scholarly journals Configurable Hardware Core for IoT Object Detection

2021 ◽  
Vol 13 (11) ◽  
pp. 280
Author(s):  
Pedro R. Miranda ◽  
Daniel Pestana ◽  
João Daniel Lopes ◽  
Rui Policarpo Duarte ◽  
Mário P. Véstias ◽  
...  
Keyword(s):  
Object Detection ◽  
Good Accuracy ◽  
Low Cost ◽  
Full System ◽  
The Core ◽  
Transportation Security ◽  
Field Programmable ◽  
Constrained Environments ◽  
Configurable Hardware ◽  
On Chip

Object detection is an important task for many applications, like transportation, security, and medical applications. Many of these applications are needed on edge devices to make local decisions. Therefore, it is necessary to provide low-cost, fast solutions for object detection. This work proposes a configurable hardware core on a field-programmable gate array (FPGA) for object detection. The configurability of the core allows its deployment on target devices with diverse hardware resources. The object detection accelerator is based on YOLO, for its good accuracy at moderate computational complexity. The solution was applied to the design of a core to accelerate the Tiny-YOLOv3, based on a CNN developed for constrained environments. However, it can be applied to other YOLO versions. The core was integrated into a full system-on-chip solution and tested with the COCO dataset. It achieved a performance from 7 to 14 FPS in a low-cost ZYNQ7020 FPGA, depending on the quantization, with an accuracy reduction from 2.1 to 1.4 points of mAP50.

scholarly journals Low-Power Pedestrian Detection System on FPGA

Proceedings ◽  
2019 ◽  
Vol 31 (1) ◽  
pp. 35 ◽  
Author(s):  
Vinh Ngo ◽  
David Castells-Rufas ◽  
Arnau Casadevall ◽  
Marc Codina ◽  
Jordi Carrabina
Keyword(s):  
Low Power ◽  
Detection System ◽  
Low Cost ◽  
Pedestrian Detection ◽  
Support Vector ◽  
Embedded Processor ◽  
Car Industry ◽  
Field Programmable ◽  
On Chip ◽  
Histogram Of Gradients

Pedestrian detection is one of the key problems in the emerging self-driving car industry. In addition, the Histogram of Gradients (HOG) algorithm proved to provide good accuracy for pedestrian detection. Many research works focused on accelerating HOG algorithm on FPGA (Field-Programmable Gate Array) due to its low-power and high-throughput characteristics. In this paper, we present an energy-efficient HOG-based implementation for pedestrian detection system on a low-cost FPGA system-on-chip platform. The hardware accelerator implements the HOG computation and the Support Vector Machine classifier, the rest of the algorithm is mapped to software in the embedded processor. The hardware runs at 50 Mhz (lower frequency than previous works), thus achieving the best pixels processed per clock and the lower power design.

scholarly journals High-Performance Time Server Core for FPGA System-on-Chip

Electronics ◽  
2019 ◽  
Vol 8 (5) ◽  
pp. 528 ◽  
Author(s):  
Julian Viejo ◽  
Jorge Juan-Chico ◽  
Manuel J. Bellido ◽  
Paulino Ruiz-de-Clavijo ◽  
David Guerrero ◽  
...  
Keyword(s):  
High Performance ◽  
System On Chip ◽  
The Core ◽  
Performance Time ◽  
Network Time ◽  
Wide Range ◽  
Network Time Protocol ◽  
Field Programmable ◽  
And Performance ◽  
On Chip

This paper presents the complete design and implementation of a low-cost, low-footprint, network time protocol server core for field programmable gate arrays. The core uses a carefully designed modular architecture, which is fully implemented in hardware using digital circuits and systems. Most remarkable novelties introduced are a hardware-optimized timekeeping algorithm implementation, and a full-hardware protocol stack and automatic network configuration. As a result, the core is able to achieve similar accuracy and performance to typical high-performance network time protocol server equipment. The core uses a standard global positioning system receiver as time reference, has a small footprint and can easily fit in a low-range field-programmable chip, greatly scaling down from previous system-on-chip time synchronization systems. Accuracy and performance results show that the core can serve hundreds of thousands of network time clients with negligible accuracy degradation, in contrast to state-of-the-art high-performance time server equipment. Therefore, this core provides a valuable time server solution for a wide range of emerging embedded and distributed network applications such as the Internet of Things and the smart grid, at a fraction of the cost and footprint of current discrete and embedded solutions.

scholarly journals Online Estimation of the Current Ripple on a Saturating Ferrite-Core Inductor in a Boost Converter

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2921 ◽  
Author(s):  
Matteo Lodi ◽  
Alberto Oliveri
Keyword(s):  
High Performance ◽  
Low Cost ◽  
Boost Converter ◽  
Operating Conditions ◽  
Nonlinear Observer ◽  
Estimation Accuracy ◽  
Ferrite Core ◽  
Field Programmable ◽  
On Chip ◽  
Current Ripple

In this paper, a nonlinear observer is proposed for the estimation of the current ripple in a ferrite-core inductor working in partial saturation, mounted on a boost converter. The estimator is based on a recently proposed nonlinear inductance model, which expresses the inductance as a function of the inductor current, taking into account also the non-negligible effects of the core temperature. The proposed observer is implemented on a low-cost microcontroller and tested, both offline and online, on a real boost converter with different operating conditions. The offline tests show a satisfactory estimation accuracy both during the electrical (fast) and thermal (slow) transients. Due to the high microcontroller latency, some delays and inaccuracies occur during electrical transients in the online tests. This work suggests that, in order to exploit the observer for control purposes, the target architecture should be a high-performance microcontroller, a system-on-chip, or a field programmable gate array, where parallelism can be exploited to speed-up the computations. The proposed implementation can be instead suitable for switch-mode power supply (SMPS) monitoring purposes.

Techniques for assessing the performance of circuit materials at microwave and millimetre-wave frequencies

2003 ◽  
Vol 783 ◽  
Author(s):  
Charles E Free
Keyword(s):  
Loss Tangent ◽  
Good Accuracy ◽  
Low Cost ◽  
Resonant Cavity ◽  
New Technique ◽  
Millimetre Wave ◽  
A New Technique

This paper discusses the techniques that are available for characterising circuit materials at microwave and millimetre wave frequencies. In particular, the paper focuses on a new technique for measuring the loss tangent of substrates at mm-wave frequencies using a circular resonant cavity. The benefits of the new technique are that it is simple, low cost, capable of good accuracy and has the potential to work at high mm-wave frequencies.

scholarly journals Design and Manufacturing of a Disposable, Cyclo-Olefin Copolymer, Microfluidic Device for a Biosensor †

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 1178 ◽  
Author(s):  
Jorge Prada ◽  
Christina Cordes ◽  
Carsten Harms ◽  
Walter Lang
Keyword(s):  
Microfluidic Device ◽  
Heating Temperature ◽  
Low Cost ◽  
Reaction Chamber ◽  
Microfluidic System ◽  
Heating Process ◽  
Design And Manufacturing ◽  
On Chip ◽  
Working Parameters ◽  
Auto Fluorescence

This contribution outlines the design and manufacturing of a microfluidic device implemented as a biosensor for retrieval and detection of bacteria RNA. The device is fully made of Cyclo-Olefin Copolymer (COC), which features low auto-fluorescence, biocompatibility and manufacturability by hot-embossing. The RNA retrieval was carried on after bacteria heat-lysis by an on-chip micro-heater, whose function was characterized at different working parameters. Carbon resistive temperature sensors were tested, characterized and printed on the biochip sealing film to monitor the heating process. Off-chip and on-chip processed RNA were hybridized with capture probes on the reaction chamber surface and identification was achieved by detection of fluorescence tags. The application of the mentioned techniques and materials proved to allow the development of low-cost, disposable albeit multi-functional microfluidic system, performing heating, temperature sensing and chemical reaction processes in the same device. By proving its effectiveness, this device contributes a reference to show the integration potential of fully thermoplastic devices in biosensor systems.

scholarly journals A low-cost wireless endoscope camera: a preliminary report

2021 ◽  
Vol 27 (1) ◽  
Author(s):  
J. M. Lazarus ◽  
M. Ncube
Keyword(s):  
Minimally Invasive Surgery ◽  
Minimally Invasive ◽  
Video Transmission ◽  
Low Cost ◽  
Battery Life ◽  
Resource Constrained ◽  
High Definition ◽  
Industry Standard ◽  
Constrained Environments ◽  
The Cost

Abstract Background Technology currently used for surgical endoscopy was developed and is manufactured in high-income economies. The cost of this equipment makes technology transfer to resource constrained environments difficult. We aimed to design an affordable wireless endoscope to aid visualisation during rigid endoscopy and minimally invasive surgery (MIS). The initial prototype aimed to replicate a 4-mm lens used in rigid cystoscopy. Methods Focus was placed on using open-source resources to develop the wireless endoscope to significantly lower the cost and make the device accessible for resource-constrained settings. An off the shelf miniature single-board computer module was used because of its low cost (US$10) and its ability to handle high-definition (720p) video. Open-source Linux software made monitor mode (“hotspot”) wireless video transmission possible. A 1280 × 720 pixel high-definition tube camera was used to generate the video signal. Video is transmitted to a standard laptop computer for display. Bench testing included latency of wireless digital video transmission. Comparison to industry standard wired cameras was made including weight and cost. The battery life was also assessed. Results In comparison with industry standard cystoscope lens, wired camera, video processing unit and light source, the prototype costs substantially less. (US$ 230 vs 28 000). The prototype is light weight (184 g), has no cables tethering and has acceptable battery life (of over 2 h, using a 1200 mAh battery). The camera transmits video wirelessly in near real time with only imperceptible latency of < 200 ms. Image quality is high definition at 30 frames per second. Colour rendering is good, and white balancing is possible. Limitations include the lack of a zoom. Conclusion The novel wireless endoscope camera described here offers equivalent high-definition video at a markedly reduced cost to contemporary industry wired units and could contribute to making minimally invasive surgery possible in resource-constrained environments.

scholarly journals A Survey on Deep Learning Based Methods and Datasets for Monocular 3D Object Detection

Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 517
Author(s):  
Seong-heum Kim ◽  
Youngbae Hwang
Keyword(s):  
Deep Learning ◽  
Object Detection ◽  
Low Cost ◽  
Detection Methods ◽  
Future Research ◽  
3D Object ◽  
Practical Applications ◽  
Depth Sensors ◽  
Significant Research ◽  
3D Object Detection

Owing to recent advancements in deep learning methods and relevant databases, it is becoming increasingly easier to recognize 3D objects using only RGB images from single viewpoints. This study investigates the major breakthroughs and current progress in deep learning-based monocular 3D object detection. For relatively low-cost data acquisition systems without depth sensors or cameras at multiple viewpoints, we first consider existing databases with 2D RGB photos and their relevant attributes. Based on this simple sensor modality for practical applications, deep learning-based monocular 3D object detection methods that overcome significant research challenges are categorized and summarized. We present the key concepts and detailed descriptions of representative single-stage and multiple-stage detection solutions. In addition, we discuss the effectiveness of the detection models on their baseline benchmarks. Finally, we explore several directions for future research on monocular 3D object detection.

Sign in / Sign up

Export Citation Format

Share Document