scholarly journals Exploring the Vision Processing Unit as Co-Processor for Inference

2018 ◽  
Author(s):  
Sergio Rivas-Gomez ◽  
Antonio J. Pena ◽  
David Moloney ◽  
Erwin Laure ◽  
Stefano Markidis
Keyword(s):  
Processing Unit ◽  
Vision Processing

Design and Implementation of a Computer Vision Based Inspection System Using CUDA

2011 ◽  
Vol 383-390 ◽  
pp. 18-24
Author(s):  
Yan Shi ◽  
Ai Guo Li ◽  
Lin Wang
Keyword(s):  
Computer Vision ◽  
Graphic Processing Unit ◽  
Work Conditions ◽  
Inspection System ◽  
Processing Unit ◽  
Device Architecture ◽  
Vision Processing ◽  
And Performance ◽  
Hardware In Loop ◽  
Real Vehicle

In the production process of electronic Instrument Clusters (IC) used in automobiles, a need for automated inspection of dynamic characteristics is identified. An inspection system based on hardware-in-loop emulation and computer vision using Computer Unified Device Architecture (CUDA) is proposed. The system generates network signals that emulate a real vehicle, sends the signals to an IC to turn it into various work conditions, captures the IC’s response into a graphic processing unit for real-time computer-vision processing and records inspection results into databases. An implementation of the design and performance analysis is provided.

scholarly journals A Hybrid Vision Processing Unit with a Pipelined Workflow for Convolutional Neural Network Accelerating and Image Signal Processing

Electronics ◽  
2021 ◽  
Vol 10 (23) ◽  
pp. 2989
Author(s):  
Peng Liu ◽  
Yan Song
Keyword(s):  
Signal Processing ◽  
Data Transmission ◽  
High Speed ◽  
High Efficiency ◽  
State Of The Art ◽  
Vision System ◽  
Processing Unit ◽  
Processing Elements ◽  
Vision Processing ◽  
Field Programmable

Vision processing chips have been widely used in image processing and recognition tasks. They are conventionally designed based on the image signal processing (ISP) units directly connected with the sensors. In recent years, convolutional neural networks (CNNs) have become the dominant tools for many state-of-the-art vision processing tasks. However, CNNs cannot be processed by a conventional vision processing unit (VPU) with a high speed. On the other side, the CNN processing units cannot process the RAW images from the sensors directly and an ISP unit is required. This makes a vision system inefficient with a lot of data transmission and redundant hardware resources. Additionally, many CNN processing units suffer from a low flexibility for various CNN operations. To solve this problem, this paper proposed an efficient vision processing unit based on a hybrid processing elements array for both CNN accelerating and ISP. Resources are highly shared in this VPU, and a pipelined workflow is introduced to accelerate the vision tasks. We implement the proposed VPU on the Field-Programmable Gate Array (FPGA) platform and various vision tasks are tested on it. The results show that this VPU achieves a high efficiency for both CNN processing and ISP and shows a significant reduction in energy consumption for vision tasks consisting of CNNs and ISP. For various CNN tasks, it maintains an average multiply accumulator utilization of over 94% and achieves a performance of 163.2 GOPS with a frequency of 200 MHz.

scholarly journals Toward Monitoring and Increasing Exercise Adherence in Older Adults by Robotic Intervention: A Proof of Concept Study

2011 ◽  
Vol 2011 ◽  
pp. 1-11 ◽  
Author(s):  
Prathik Gadde ◽  
Hadi Kharrazi ◽  
Himalaya Patel ◽  
Karl F. MacDorman
Keyword(s):  
Older Adults ◽  
Exercise Program ◽  
Exercise Adherence ◽  
Cognitive Stimulation ◽  
Processing Unit ◽  
Assistive Robots ◽  
Socially Assistive Robots ◽  
Vision Processing ◽  
Personal Trainer ◽  
Pencil And Paper

Socially assistive robots have the potential to improve the quality of life of older adults by encouraging and guiding their performance of rehabilitation exercises while offering cognitive stimulation and companionship. This study focuses on the early stages of developing and testing an interactive personal trainer robot to monitor and increase exercise adherence in older adults. The robot physically demonstrates exercises for the user to follow and monitors the user's progress using a vision-processing unit that detects face and hand movements. When the user successfully completes a move, the robot gives positive feedback and begins the next repetition. The results of usability testing with 10 participants support the feasibility of this approach. Further extensions are planned to evaluate a complete exercise program for improving older adults' physical range of motion in a controlled experiment with three conditions: a personal trainer robot, a personal trainer on-screen character, and a pencil-and-paper exercise plan.

Always-on Vision Processing Unit for Mobile Applications

IEEE Micro ◽  
2015 ◽  
Vol 35 (2) ◽  
pp. 56-66 ◽  
Author(s):  
Brendan Barry ◽  
Cormac Brick ◽  
Fergal Connor ◽  
David Donohoe ◽  
David Moloney ◽  
...  
Keyword(s):  
Mobile Applications ◽  
Processing Unit ◽  
Vision Processing

Evaluation of Microbial Load from Canned Soya Milk Drinks in Malaysia

2016 ◽  
Vol 2 (1) ◽  
pp. 22-25
Author(s):  
Nur Amalina binti Mustafa ◽  
Muhammad Ashraf bin Redzuan ◽  
Muhamad Hazim bin Zuraimi ◽  
Muhamad Shuhaimi bin Shuib ◽  
Shahnaz Majeed ◽  
...  
Keyword(s):  
Culture Media ◽  
Storage Condition ◽  
Storage Conditions ◽  
Nutrient Agar ◽  
Microbial Load ◽  
Blood Agar ◽  
Human Consumption ◽  
Processing Unit ◽  
Soya Milk ◽  
Two Samples

Objective: Owing to the habit of consuming ready food among the citizens of Malaysia a study was conducted to evaluate 20 samples of canned soya milk for the presence of possible microbial content. The samples were collected randomly from shopping malls, restaurants and kiosk in Ipoh Malaysia. Methods: All samples collected across Ipoh, were subjected to test for presence bacteria in nutrient agar, blood agar and macConkey media. The possible microbial load was swapped from surface and soya milk content with a sterile cotton and streaked on nutrient agar, blood agar and macConkey culture media. The streaked petri plates were incubated for 48 hours at 37oC. Results: The study revealed negative microbial growth in all except two samples from the surface and soya milk content collected from a restaurant in nutrient agar and blood agar medium. The presence of microbes was conformed as gram positive staphylococcus sp. through gram staining. The positive growth may be imputed to poor storage condition at the restaurant. Conclusion: It can be computed from the study that the majority of the samples were free from bacterial growth, suggesting strong in house quality control mechanism at the processing unit and exquisite storage conditions in malls and kiosk suggesting that soya milk available in malls and kiosk are fit for human consumption.

cognitive-pragmatic account of the English imperative-conditional construction

2016 ◽  
Vol 1 (2) ◽  
pp. 251-269
Author(s):  
Keding Zhang
Keyword(s):  
Cognitive Linguistics ◽  
Processing Unit ◽  
Pragmatic Approach ◽  
The Third ◽  
Pragmatic Enrichment ◽  
Symbolic Structure ◽  
Speaker Intentions ◽  
Interactive Relationship ◽  
Pragmatic Account ◽  
Everyday Communication

The imperative-conditional construction (ICC) in English is a type of construction which consists of an ordinary imperative clause and an ordinary declarative clause connected by the connective and or or. This article deals with the speaker intentions of ICCs and their motivations from a cognitive-pragmatic approach. Based on the concept of construction in cognitive linguistics, an ICC can be called a complex symbolic structure which, though composed of two components, should be regarded as a single pragmatic processing unit. It is demonstrated that, in everyday communication, the ICC can usually convey three kinds of speaker intentions: a prohibitive intention, an inducing/forcing intention, and an advisory intention. The first refers to the intention of the speaker to prohibit the hearer from carrying out the act described by the imperative. The second is the intention of the speaker to induce or force the hearer to bring about the act described by the imperative. The third refers to the intention of the speaker to advise the hearer to carry out the act described by the imperative. These speaker intentions are highly motivated. The motivations include the constructional context, the conditional relation between the imperative and the declarative, the directive force of the imperative, the pragmatic enrichment of the declarative, and the complementary and interactive relationship between the imperative and declarative clauses, among which the constructional context serves as an overall motivation, and the rest may be seen as specific motivations.

A High Performance Image Processing Unit for On-orbit Servicing

2006 ◽  
Author(s):  
Hiroshi Yamamoto ◽  
Yasufumi Nagai ◽  
Shinichi Kimura ◽  
Hiroshi Takahashi ◽  
Satoko Mizumoto ◽  
...  
Keyword(s):  
Image Processing ◽  
High Performance ◽  
Processing Unit
Sign in / Sign up

Export Citation Format

Share Document