ◽  
Processing Techniques

This paper provides details of both hardware and software conception and realization of a hand-held stereo embedded system for underwater imaging. The designed system can run most image processing techniques smoothly in real-time. The developed functions provide direct visual feedback on the quality of the taken images which helps taking appropriate actions accordingly in terms of movement speed and lighting conditions. The proposed functionalities can be easily customized or upgraded whereas new functions can be easily added thanks to the available supported libraries. Furthermore, by connecting the designed system to a more powerful computer, a real-time visual odometry can run on the captured images to have live navigation and site coverage map. We use a visual odometry method adapted to low computational resources systems and long autonomy. The system is tested in a real context and showed its robustness and promising further perspectives.

scholarly journals Fast Visual Odometry for a Low-Cost Underwater Embedded Stereo System †

Sensors ◽  
2018 ◽  
Vol 18 (7) ◽  
pp. 2313 ◽  
Author(s):  
Mohamad Nawaf ◽  
Djamal Merad ◽  
Jean-Philip Royer ◽  
Jean-Marc Boï ◽  
Mauro Saccone ◽  
...  
Keyword(s):  
Embedded System ◽  
Real Time ◽  
Stereo Matching ◽  
Low Cost ◽  
Visual Odometry ◽  
Stereo Image ◽  
Movement Speed ◽  
Optimization Approach ◽  
Underwater Imaging ◽  
Fast Processing

This paper provides details of hardware and software conception and realization of a stereo embedded system for underwater imaging. The system provides several functions that facilitate underwater surveys and run smoothly in real-time. A first post-image acquisition module provides direct visual feedback on the quality of the taken images which helps appropriate actions to be taken regarding movement speed and lighting conditions. Our main contribution is a light visual odometry method adapted to the underwater context. The proposed method uses the captured stereo image stream to provide real-time navigation and a site coverage map which is necessary to conduct a complete underwater survey. The visual odometry uses a stochastic pose representation and semi-global optimization approach to handle large sites and provides long-term autonomy, whereas a novel stereo matching approach adapted to underwater imaging and system attached lighting allows fast processing and suitability to low computational resource systems. The system is tested in a real context and shows its robustness and promising future potential.

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

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.

scholarly journals REAL-TIME ENVIRONMENTAL SENSORS TO IMPROVE HEALTH IN THE SENSING CITY

2016 ◽  
Vol XLI-B2 ◽  
pp. 729-733 ◽  
Author(s):  
L. Marek ◽  
M. Campbell ◽  
M. Epton ◽  
M. Storer ◽  
S. Kingham
Keyword(s):  
Quality Of Life ◽  
Air Pollution ◽  
Air Quality ◽  
Real Time ◽  
Low Cost ◽  
Monitoring Network ◽  
Environmental Data ◽  
Chronic Obstructive ◽  
Actual Usage

The opportunity of an emerging smart city in post-disaster Christchurch has been explored as a way to improve the quality of life of people suffering Chronic Obstructive Pulmonary Disease (COPD), which is a progressive disease that affects respiratory function. It affects 1 in 15 New Zealanders and is the 4th largest cause of death, with significant costs to the health system. While, cigarette smoking is the leading cause of COPD, long-term exposure to other lung irritants, such as air pollution, chemical fumes, or dust can also cause and exacerbate it. Currently, we do know little what happens to the patients with COPD after they leave a doctor’s care. By learning more about patients’ movements in space and time, we can better understand the impacts of both the environment and personal mobility on the disease. This research is studying patients with COPD by using GPS-enabled smartphones, combined with the data about their spatiotemporal movements and information about their actual usage of medication in near real-time. We measure environmental data in the city, including air pollution, humidity and temperature and how this may subsequently be associated with COPD symptoms. In addition to the existing air quality monitoring network, to improve the spatial scale of our analysis, we deployed a series of low-cost Internet of Things (IoT) air quality sensors as well. The study demonstrates how health devices, smartphones and IoT sensors are becoming a part of a new health data ecosystem and how their usage could provide information about high-risk health hotspots, which, in the longer term, could lead to improvement in the quality of life for patients with COPD.

scholarly journals ZARATAMAP: Noise Characterization in the Scope of a Smart City through a Low Cost and Mobile Electronic Embedded System

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1707
Author(s):  
Unai Hernandez-Jayo ◽  
Amaia Goñi
Keyword(s):  
Embedded System ◽  
Low Cost ◽  
Noise Pollution ◽  
Mobile Node ◽  
Machine Learning Techniques ◽  
Potential Harm ◽  
Sources Of Pollution ◽  
Learning Techniques ◽  
Noise Characterization

Like other sources of pollution, noise is considered to be one of the main concerns of citizens, due to its invisibility and the potential harm it can cause. Noise pollution could be considered as one of the biggest quality-of-life concerns for urban residents in big cities, mainly due to the high levels of noise to which they may be exposed. Such levels have proven effects on health, such as: sleep disruption, hypertension, heart disease, and hearing loss. In a scenario where the number of people concentrated in cities is increasing, tools are needed to quantify, monitor, characterize, and quantify noise levels. This paper presents the ZARATAMAP project, which combines machine learning techniques with a geo-sensing application so that the authorities can have as much information as possible, using a low-cost embedded and mobile node, that is easy to deploy, develop, and use.

scholarly journals Artificial vision system for object classification in real time using Raspberry Pi and a Web camera

2021 ◽  
pp. 20-25
Author(s):  
Tomás Serrano-Ramírez ◽  
Ninfa del Carmen Lozano-Rincón ◽  
Arturo Mandujano-Nava ◽  
Yosafat Jetsemaní Sámano-Flores
Keyword(s):  
Embedded System ◽  
Real Time ◽  
Vision System ◽  
Low Cost ◽  
Artificial Vision ◽  
Maintenance Cost ◽  
Raspberry Pi ◽  
Smart Cameras ◽  
Suggested Technique ◽  
Web Camera

Computer vision systems are an essential part in industrial automation tasks such as: identification, selection, measurement, defect detection and quality control in parts and components. There are smart cameras used to perform tasks, however, their high acquisition and maintenance cost is restrictive. In this work, a novel low-cost artificial vision system is proposed for classifying objects in real time, using the Raspberry Pi 3B + embedded system, a Web camera and the Open CV artificial vision library. The suggested technique comprises the training of a supervised classification system of the Haar Cascade type, with image banks of the object to be recognized, subsequently generating a predictive model which is put to the test with real-time detection, as well as the calculation for the prediction error. This seeks to build a powerful vision system, affordable and also developed using free software.

scholarly journals ZigBee-Based Telemetry System

2010 ◽  
Vol 7 (2) ◽  
pp. 32 ◽  
Author(s):  
L. Khriji ◽  
F. Touati ◽  
N. Hamza
Keyword(s):  
Real Time ◽  
Mobile Device ◽  
Low Cost ◽  
Base Station ◽  
The Body ◽  
Telemetry System ◽  
Real Time Monitoring ◽  
Digital Convergence ◽  
Machine Interface

 Nowadays, there is a significant improvement in technology regarding healthcare. Real-time monitoring systems improve the quality of life of patients as well as the performance of hospitals and healthcare centers. In this paper, we present an implementation of a designed framework of a telemetry system using ZigBee technology for automatic and real-time monitoring of Biomedical signals. These signals are collected and processed using 2-tiered subsystems. The first subsystem is the mobile device which is carried on the body and runs a number of biosensors. The second subsystem performs further processing by a local base station using the raw data which is transmitted on-request by the mobile device. The processed data as well as its analysis are then continuously monitored and diagnosed through a human-machine interface. The system should possess low power consumption, low cost and advanced configuration possibilities. This paper accelerates the digital convergence age through continual research and development of technologies related to healthcare. 

Implementation of UMTS Protocol CC Sublayer Based on WinCE Embedded System

2011 ◽  
Vol 130-134 ◽  
pp. 2973-2976
Author(s):  
Lin Gao ◽  
Jing Gang Lv
Keyword(s):  
Embedded System ◽  
Real Time ◽  
Message Queue ◽  
State Transfer ◽  
Hardware Resource ◽  
The Way

In the paper, a plan based on WinCE is proposed to implement the UMTS CC protocol in the circumstance of system restricted by hardware resource. In the plan, we create call connection (CC) thread, which implements state transfer according to primitives. In order to realize the communication of primitives withmessages, the paper applies the way of WinCE message queue, with WinCE memory managing in a dynamic way which can increase the efficiency of memory effectively. In programming, mutex is applied so as to construct and synchronize the threads. Also, function pointer array is used in realizing FSM, which can make programming code more efficient. In the paper, the principle of WinCE is discussed, and also the key code in realization is analyzed. The test proves that the design has the quality of programming efficiently with good real time ability.

A method for real-time error detection in low-cost environmental sensors data

2019 ◽  
Vol 8 (4) ◽  
pp. 338-350
Author(s):  
Mauricio Loyola
Keyword(s):  
Real Time ◽  
Error Detection ◽  
Measurement Errors ◽  
Low Cost ◽  
Detection Algorithm ◽  
Environmental Sensors ◽  
Content Type ◽  
Building Monitoring ◽  
Learning Techniques

Purpose The purpose of this paper is to propose a simple, fast, and effective method for detecting measurement errors in data collected with low-cost environmental sensors typically used in building monitoring, evaluation, and automation applications. Design/methodology/approach The method combines two unsupervised learning techniques: a distance-based anomaly detection algorithm analyzing temporal patterns in data, and a density-based algorithm comparing data across different spatially related sensors. Findings Results of tests using 60,000 observations of temperature and humidity collected from 20 sensors during three weeks show that the method effectively identified measurement errors and was not affected by valid unusual events. Precision, recall, and accuracy were 0.999 or higher for all cases tested. Originality/value The method is simple to implement, computationally inexpensive, and fast enough to be used in real-time with modest open-source microprocessors and a wide variety of environmental sensors. It is a robust and convenient approach for overcoming the hardware constraints of low-cost sensors, allowing users to improve the quality of collected data at almost no additional cost and effort.

scholarly journals Network-Oriented Real-Time Embedded System Considering Synchronous Joint Space Motion for an Omnidirectional Mobile Robot

Electronics ◽  
2019 ◽  
Vol 8 (3) ◽  
pp. 317 ◽  
Author(s):  
Raimarius Delgado ◽  
Byoung Choi
Keyword(s):  
Mobile Robot ◽  
Embedded System ◽  
Real Time ◽  
Low Cost ◽  
Joint Space ◽  
Geometric Constraints ◽  
Real Time Control ◽  
Synchronization Mechanism ◽  
Omnidirectional Mobile Robot ◽  
Time Control

This paper proposes a real-time embedded system for joint space control of omnidirectional mobile robots. Actuators driving an omnidirectional mobile robot are connected in a line topology which requires synchronization to move simultaneously in translation and rotation. We employ EtherCAT, a real-time Ethernet network, to control servo controllers for the mobile robot. The first part of this study focuses on the design of a low-cost embedded system utilizing an open-source EtherCAT master. Although satisfying real-time constraints is critical, a desired trajectory on the center of the mobile robot should be decomposed into the joint space to drive the servo controllers. For the center of the robot, a convolution-based path planner and a corresponding joint space control algorithm are presented considering its physical limits. To avoid obstacles that introduce geometric constraints on the curved path, a trajectory generation algorithm considering high curvature turning points is adapted for an omnidirectional mobile robot. Tracking a high curvature path increases mathematical complexity, which requires precise synchronization between the actuators of the mobile robot. An improvement of the distributed clock—the synchronization mechanism of EtherCAT for slaves—is presented and applied to the joint controllers of the mobile robot. The local time of the EtherCAT master is dynamically adjusted according to the drift of the reference slave, which minimizes the synchronization error between each joint. Experiments are conducted on our own developed four-wheeled omnidirectional mobile robot. The experiment results confirm that the proposed system is very effective in real-time control applications for precise motion control of the robot even for tracking high curvature paths.

The Research of the Real-Time High-Resolution Image Acquisition Based on Embedded System

2014 ◽  
Vol 631-632 ◽  
pp. 508-511
Author(s):  
Xi Ye Feng ◽  
Xiu Qing Huang
Keyword(s):  
High Resolution ◽  
Embedded System ◽  
Real Time ◽  
Low Cost ◽  
Image Acquisition ◽  
Image Data ◽  
Image Sensor ◽  
High Definition ◽  
The Real ◽  
Embedded Linux System

This paper presents the design of a real-time high-definition image acquisition. The hardware platform combines Intel Xscale PXA270 processor, high-resolution camera and SAA7114H. The system is based on the embedded Linux system. Beetween the image sensor and the system memory,there is a quick capture interface.The interface receives the data from the image sensor,and converts the raw image data to a suitable format, and sends H.264 stream to the memory via the DMA channel. The result shows that the design can realize the real-time and high-definition image acquisition in a complicated environment. The advantage of this system is small volume, low power consumption and low cost. It can be widely used in agricultural and hydrological monitoring, intelligent transportation, security monitoring and intelligent home.

Sign in / Sign up

Export Citation Format

Share Document