Towards Fine-Grained Online Adaptive Approximation Control for Dense SLAM on Embedded GPUs

2022 ◽  
Vol 27 (2) ◽  
pp. 1-19
Author(s):  
Tiancong Bu ◽  
Kaige Yan ◽  
Jingweijia Tan
Keyword(s):  
Energy Saving ◽  
Real Time ◽  
High Accuracy ◽  
Important Application ◽  
The Other ◽  
Approximation Techniques ◽  
Fine Grained ◽  
Critical Data ◽  
Adaptive Approximation ◽  
Adaptive Approximation Control

Dense SLAM is an important application on an embedded environment. However, embedded platforms usually fail to provide enough computation resources for high-accuracy real-time dense SLAM, even with high-parallelism architecture such as GPUs. To tackle this problem, one solution is to design proper approximation techniques for dense SLAM on embedded GPUs. In this work, we propose two novel approximation techniques, critical data identification and redundant branch elimination. We also analyze the error characteristics of the other two techniques—loop skipping and thread approximation. Then, we propose SLaPP, an online adaptive approximation controller, which aims to control the error to be under an acceptable threshold. The evaluation shows SLaPP can achieve 2.0× performance speedup and 30% energy saving on average compared to the case without approximation.

scholarly journals Dtree2vec: A High-Accuracy and Dynamic Scheme for Real-Time Book Recommendation by Serialized Chapters and Local Fine-Grained Partitioning

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 23197-23208
Author(s):  
Huaxuan Zhao ◽  
Hongchen Wu ◽  
Jingzhi Li ◽  
Huaxiang Zhang ◽  
Xinjun Wang
Keyword(s):  
Real Time ◽  
High Accuracy ◽  
Fine Grained

Real Time Person Recognition and Attendance Marking Using Holistic Based Approach

2017 ◽  
Vol 7 (7) ◽  
pp. 302
Author(s):  
Reshma P ◽  
Muneer VK ◽  
Muhammed Ilyas P
Keyword(s):  
Face Recognition ◽  
Real Time ◽  
High Accuracy ◽  
Efficient Technique ◽  
Human Face ◽  
Traditional Methods ◽  
Person Recognition ◽  
The Face

Face recognition is a challenging task for the researches. It is very useful for personal verification and recognition and also it is very difficult to implement due to all different situation that a human face can be found. This system makes use of the face recognition approach for the computerized attendance marking of students or employees in the room environment without lectures intervention or the employee. This system is very efficient and requires very less maintenance compared to the traditional methods. Among existing methods PCA is the most efficient technique. In this project Holistic based approach is adapted. The system is implemented using MATLAB and provides high accuracy.

scholarly journals Augmented Reality Maintenance Assistant Using YOLOv5

2021 ◽  
Vol 11 (11) ◽  
pp. 4758
Author(s):  
Ana Malta ◽  
Mateus Mendes ◽  
Torres Farinha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Object Recognition ◽  
Augmented Reality ◽  
Real Time ◽  
Recognition System ◽  
High Accuracy ◽  
Video Streams ◽  
The Neural Network ◽  
Deep Learning Neural Network

Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.

scholarly journals Evaluating Latency in Multiprocessing Embedded Systems for the Smart Grid

Energies ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 3322
Author(s):  
Sara Alonso ◽  
Jesús Lázaro ◽  
Jaime Jiménez ◽  
Unai Bidarte ◽  
Leire Muguira
Keyword(s):  
Operating System ◽  
Smart Grid ◽  
Real Time ◽  
Processing System ◽  
The Other ◽  
Programmable Logic ◽  
Detailed Characterization ◽  
Timing Constraint ◽  
Time Part

Smart grid endpoints need to use two environments within a processing system (PS), one with a Linux-type operating system (OS) using the Arm Cortex-A53 cores for management tasks, and the other with a standalone execution or a real-time OS using the Arm Cortex-R5 cores. The Xen hypervisor and the OpenAMP framework allow this, but they may introduce a delay in the system, and some messages in the smart grid need a latency lower than 3 ms. In this paper, the Linux thread latencies are characterized by the Cyclictest tool. It is shown that when Xen hypervisor is used, this scenario is not suitable for the smart grid as it does not meet the 3 ms timing constraint. Then, standalone execution as the real-time part is evaluated, measuring the delay to handle an interrupt created in programmable logic (PL). The standalone application was run in A53 and R5 cores, with Xen hypervisor and OpenAMP framework. These scenarios all met the 3 ms constraint. The main contribution of the present work is the detailed characterization of each real-time execution, in order to facilitate selecting the most suitable one for each application.

scholarly journals Neutron Imaging Using a Fine-Grained Nuclear Emulsion

2021 ◽  
Vol 7 (1) ◽  
pp. 4
Author(s):  
Katsuya Hirota ◽  
Tomoko Ariga ◽  
Masahiro Hino ◽  
Go Ichikawa ◽  
Shinsuke Kawasaki ◽  
...  
Keyword(s):  
Image Analysis ◽  
High Resolution ◽  
Neutron Detector ◽  
Nuclear Emulsion ◽  
Neutron Imaging ◽  
The Other ◽  
Crystal Oscillator ◽  
Fine Grained ◽  
Cold Neutrons ◽  
Track Analysis

A neutron detector using a fine-grained nuclear emulsion has a sub-micron spatial resolution and thus has potential to be applied as high-resolution neutron imaging. In this paper, we present two approaches to applying the emulsion detectors for neutron imaging. One is using a track analysis to derive the reaction points for high resolution. From an image obtained with a 9 μm pitch Gd grating with cold neutrons, periodic peak with a standard deviation of 1.3 μm was observed. The other is an approach without a track analysis for high-density irradiation. An internal structure of a crystal oscillator chip, with a scale of approximately 30 μm, was able to be observed after an image analysis.

scholarly journals A Machine Vision Approach for Bioreactor Foam Sensing

2021 ◽  
pp. 247263032110088
Author(s):  
Jonas Austerjost ◽  
Robert Söldner ◽  
Christoffer Edlund ◽  
Johan Trygg ◽  
David Pollard ◽  
...  
Keyword(s):  
Machine Learning ◽  
Machine Vision ◽  
State Of The Art ◽  
Low Cost ◽  
High Accuracy ◽  
Consumer Electronics ◽  
Learning System ◽  
Automotive Applications ◽  
Fine Grained

Machine vision is a powerful technology that has become increasingly popular and accurate during the last decade due to rapid advances in the field of machine learning. The majority of machine vision applications are currently found in consumer electronics, automotive applications, and quality control, yet the potential for bioprocessing applications is tremendous. For instance, detecting and controlling foam emergence is important for all upstream bioprocesses, but the lack of robust foam sensing often leads to batch failures from foam-outs or overaddition of antifoam agents. Here, we report a new low-cost, flexible, and reliable foam sensor concept for bioreactor applications. The concept applies convolutional neural networks (CNNs), a state-of-the-art machine learning system for image processing. The implemented method shows high accuracy for both binary foam detection (foam/no foam) and fine-grained classification of foam levels.

scholarly journals Global-Local Enhancement Network for NMF-Aware Sign Language Recognition

2021 ◽  
Vol 17 (3) ◽  
pp. 1-19
Author(s):  
Hezhen Hu ◽  
Wengang Zhou ◽  
Junfu Pu ◽  
Houqiang Li
Keyword(s):  
Sign Language ◽  
Daily Life ◽  
The Other ◽  
Challenging Problem ◽  
Language Recognition ◽  
Local Enhancement ◽  
Sign Language Recognition ◽  
Vocabulary Size ◽  
Hand Gestures ◽  
Fine Grained

Sign language recognition (SLR) is a challenging problem, involving complex manual features (i.e., hand gestures) and fine-grained non-manual features (NMFs) (i.e., facial expression, mouth shapes, etc .). Although manual features are dominant, non-manual features also play an important role in the expression of a sign word. Specifically, many sign words convey different meanings due to non-manual features, even though they share the same hand gestures. This ambiguity introduces great challenges in the recognition of sign words. To tackle the above issue, we propose a simple yet effective architecture called Global-Local Enhancement Network (GLE-Net), including two mutually promoted streams toward different crucial aspects of SLR. Of the two streams, one captures the global contextual relationship, while the other stream captures the discriminative fine-grained cues. Moreover, due to the lack of datasets explicitly focusing on this kind of feature, we introduce the first non-manual-feature-aware isolated Chinese sign language dataset (NMFs-CSL) with a total vocabulary size of 1,067 sign words in daily life. Extensive experiments on NMFs-CSL and SLR500 datasets demonstrate the effectiveness of our method.

scholarly journals I.—Microscopic Structure of Irish Granites. No. 2. Granite of Aillemore, Co. Mayo

1874 ◽  
Vol 1 (1) ◽  
pp. 1-2
Author(s):  
Edward Hull
Keyword(s):  
The Other ◽  
Microscopic Structure ◽  
South Side ◽  
North West ◽  
Fine Grained ◽  
Lower Silurian ◽  
The North ◽  
Geological Map ◽  
Vertical Walls ◽  
Dark Green

This granite forms an isolated mass, rising into two eminences a few miles south of Louisburg, called Corvock Brack (1287 feet) and Knockaskeheen (1288 feet). It is a greyish granite—generally fine—grained—consisting of quartz, two felspars,—one orthoclase, the other triclinic, probably oligoclase—and dark green mica. In some places there are patches in which the felspar assumes the appearance of “graphic granite.” Numerous boulders of this granite are strewn over the district to the north-west, and on the south side of Knockaskeheen; the rock is traversed by regular joints ranging N. 10 W., along which it splits off into nearly vertical walls. The position of the granite is shown on Griffith's Geological Map of Ireland, and it is surrounded by schistose beds, generally metamorphosed, and probably of Lower Silurian age. The granite itself is of older date than the Upper Llandovery beds, which lie to the southward.

Sign in / Sign up

Export Citation Format

Share Document