Smart camera design for intensive embedded computing

Heyrman, Barthélémy; Paindavoine, Michel; Schmit, Renaud; Letellier, Laurent; Collette, T.

doi:10.1016/j.rti.2005.04.006

Cited by 11 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current system lost the marker(s) above 208 s À1 because of its low sample rate. An embedded system dedicated to real-time image processing and movement analysis could enhance time resolution and marker extraction [8][9][10]. We are designing a new system using a fast CMOS sensor (250 images per second) connected to an embedded programmable device (FPGA) able to perform marker extraction in a very short time (less than 10 ms).…”

Section: Discussionmentioning

confidence: 99%

Measuring trunk orientation with a CMOS camera: Feasibility and accuracy

et al. 2007

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Measuring trunk orientation with a CMOS camera: Feasibility and accuracy

et al. 2007

View full text Add to dashboard Cite

“…Many articles have been published on image-processing technology applications used to inspect the quality of a product (Sturgill and Detrick, 1986;Lahajnar et al, 2002;Ranky, 2003;Ghita et al, 2006;Patel et al, 2012). One example is the bottling industry, in which image recognition technology made human inspections redundant (Heyrman et al, 2005). In the bottling industry, bottles are taken out of service if they are not filled correctly or if the label is missing or misaligned.…”

Section: Digital Image Analysismentioning

confidence: 99%

Condition-based maintenance for major airport baggage systems

Koenig

Found

Kumar

et al. 2020

JMTM

View full text Add to dashboard Cite

PurposeThe aim of this paper is to develop a contribution to knowledge that adds to the empirical evidence of predictive condition-based maintenance by demonstrating how the availability and reliability of current assets can be improved without costly capital investment, resulting in overall system performance improvementsDesign/methodology/approachThe empirical, experimental approach, technical action research (TAR), was designed to study a major Middle Eastern airport baggage handling operation. A predictive condition-based maintenance prototype station was installed to monitor the condition of a highly complex system of static and moving assets.FindingsThe research provides evidence that the performance frontier for airport baggage handling systems can be improved using automated dynamic monitoring of the vibration and digital image data on baggage trays as they pass a service station. The introduction of low-end innovation, which combines advanced technology and low-cost hardware, reduced asset failures in this complex, high-speed operating environment.Originality/valueThe originality derives from the application of existing hardware with the combination of edge and cloud computing software through architectural innovation, resulting in adaptations to an existing baggage handling system within the context of a time-critical logistics system.

show abstract

“…Other works related to the use of a CMOS associated to a processor are. [7][8][9] In all these works, the computation module is simple and not powerful enough to solve complex problems. However, recent works, 5,10,11 demonstrate the ability of smart cameras to reach performance beyond the power of recent microprocessors by exploiting dedicated hardware as the FPGA.…”

Section: Smart Camerasmentioning

confidence: 99%

Cost-efficient RGB-D smart camera for people detection and tracking

Carraro

Munaro

Menegatti

2016

J. Electron. Imaging

View full text Add to dashboard Cite

We describe a software library we developed for efficiently using the Kinect v2, a time-of-flight RGB-D sensor, with an embedded system, the NVidia Jetson TK1, as a cost-efficient RGB-D smart camera for people detection and tracking. The speed-up needed for achieving real-time operation has been obtained using NVidia CUDA to concurrently generate and process the raw depth and infrared data and to create the three-dimensional point cloud. This library has been released as open source and the smart camera has been tested in real-world scenarios, as a people-detection node in an open-source multinode RGB-D tracking system (OpenPTrack) and onboard a service robot for endowing it with robust people-following capabilities. Moreover, we show that nonembedded computers also can benefit from our library in terms of people-detection frame rate

show abstract

Smart camera design for intensive embedded computing

Cited by 11 publications

References 6 publications

Measuring trunk orientation with a CMOS camera: Feasibility and accuracy

Measuring trunk orientation with a CMOS camera: Feasibility and accuracy

Condition-based maintenance for major airport baggage systems

Cost-efficient RGB-D smart camera for people detection and tracking

Contact Info

Product

Resources

About