scholarly journals Portable device for presbyopia correction with optoelectronic lenses driven by pupil response

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Juan Mompeán ◽  
Juan L. Aragón ◽  
Pablo Artal
Keyword(s):  
Image Processing ◽  
Visual Acuity ◽  
Real Time ◽  
Portable Device ◽  
Pupil Response ◽  
Image Processing Algorithms ◽  
Processing Algorithms ◽  
Pupil Tracking ◽  
Presbyopia Correction ◽  
High Range

AbstractA novel portable device has been developed and built to dynamically, and automatically, correct presbyopia by means of a couple of opto-electronics lenses driven by pupil tracking. The system is completely portable providing with a high range of defocus correction up to 10 D. The glasses are controlled and powered by a smartphone. To achieve a truly real-time response, image processing algorithms have been implemented in OpenCL and ran on the GPU of the smartphone. To validate the system, different visual experiments were carried out in presbyopic subjects. Visual acuity was maintained nearly constant for a range of distances from 5 m to 20 cm.

High-Speed Image Processing Algorithms for Real-Time Detection of MARFEs on JET

2012 ◽  
Vol 40 (12) ◽  
pp. 3485-3492 ◽  
Author(s):  
Márcio Portes de Albuquerque ◽  
Marcelo Portes de Albuquerque ◽  
Germano T. Chacon ◽  
E. L. de Faria ◽  
Andrea Murari
Keyword(s):  
Image Processing ◽  
Real Time ◽  
High Speed ◽  
Image Processing Algorithms ◽  
Processing Algorithms ◽  
Real Time Detection ◽  
High Speed Image Processing

scholarly journals Road Object Detection: A Comparative Study of Deep Learning-Based Algorithms

Electronics ◽  
2021 ◽  
Vol 10 (16) ◽  
pp. 1932
Author(s):  
Malik Haris ◽  
Adam Glowacz
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Object Detection ◽  
Real Time ◽  
Large Scale ◽  
Single Shot ◽  
Automated Driving ◽  
Convolutional Network ◽  
Image Processing Algorithms ◽  
Processing Algorithms

Automated driving and vehicle safety systems need object detection. It is important that object detection be accurate overall and robust to weather and environmental conditions and run in real-time. As a consequence of this approach, they require image processing algorithms to inspect the contents of images. This article compares the accuracy of five major image processing algorithms: Region-based Fully Convolutional Network (R-FCN), Mask Region-based Convolutional Neural Networks (Mask R-CNN), Single Shot Multi-Box Detector (SSD), RetinaNet, and You Only Look Once v4 (YOLOv4). In this comparative analysis, we used a large-scale Berkeley Deep Drive (BDD100K) dataset. Their strengths and limitations are analyzed based on parameters such as accuracy (with/without occlusion and truncation), computation time, precision-recall curve. The comparison is given in this article helpful in understanding the pros and cons of standard deep learning-based algorithms while operating under real-time deployment restrictions. We conclude that the YOLOv4 outperforms accurately in detecting difficult road target objects under complex road scenarios and weather conditions in an identical testing environment.

Near real time monitoring of snow cover using webcam imagery

2020 ◽  
Author(s):  
Cemal Melih Tanis ◽  
Ali Nadir Arslan ◽  
Miina Rautiainen
Keyword(s):  
Image Processing ◽  
Snow Cover ◽  
Real Time ◽  
Forest Canopy ◽  
Time Lapse ◽  
Camera Networks ◽  
Finnish Meteorological Institute ◽  
Image Processing Algorithms ◽  
Processing Algorithms

<p>Environmental camera networks are growing in usage in different parts of the globe. Time series of webcam imagery from the camera networks are used in estimating snow cover properties. Fractional snow cover (FSC) and snow depth (SD) are two important parameters which can be estimated from the webcam imagery using image processing algorithms. Monitoring of snow cover from webcam imagery has the potential to be used in gap filling and validation of satellite derived products. It can also be used as a data source for snow monitoring in remote areas where manual measurements and in-situ sensor installation and maintenance are costly, especially under forest canopy which retrieval of signal from ground by satellites is a challenge. In this paper, we have used multiple webcams from MONIMET Camera Network in Finland and Finnish Meteorological Institute Image Processing Toolbox (FMIPROT) on the cloud to establish an automated processing chain which reports FSC and SD estimations in near real time, available in FMIPROT website. Image processing algorithms are implemented in the toolbox, the images from last year are also processed and the results are compared with ultrasonic in-situ measurements and values generated by visual inspections on images. In the website, estimations from the day-time images of the latest one month are visualized on interactive plots, along with time-lapse animations of images, with a latency of 3 hours.</p>

Sign in / Sign up

Export Citation Format

Share Document