Assessing the influence of temperature variations on the geometrical properties of a low-cost calibrated camera system by using computer vision procedures

2011 ◽  
Vol 23 (5) ◽  
pp. 953-966 ◽  
Author(s):  
Peter Podbreznik ◽  
Božidar Potočnik
Keyword(s):  
Computer Vision ◽  
Low Cost ◽  
Camera System ◽  
Temperature Variations ◽  
Influence Of Temperature ◽  
Geometrical Properties

Kameraunterstützte Verschwendungsreduktion*/Computer-vision supported waste reduction in lean production

2017 ◽  
Vol 107 (09) ◽  
pp. 572-577
Author(s):  
B. Prof. Lorenz ◽  
I. Kaltenmark
Keyword(s):  
Computer Vision ◽  
Lean Manufacturing ◽  
Lean Production ◽  
Low Cost ◽  
Industrie 4.0 ◽  
Waste Reduction ◽  
Camera System ◽  
New Developments ◽  
Neue Entwicklungen

In modernen Produktionen ist Lean Manufacturing einer der wichtigsten Treiber für Produktivitätssteigerungen. Durch neue Entwicklungen im Bereich Industrie 4.0 können Impulse im Lean Manufacturing gegeben werden. An der OTH Regensburg wird getestet, wie kostengünstige Kamerasysteme helfen können, Verschwendungen sichtbar zu machen und zu minimieren. Es zeigt sich, dass auch mit geringen Investitionskosten neue Potentiale zur Verschwendungsreduktion aufgedeckt werden können.   In modern production lean manufacturing is one of the most effective drivers for productivity. Due to new developments in the Industrie 4.0-campaign new impulses can be given into lean manufacturing. Experiments at OTH Regensburg indicate that a low-cost camera system can help to make waste visible and minimize it. This shows that with low invest costs, new potentials for waste reduction can be revealed.

scholarly journals Smart Video Surveillance System Based on Edge Computing

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2958
Author(s):  
Antonio Carlos Cob-Parro ◽  
Cristina Losada-Gutiérrez ◽  
Marta Marrón-Romera ◽  
Alfredo Gardel-Vicente ◽  
Ignacio Bravo-Muñoz
Keyword(s):  
Computer Vision ◽  
Video Surveillance ◽  
Surveillance System ◽  
Video Surveillance System ◽  
Smart Camera ◽  
People Detection ◽  
Camera System ◽  
Edge Node ◽  
New Processing ◽  
Processor Unit

New processing methods based on artificial intelligence (AI) and deep learning are replacing traditional computer vision algorithms. The more advanced systems can process huge amounts of data in large computing facilities. In contrast, this paper presents a smart video surveillance system executing AI algorithms in low power consumption embedded devices. The computer vision algorithm, typical for surveillance applications, aims to detect, count and track people’s movements in the area. This application requires a distributed smart camera system. The proposed AI application allows detecting people in the surveillance area using a MobileNet-SSD architecture. In addition, using a robust Kalman filter bank, the algorithm can keep track of people in the video also providing people counting information. The detection results are excellent considering the constraints imposed on the process. The selected architecture for the edge node is based on a UpSquared2 device that includes a vision processor unit (VPU) capable of accelerating the AI CNN inference. The results section provides information about the image processing time when multiple video cameras are connected to the same edge node, people detection precision and recall curves, and the energy consumption of the system. The discussion of results shows the usefulness of deploying this smart camera node throughout a distributed surveillance system.

scholarly journals An Automated Light Trap to Monitor Moths (Lepidoptera) Using Computer Vision-Based Tracking and Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 343
Author(s):  
Kim Bjerge ◽  
Jakob Bonde Nielsen ◽  
Martin Videbæk Sepstrup ◽  
Flemming Helsing-Nielsen ◽  
Toke Thomas Høye
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Vision System ◽  
Low Cost ◽  
Light Trap ◽  
Automatic Monitoring ◽  
Light Sources ◽  
Monitoring Methods ◽  
Computer Vision System ◽  
Substantial Investment

Insect monitoring methods are typically very time-consuming and involve substantial investment in species identification following manual trapping in the field. Insect traps are often only serviced weekly, resulting in low temporal resolution of the monitoring data, which hampers the ecological interpretation. This paper presents a portable computer vision system capable of attracting and detecting live insects. More specifically, the paper proposes detection and classification of species by recording images of live individuals attracted to a light trap. An Automated Moth Trap (AMT) with multiple light sources and a camera was designed to attract and monitor live insects during twilight and night hours. A computer vision algorithm referred to as Moth Classification and Counting (MCC), based on deep learning analysis of the captured images, tracked and counted the number of insects and identified moth species. Observations over 48 nights resulted in the capture of more than 250,000 images with an average of 5675 images per night. A customized convolutional neural network was trained on 2000 labeled images of live moths represented by eight different classes, achieving a high validation F1-score of 0.93. The algorithm measured an average classification and tracking F1-score of 0.71 and a tracking detection rate of 0.79. Overall, the proposed computer vision system and algorithm showed promising results as a low-cost solution for non-destructive and automatic monitoring of moths.

Low-cost Smart Camera System for Water Stress Detection in Crops

2020 ◽  
Author(s):  
Paula Ramos-Giraldo ◽  
S. Chris Reberg-Horton ◽  
Steven Mirsky ◽  
Edgar Lobaton ◽  
Anna M. Locke ◽  
...  
Keyword(s):  
Water Stress ◽  
Low Cost ◽  
Smart Camera ◽  
Stress Detection ◽  
Camera System

One Touch Workpiece Verification System for CNC Machining Using a Low-Cost Computer Vision Approach

2016 ◽  
Author(s):  
Maxwell K. Micali ◽  
Hayley M. Cashdollar ◽  
Zachary T. Gima ◽  
Mitchell T. Westwood
Keyword(s):  
Computer Vision ◽  
Low Cost ◽  
Cnc Machining ◽  
Potential Operator ◽  
Cnc Milling ◽  
Machining Processes ◽  
Loop Control ◽  
Operator Error ◽  
Verification System ◽  
Milling Machines

While CNC programmers have powerful tools to develop optimized toolpaths and machining plans, these efforts can be wholly undermined by something as simple as human operator error during fixturing. This project addresses that potential operator error with a computer vision approach to provide coarse, closed-loop control between fixturing and machining processes. Prior to starting the machining cycle, a sensor suite detects the geometry that is currently fixtured using computer vision algorithms and compare this geometry to a CAD reference. If the detected and reference geometries are not similar, the machining cycle will not start, and an alarm will be raised. The outcome of this project is the proof of concept of a low-cost, machine/controller agnostic solution that is applied to CNC milling machines. The Workpiece Verification System (WVS) prototype implemented in this work cost a total of $100 to build, and all of the processing is performed on the self-contained platform. This solution has additional applications beyond milling that the authors are exploring.

FEASIBILITY ANALYSIS OF AN AUTOMATED DETECTION OF PHYSICAL DEFECT VIA COMPUTER VISION

2015 ◽  
Vol 76 (12) ◽  
Author(s):  
Por Jing Zhao ◽  
Shafriza Nisha Basah ◽  
Shazmin Aniza Abdul Shukor
Keyword(s):  
Computer Vision ◽  
Low Cost ◽  
Image Data ◽  
Automated Detection ◽  
Building Construction ◽  
High Demand ◽  
Major City ◽  
Cost System ◽  
Kinect Camera ◽  
Wall Condition

High demand of building construction has been taking places in the major city of Malaysia. However, despite this magnificent development, the lack of proper maintenance has caused a large portion of these properties deteriorated over time. The implementation of the project - Automated Detection of Physical Defect via Computer Vision - is a low cost system that helps to inspect the wall condition using Kinect camera. The system is able to classify the types of physical defects -crack and hole - and state its level of severity.The system uses artificial neural network as the image classifier due to its reliability and consistency. The validity of the system is shown using experiments on synthetic and real image data. This automated physical defect detection could detect building defect early, quickly, and easily, which results in cost saving and extending building life span. 

scholarly journals Annealing effects on luminescent properties of Eu3+ doped Gd2Zr2O7 nanopowders

2015 ◽  
Vol 47 (3) ◽  
pp. 269-272 ◽  
Author(s):  
M.S. Rabasovic ◽  
D. Sevic ◽  
J. Krizan ◽  
M.D. Rabasovic ◽  
N. Romcevic
Keyword(s):  
Low Cost ◽  
Emission Spectra ◽  
Luminescent Properties ◽  
Combustion Method ◽  
Luminescence Properties ◽  
Camera System ◽  
Strong Emission ◽  
Structure Morphology ◽  
Annealing Effects ◽  
Size And Morphology

In this report presented are structure, morphology and luminescence properties of nanopowders based on gadolinium zirconium oxide (Gd2Zr2O7) doped by europium ions (Eu3+). The nanopowders were prepared using a flame combustion method, the most frequently used process due to the simplicity and low cost of the synthesis procedures and also due to the possibility of tailoring the size and morphology of particles. The produced material is suitable for various optical devices. The luminescence properties of synthesized nanopowders were characterized by emission spectra and luminescence lifetimes obtained by using the streak camera system. Moreover, emission spectra were obtained and compared for powders as-obtained and after additional annealing at 1200o C. Luminescence emission spectra clearly show peaks characteristic for the strong emission lines at 611 nm and 630 nm corresponding to the 5D0 ? 7F2 long lived transition.

Sign in / Sign up

Export Citation Format

Share Document