scholarly journals An Evaluation of Low-Cost Vision Processors for Efficient Star Identification

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6250
Author(s):  
Surabhi Agarwal ◽  
Elena Hervas-Martin ◽  
Jonathan Byrne ◽  
Aubrey Dunne ◽  
Jose Luis Espinosa-Aranda ◽  
...  
Keyword(s):  
Low Power ◽  
Attitude Determination ◽  
Low Cost ◽  
Cost Effective ◽  
Power Measurement ◽  
Star Tracker ◽  
Processing Unit ◽  
Small Satellites ◽  
Star Identification ◽  
Star Tracking

Star trackers are navigation sensors that are used for attitude determination of a satellite relative to certain stars. A star tracker is required to be accurate and also consume as little power as possible in order to be used in small satellites. While traditional approaches use lookup tables for identifying stars, the latest advances in star tracking use neural networks for automatic star identification. This manuscript evaluates two low-cost processors capable of running a star identification neural network, the Intel Movidius Myriad 2 Vision Processing Unit (VPU) and the STM32 Microcontroller. The intention of this manuscript is to compare the accuracy and power usage to evaluate the suitability of each device for use in a star tracker. The Myriad 2 VPU and the STM32 Microcontroller have been specifically chosen because of their performance on computer vision algorithms alongside being cost-effective and low power consuming devices. The experimental results showed that the Myriad 2 proved to be efficient and consumed around 1 Watt of power while maintaining 99.08% accuracy with an input including false stars. Comparatively the STM32 was able to deliver comparable accuracy (99.07%) and power measurement results. The proposed experimental setup is beneficial for small spacecraft missions that require low-cost and low power consuming star trackers.

An Innovative Low Cost Well Monitoring Solution: W.A.N.D

2021 ◽  
Author(s):  
Jean Grégoire Boero Rollo ◽  
John Richard Ordonez Varela ◽  
Tayssir Ben Ghzaiel ◽  
Cedric Mouanga ◽  
Arnaud Luxey ◽  
...  
Keyword(s):  
Magnetic Field ◽  
Low Power ◽  
Low Cost ◽  
Field Measurements ◽  
Cost Effective ◽  
Complex Environment ◽  
Sensor Device ◽  
Magnetic Field Measurements ◽  
Pipeline Monitoring ◽  
Harsh Conditions

Abstract Wireless Autonomous Nano-sensor Device (WAND) system is a disruptive cost-effective micro-system for well monitoring. It allows to realize pressure, temperature, inertial, and magnetic field measurements in harsh conditions; it also offers Bluetooth low-power communication and Wireless charging capabilities. Analysis’ results of an industrial offshore pilot realized in Congo (a world first in O&G industry in such complex environment), and major improvements implemented after this pilot are reported in this paper. Accomplished advancements comprise hardware and software developments extending operation lifetime, and simplifying on-site utilization. To date, there is not a commercial solution of this type in the market, the realization of this project is a real innovation allowing practical and low-cost monitoring during well intervention while minimizing the risks associated with standard Rigless intervention. Other applications regarding dry-tree wells on tension-leg platforms (TLP), drilling and completion operations, and pipeline monitoring are being investigated, too.

scholarly journals An improved low power measurement of ambient NO<sub>2</sub> and O<sub>3</sub> combining electrochemical sensor clusters and machine learning

2018 ◽  
Author(s):  
Kate R. Smith ◽  
Peter M. Edwards ◽  
Peter D. Ivatt ◽  
James D. Lee ◽  
Freya Squires ◽  
...  
Keyword(s):  
Machine Learning ◽  
Low Power ◽  
Electrochemical Sensors ◽  
Low Cost ◽  
Quality Measurement ◽  
Power Measurement ◽  
Clustering Approach ◽  
Long Timescales ◽  
Signal Variability ◽  
Analytical Device

Abstract. Low cost sensors (LCS) are an appealing solution to the problem of spatial resolution in air quality measurement, but they currently do not have the same analytical performance as regulatory reference methods. Individual sensors can be susceptible to analytical cross interferences, have random signal variability and experience drift over short, medium and long timescales. To overcome some of the performance limitations of individual sensors we use a clustering approach using the instantaneous median signal from six identical electrochemical sensors to minimise the randomised drifts and inter-sensor differences. We report here a low power analytical device (

First Flight Experiment with the NERVA-1 Inertial Platform

2013 ◽  
Vol 325-326 ◽  
pp. 990-993 ◽  
Author(s):  
Cristian E. Constantinescu ◽  
Radu D. Rugescu ◽  
Silviu Ciochina ◽  
Remus C. Cacoveanu
Keyword(s):  
Degrees Of Freedom ◽  
Inertial Sensors ◽  
Low Cost ◽  
Cost Effective ◽  
Flight Test ◽  
Guidance System ◽  
Ministry Of Education ◽  
Flight Experiment ◽  
Small Satellites ◽  
Space Launcher

The guidance system of the NERVA small space launcher is based on the six degrees-of-freedom information delivered by an inertial platform. Due to the main scope of the project sponsored by the Romanian Ministry of Education, Research, Youth and Sports to build a cost-effective space launcher, the inertial platform was built with extensive use of on-the-shelf, low cost inertial sensors and equipment. Concerns regarding the behavior and reliability of the sensing block were solved during the first flight experiment in June 2010, on-board the military, unguided drone missile RT-759-01 NERVA-1 and the results are described. The behavior of the electronics under the dynamical loads of the rocket flight, involving overloads of more than 20 g-s and the level of vibration during the real flight was the focus of the flight test, the first ever performed in Romania. The data were broadcast through a eight channel telemetry chain and received on the ground in two different locations for reliability enhancement. The data acquisition performed very well and supplied the basis for further development of the more accurate orbital injection guidance system of the NERVA launcher of small satellites in LEO.

scholarly journals Design approach for wideband FM receiver using RTL-SDR and raspberry PI

2018 ◽  
Vol 7 (2.31) ◽  
pp. 9 ◽  
Author(s):  
P Satya Narayana ◽  
M N.V.S. Syam Kumar ◽  
A Keerthi Kishan ◽  
K V.R.K. Suraj
Keyword(s):  
Communication System ◽  
Software Defined Radio ◽  
Low Cost ◽  
Wide Band ◽  
Cost Effective ◽  
Raspberry Pi ◽  
Processing Unit ◽  
Capture Process ◽  
Band Frequency ◽  
Wide Range

Software defined radio replaced majority of hardware modules like mixers, filters, modulators and demodulators etc., with Software blocks in the field of radio electronics and communication. In this some or all the functionalities are Configurable using this software implemented on technologies like FPGAs, DSPs etc. Owing to lack of ease in implementing and reconfiguring huge hardware modules, we move on to implement an adaptable communication system with the help of SDR, as it can be easily configured to work with wide range of frequencies. We find various SDR transceiver modules which can be interfaced with digital computer and aided with firmware like GNU radio, SDR shark, etc., allowing us to construct blocks with the help of built in components that decode and process the received data and produce required output. In requirement of implementing a cost-effective, compact sized and portable system, we use a processing unit providing enough computational power to perform signal processing tasks which is Raspberry pi. Here we are going to implement a low cost SDR communication system that capture, process and visualize the Wide Band Frequency signal. 

Cost-effective low-power graphics processing unit for handheld devices

2008 ◽  
Vol 46 (4) ◽  
pp. 152-159 ◽  
Author(s):  
Byeong-Gyu Nam ◽  
Jeabin Lee ◽  
Kwanho Kim ◽  
Seungjin Lee ◽  
Hoi-Jun Yoo
Keyword(s):  
Low Power ◽  
Graphics Processing Unit ◽  
Cost Effective ◽  
Handheld Devices ◽  
Processing Unit ◽  
Graphics Processing

scholarly journals Grape Bunch Detection at Different Growth Stages Using Deep Learning Quantized Models

Agronomy ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 1890
Author(s):  
André Silva Aguiar ◽  
Sandro Augusto Magalhães ◽  
Filipe Neves dos Santos ◽  
Luis Castro ◽  
Tatiana Pinho ◽  
...  
Keyword(s):  
Deep Learning ◽  
Low Power ◽  
Agricultural Sector ◽  
Early Stage ◽  
Low Cost ◽  
Confidence Score ◽  
Growth Stages ◽  
Processing Unit ◽  
Single Shot ◽  
Different Growth Stages

The agricultural sector plays a fundamental role in our society, where it is increasingly important to automate processes, which can generate beneficial impacts in the productivity and quality of products. Perception and computer vision approaches can be fundamental in the implementation of robotics in agriculture. In particular, deep learning can be used for image classification or object detection, endowing machines with the capability to perform operations in the agriculture context. In this work, deep learning was used for the detection of grape bunches in vineyards considering different growth stages: the early stage just after the bloom and the medium stage where the grape bunches present an intermediate development. Two state-of-the-art single-shot multibox models were trained, quantized, and deployed in a low-cost and low-power hardware device, a Tensor Processing Unit. The training input was a novel and publicly available dataset proposed in this work. This dataset contains 1929 images and respective annotations of grape bunches at two different growth stages, captured by different cameras in several illumination conditions. The models were benchmarked and characterized considering the variation of two different parameters: the confidence score and the intersection over union threshold. The results showed that the deployed models could detect grape bunches in images with a medium average precision up to 66.96%. Since this approach uses low resources, a low-cost and low-power hardware device that requires simplified models with 8 bit quantization, the obtained performance was satisfactory. Experiments also demonstrated that the models performed better in identifying grape bunches at the medium growth stage, in comparison with grape bunches present in the vineyard after the bloom, since the second class represents smaller grape bunches, with a color and texture more similar to the surrounding foliage, which complicates their detection.

Hardware Realization of Antifogging System

2017 ◽  
pp. 153-172
Author(s):  
Amruta Laxman Deshmukh ◽  
Satbir Singh ◽  
Balwinder Singh
Keyword(s):  
Embedded System ◽  
Low Power ◽  
Computer Model ◽  
Surveillance System ◽  
Low Cost ◽  
Model System ◽  
Raspberry Pi ◽  
Processing Unit ◽  
Matlab Code ◽  
Condensed Water

There are many reasons for invisibility of objects on road in daylight, majority of them are Fog (condensed water droplets in atmosphere), smog (soot particles in air). This reduced visibility is one of the prime factors responsible for accident of vehicles and disadvantage in surveillance system. This chapter takes account of a method that comprises of a complete embedded system for the process of restoring the captured foggy images. Use of a novel ‘Mean Channel Prior' algorithm for defogging is presented. Further detailed step by step explanation is given for hardware implementation of MATLAB code. Hardware consists of raspberry pi which is an ARM7 Quad Core processor based mini computer model. System serves as portable, low cost and low power processing unit with provision of interfacing a camera and a display screen.

Sign in / Sign up

Export Citation Format

Share Document