Low-cost Raspberry Pi Research Articles

Robust embedded access control system based on face and encrypted QR with RPi4

<p><span>Facial-based recognition systems are commonly used for building access control, with the accuracy and computing requirements still being improved. On the other hand, QR codes are gaining rising attention as an input interface to many embedded applications. This paper proposes an embedded access control system that customises both previous techniques to be implemented on the CPU of a low-cost Raspberry Pi 4 computer. The achieved system works smoothly with a frame rate of 8.27 FPS, increasing the accessing control's robustness compared to a system based on face recognition only. It also offers the ability to control the access of unknown faces. In tandem with integration, this strengthens security measures, improves user experience, and outperforms conventional access control approaches, creating an attractive offer for many businesses.</span></p>

A low-cost Raspberry Pi based imaging system for analysis of fiber specklegram sensors

A low-cost Raspberry Pi based imaging system for analysis of fiber specklegram sensors

Low-cost Raspberry Pi star sensor for small satellites. II: StarberrySense flight and in-orbit performance

Low-cost Raspberry Pi star sensor for small satellites. II: StarberrySense flight and in-orbit performance

A 3D image-based method to measure soil stiffness in triaxial tests

This paper describes a new simple and inexpensive method for accurately measuring the three-dimensional deformation of soil specimens during triaxial tests. The method incorporates a cost-effective image capture system that can be applied to any triaxial apparatus as well as an automated post-image analysis approach for processing the images acquired during triaxial tests. Image capture is performed using multiple low-cost Raspberry Pi cameras and accessories placed outside the triaxial chamber. The system employs particle image velocimetry, camera calibration and stereophotogrammetry to determine the spatial variation in axial and radial sample strains as samples are loaded. It is demonstrated that axial and radial displacements can be measured with an accuracy of 1–2 μm, respectively, and it is verified by comparison with data from triaxial tests on sand samples that the full nonlinear stiffness–strain degradation of soil samples from fully elastic conditions can be determined without the need for any additional sensors.

Implementation of a steganography system based on hybrid square quaternion moment compression in IoMT

Internet of Medical Things (IoMT) systems generate medical data transmissions between patients, medical experts, and medical centers over public networks, which require high levels of security to protect the content of medical images and the personal information they contain. In this paper, we propose a new stego image encryption scheme based on a new secret image compression method, wavelet transformation, QR decomposition of the cover image, and a new chaotic map. The secret image is compressed by the Hahn-Krawtchouk hybrid quaternion square moments (HK-HQSM), which are optimized by a new hybrid metaheuristic algorithm based on the Salp Swarm Algorithm (SSA) and the Arithmetic Optimization Algorithm (AOA). To increase the security level when transmitting the proposed stego images over public networks, we introduce a new chaotic map based on the 2D fractional Henon map to encrypt the stego image. To demonstrate the effectiveness of the proposed steganography scheme for IoMT, we implemented this scheme on a low-cost Raspberry Pi 4 hardware board. The results of the performed numerical experiments show that our method is secure and provides exceptional robustness against common standard image processing attacks (steganalysis attacks). The results also demonstrate that our strategy is able to work efficiently and quickly when implemented on a Raspberry Pi board.

Classification of Mammography Images Using Deep-CNN based Feature Ensemble Approach and its Implementation on a Low-Cost Raspberry Pi

Classification of Mammography Images Using Deep-CNN based Feature Ensemble Approach and its Implementation on a Low-Cost Raspberry Pi

Evaluation of low-cost Raspberry Pi sensors for structure-from-motion reconstructions of glacier calving fronts

Abstract. Glacier calving fronts are highly dynamic environments that are becoming ubiquitous as glaciers recede and, in many cases, develop proglacial lakes. Monitoring of calving fronts is necessary to fully quantify the glacier ablation budget and to warn nearby communities of the threat of hazards, such as glacial lake outburst floods (GLOFs), tsunami waves, and iceberg collapses. Time-lapse camera arrays, with structure-from-motion photogrammetry, can produce regular 3D models of glaciers to monitor changes in the ice but are seldom incorporated into monitoring systems owing to the high cost of equipment. In this proof-of-concept study at Fjallsjökull, Iceland, we present and test a low-cost, highly adaptable camera system based on Raspberry Pi computers and compare the resulting point cloud data to a reference cloud generated using an unoccupied aerial vehicle (UAV). The mean absolute difference between the Raspberry Pi and UAV point clouds is found to be 0.301 m with a standard deviation of 0.738 m. We find that high-resolution point clouds can be robustly generated from cameras positioned up to 1.5 km from the glacier (mean absolute difference 0.341 m, standard deviation 0.742 m). Combined, these experiments suggest that for monitoring calving events in glaciers, Raspberry Pi cameras are an affordable, flexible, and practical option for future scientific research. Owing to the connectivity capabilities of Raspberry Pi computers, this opens the possibility for real-time structure-from-motion reconstructions of glacier calving fronts for deployment as an early warning system to calving-triggered GLOFs.

92 Mb/s Fat-Intrabody Communication (Fat-IBC) With Low-Cost WLAN Hardware.

The human subcutaneous fat layer, skin and muscle together act as a waveguide for microwave transmissions and provide a low-loss communication medium for implantable and wearable body area networks (BAN). In this work, fat-intrabody communication (Fat-IBC) as a human body-centric wireless communication link is explored. To reach a target 64 Mb/s inbody communication, wireless LAN in the 2.4 GHz band was tested using low-cost Raspberry Pi single-board computers. The link was characterized using scattering parameters, bit error rate (BER) for different modulation schemes, and IEEE 802.11n wireless communication using inbody (implanted) and onbody (on the skin) antenna combinations. The human body was emulated by phantoms of different lengths. All measurements were done in a shielded chamber to isolate the phantoms from external interference and to suppress unwanted transmission paths. The BER measurements show that, except when using dual on-body antennas with longer phantoms, the Fat-IBC link is very linear and can handle modulations as complex as 512-QAM without any significant degradation of the BER. For all antenna combinations and phantoms lengths, link speeds of 92 Mb/s were achieved using 40 MHz bandwidth provided by the IEEE 802.11n standard in the 2.4 GHz band. This speed is most likely limited by the used radio circuits, not the Fat-IBC link. The results show that Fat-IBC, using low-cost off-the-shelf hardware and established IEEE 802.11 wireless communication, can achieve high-speed data communication within the body. The obtained data rate is among the fastest measured with intrabody communication.

Low-Cost Raspberry-Pi-Based UAS Detection and Classification System Using Machine Learning

Small Unmanned Aerial Systems (UAS) usage is undoubtedly increasing at a significant rate. However, alongside this expansion is a growing concern that dependable low-cost counter measures do not exist. To mitigate a threat in a restricted airspace, it must first be known that a threat is present. With airport disruption from malicious UASs occurring regularly, low-cost methods for early warning are essential. This paper considers a low-cost early warning system for UAS detection and classification consisting of a BladeRF software-defined radio (SDR), wideband antenna and a Raspberry Pi 4 producing an edge node with a cost of under USD 540. The experiments showed that the Raspberry Pi using TensorFlow is capable of running a CNN feature extractor and machine learning classifier as part of an early warning system for UASs. Inference times ranged from 15 to 28 s for two-class UAS detection and 18 to 28 s for UAS type classification, suggesting that for systems that require timely results the Raspberry Pi would be better suited to act as a repeater of the raw SDR data, enabling the processing to be carried out on a higher powered central control unit. However, an early warning system would likely fuse multiple sensors. These experiments showed the RF machine learning classifier capable of running on a low-cost Raspberry Pi 4, which produced overall accuracy for a two-class detection system at 100% and 90.9% for UAS type classification on the UASs tested. The contribution of this research is a starting point for the consideration of low-cost early warning systems for UAS classification using machine learning, an SDR and Raspberry Pi.

RedStat: Leveraging open-source hardware by using low-cost computers and open-source software in a client-server wi-fi infrastructure for continuous monitoring and condition-controlled experiments

Due to the memory limitation challenges of using low-cost computer interfacing hardware in long-term monitoring of signals, we present a flexible and easy-to-deploy wi-fi server-client platform. It allows using low-cost Raspberry Pi computers to interface hardware in the laboratory and use up-to-date software tools such as time-series database software. This facilitates long-term monitoring and data management in a local area network (LAN). RedStat consists of an installation script that helps configuring the LAN hostname and installs the open software tools required to interface and manage the data monitoring. Node-RED acts as the orchestrator of the software integration and RedStat supplies three different example programs to interface three open hardware projects: the microcontroller Arduino, the hardware incubator “OpenTCC” and the open-source potentiostat “DStat”. RedStat provides an infrastructure to develop similar programs interacting other types of serial communication devices, thus facilitating developing and increasing the impact of open-source hardware in continuous monitoring and condition-controlled experiments.

Pi USB Cam: A Simple and Affordable DIY Solution That Enables High-Quality, High-Throughput Video Capture for Behavioral Neuroscience Research.

Video recording is essential for behavioral neuroscience research, but the majority of available systems suffer from poor cost-to-functionality ratio. Commercial options frequently come at high financial cost that prohibits scalability and throughput, whereas DIY solutions often require significant expertise and time investment unaffordable to many researchers. To address this, we combined a low-cost Raspberry Pi microcomputer, DIY electronics peripherals, freely available open-source firmware, and custom 3D-printed casings to create Pi USB Cam, a simple yet powerful and highly versatile video recording solution. Pi USB Cam is constructed using affordable and widely available components and requires no expertise to build and implement. The result is a system that functions as a plug-and-play USB camera that can be easily installed in various animal testing and housing sites and is readily compatible with popular behavioral and neural recording software. Here, we provide a comprehensive parts list and step-by-step instructions for users to build and implement their own Pi USB Cam system. In a series of benchmark comparisons, Pi USB Cam was able to capture ultra-wide fields of view of behaving rats given limited object distance and produced high image quality while maintaining consistent frame rates even under low-light and no-light conditions relative to a standard, commercially available USB camera. Video recordings were easily scaled using free, open-source software. Altogether, Pi USB Cam presents an elegant yet simple solution for behavioral neuroscientists seeking an affordable and highly flexible system to enable quality video recordings.

Low-cost Raspberry Pi star sensor for small satellites

We present here a low-cost Raspberry Pi (RPi)-based star sensor StarberrySense using commercial-off-the-shelf (COTS) components, developed and built for applications in small satellites and CubeSat-based missions. A star sensor is one of the essential instruments onboard a satellite for attitude determination. However, most commercially available star sensors are expensive and bulky to be used in small satellite missions. StarberrySense is a configurable system -- it can operate as an imaging camera, a centroiding camera, or as a star sensor. We describe the algorithms implemented in the sensor, its assembly and calibration. This payload was selected by a recent Announcement of Opportunity call for payloads to fly on the PS4-Orbital Platform by the Indian Space Research Organization (ISRO).

An efficient and reliable chemical inventory system at a growing drug discovery company.

Within a growing drug discovery company, hundreds of scientists take and move reagent chemicals on a daily basis. Conveniently updating the locations of tens of thousands of chemical containers in an electronic system is a big challenge. We have an electronic inventory system, but keeping the chemical records up to date relied on scientists finding an available computer in the lab and logging into a system whenever they took or moved a chemical container, taking several minutes. It was all too easy to think that the task could be deferred until later, but the scientist may then forget all about it, leaving the database inaccurate. As a result, searching for the chemicals we need can take a frustratingly long time if they are not where they should be. We have developed an efficient and reliable system, namely ScanStation, to solve this issue. It relies on a low-cost Raspberry Pi attached to a touch screen connected with a barcode scanner. This equipment is always on and placed in strategic locations around all our labs and chemical stores. This new process is much easier. There is no need to remove gloves to log into the computer, and it is just a scan on the barcode and is done. Now when we check the database for a chemical, we get an instant answer that reliably tells us where to find it. All the time we save have a real benefit in our productivity and our scientists can focus on discovering new medicines.

IoT-Enabled Vehicle Speed Monitoring System

Millions of people lose their lives each year worldwide due to traffic law violations, specifically, over speeding. The existing systems fail to report most of such violations due to their respective flaws. For instance, speed guns work in isolation and cannot measure speed of all vehicles on roads at all spatial points. They can only detect the speed of the vehicle the line of sight of the camera. A solution is to deploy a huge number of speed guns at different locations on the road to detect and report vehicles that are over speeding. However, this solution is not feasible because it demands a large amount of equipment and computational resources to process such a big amount of data. In this paper, a speed detection framework is developed to detect vehicles’ speeds with only two speed guns, which can report speed even when the vehicle is not within the camera’s line of sight. The system is specifically designed for an irregular traffic scenario such as that of Pakistan, where it is inconvenient to install conventional systems. The idea is to calculate the average speed of vehicles traveling in a specific region, for instance, between two spatial points. A low-cost Raspberry Pi (RPi) module and an ordinary camera are deployed to detect the registration numbers on vehicle license plates. This hardware presents a more stable system since it is powered by a low consumption Raspberry Pi that can operate for hours without crashing or malfunctioning. More specifically, the entrance and exit locations and the time taken to get from one point to another are recorded. An automatic alert to traffic authorities is generated when a driver is over speeding. A detailed explanation of the hardware prototype and the algorithms is given, along with the setup configurations of the hardware prototype, the website, and the mobile device applications.

Wireless Fixed Camera Network for Greenhouse-Based Plant Phenotyping.

An indoor wireless fixed camera network was developed for an efficient, cost-effective method of extracting informative plant phenotypes in a controlled greenhouse environment. Deployed at the Donald Danforth Plant Science Center (DDPSC), this fixed camera platform implements rapid and automated plant phenotyping. The platform uses low-cost Raspberry Pi computers and digital cameras to monitor aboveground morphological and developmental plant phenotypes. The Raspberry Pi is a readily programmable, credit card-sized computer board with remote accessibility. A standard camera module connects to the Raspberry Pi computer board and generates eight-megapixel resolution images. With a fixed array, or "bramble," of Raspberry Pi computer boards and camera modules placed strategically in a greenhouse, we can capture automated, high-resolution images for 3D reconstructions of individual plants on timescales ranging from minutes to hours, capturing temporal changes in plant phenotypes.

Variable Exposure Portable Perfusion Monitor Using Commercial Vision Processing System-on-Modules (SOMs)

Laser speckle imaging (LSI) has been widely used to image blood flow in biomedical/clinical research. Commercially available perfusion monitoring systems are bulky, expensive and lack portability. Portable devices that perform LSI using custom Digital Signal Processors (DSPs), and smartphones have been proposed to perform single exposure LSI to monitor blood flow. While these can perform LSI, it is difficult to estimate flow rates using single exposure LSI. In this study, we use NVIDIA’s Xavier NX embedded vision processing platform to perform variable exposure LSI to evaluate flow rates in a 3D printed flow phantom. A low-cost Raspberry Pi HQ camera was used to acquire LSI images and the increased sensitivity of the camera allowed images to be captured with exposure times < 1ms. The higher performance of the Xavier NX platform allowed for video-rate LSI imaging (25 ± 2 FPS for spatial and 5 ± 2 FPS for temporal variance images respectively) of the phantom and using variable exposure datasets, slow (2mm/s-6mm/s), medium (6mm/s-12mm/s), and fast (>12mm/s) flow rates were distinguished. Such a platform can extend the use of portable LSI devices in peri-operative, post-operative and other point-of-care applications as this platform can be commercialized into a tablet-like form factor for convenient portable operation.

Multiple Zero-Watermarking of Medical Images for Internet of Medical Things

The Internet of Medical Things (IoMT) plays a vital role in healthcare systems to increase electronic devices’ accuracy, reliability, and productivity. This paper presents fast multiple zero-watermarking methods based on Multi-channel Fractional Legendre Fourier moments (MFrLFMs) for medical image security and copyright protection in IoMT applications without deforming the original medical images. The MFrLFMs are utilized due to their high accuracy, numerical stability, geometric invariances, and high resistance to various attacks. Based on the most significant features generated from MFrLFMs, after scrambling using a two-dimensional Discrete Henon Map, then XORed with binary scrambled watermark to construct owner share. The proposed watermarking method is implemented using a low-cost Raspberry Pi Linux microprocessor, which ensures the suitability of medical devices in the IoMT environment. We evaluated the robustness of the proposed algorithm against different geometric and common signal processing attacks using various medical images. The proposed method gives better BER, NC, and SSIM values than existing methods.

A Low-Cost Raspberry Pi-based System for Facial Recognition

Deep learning has become increasingly popular and widely applied to computer vision systems. Over the years, researchers have developed various deep learning architectures to solve different kinds of problems. However, these networks are power-hungry and require high-performance computing (i.e., GPU, TPU, etc.) to run appropriately. Moving computation to the cloud may result in traffic, latency, and privacy issues. Edge computing can solve these challenges by moving the computing closer to the edge where the data is generated. One major challenge is to fit the high resource demands of deep learning in less powerful edge computing devices. In this research, we present an implementation of an embedded facial recognition system on a low cost Raspberry Pi, which is based on the FaceNet architecture. For this implementation it was required the development of a library in C++, which allows the deployment of the inference of the Neural Network Architecture. The system had an accuracy and precision of 77.38% and 81.25%, respectively. The time of execution of the program is 11 seconds and it consumes 46 [kB] of RAM. The resulting system could be utilized as a stand-alone access control system. The implemented model and library are released at https://github.com/cristianMiranda-Oro/FaceNet_EmbeddedSystem

Low-complexity three-dimensional discrete Hartley transform approximations for medical image compression

The discrete Hartley transform (DHT) is a useful tool for medical image coding. The three-dimensional DHT (3D DHT) can be employed to compress medical image data, such as magnetic resonance and X-ray angiography. However, the computation of the 3D DHT involves several multiplications by irrational quantities, which require floating-point arithmetic and inherent truncation errors. In recent years, a significant progress in wireless and implantable biomedical devices has been achieved. Such devices present critical power and hardware limitations. The multiplication operation demands higher hardware, power, and time consumption than other arithmetic operations, such as addition and bit-shifts. In this work, we present a set of multiplierless DHT approximations, which can be implemented with fixed-point arithmetic. We derive 3D DHT approximations by employing tensor formalism. Such proposed methods present prominent computational savings compared to the usual 3D DHT approach, being appropriate for devices with limited resources. The proposed transforms are applied in a lossy 3D DHT-based medical image compression algorithm, presenting practically the same level of visual quality (>98% in terms of SSIM) at a considerable reduction in computational effort (100% multiplicative complexity reduction). Furthermore, we implemented the proposed 3D transforms in an ARM Cortex-M0+ processor employing the low-cost Raspberry Pi Pico board. The execution time was reduced by ∼70% compared to the usual 3D DHT and ∼90% compared to 3D DCT.

Harmonic/interharmonic estimation using standard deviation assisted ESPRIT method

PurposeThis paper aims to accurately estimate harmonics/interharmonics in modern power system. There are several high spectral resolution techniques that have been in use for several years like Estimation of Signal Parameters via Rotational Invariance Technique (ESPRIT), Prony methods, etc. but these techniques require prior knowledge of number of modes present in the signal. Model Order (MO) estimation techniques have to make a trade-off between accuracy and their speed i.e., computational burden. Therefore, there is always a requirement of a technique that is fast as well as accurate.Design/methodology/approachThe proposed standard deviation (SD) method eliminates the requirement of energy validation test and analyses the distribution pattern, i.e. standard deviation of eigenvalues to identify the number of modes present in the signal. Signal is reconstructed using estimated modes and reconstruction error is obtained to show accuracy of the proposed estimation.FindingsSix test synthetic signals as well as one practical signal have been taken for validating the proposed method. The paper shows that proposed methodology has a better accuracy compared to modified exact model order (MEMO) method in high noise environment and takes very less computation time compared to the exact model order (EMO) method.Practical implicationsThe proposed method has been practically implemented for harmonic/interharmonic analysis at a sewage treatment plant at GIFT City, Gujarat, India. Apart from this the proposed method is modeled in python-based tool and is run into low-cost Raspberry Pi like hardware to create an onsite as well as remote monitoring device.Originality/valueSD-based approach for model order estimation is novel to this area. Further, the proposed method is compared with EMO and MEMO under varying noise conditions to check for accuracy and estimation time.