Adaptive Queue Management in Embedded Edge Devices for Object Detection with Low Latency

Yang, Yousung; Kim, Jingyeom; Lee, Joohyung; Lee, Seongsoo; Hong, Suk Bong; Newaz, S. H. Shah

doi:10.1109/ictc49870.2020.9289509

Cited by 3 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The testing is carried out by MATLAB and the accuracy prediction can be carried out by using Evaluation Board (EVB). Yang et al (2020) The queue management of object detection (QMOD) is connected to the IP camera which captures the video footages via internet of things as send to the cloud, which converts the videos into ip packages and stored in the adaptive queue typically so other than the static queue size, makes the capturing as fast and comfort of video irrespective of the size. The computation of the Xavier, Jetson and Nano were verified and observed that latency has been observed between 80%-90% and implemented by means of python 3.7.…”

Section: Objectivesmentioning

confidence: 99%

Real-time Object Prediction by Collaboration of IOT and Deep Learning

Parimala,

Bhoopal,

kumar

et al. 2022

Proceedings of the International Conference on Industrial Engineering and Operations Management

View full text Add to dashboard Cite

Object detection or the prediction of the objects in the image form can be performed in tremendous ways as a general means. Here we are detecting the objects by the collaboration of the deep-learning along with the IOT technology, so that the predicting system or PC will be in one place and the capturing smart phones will be in someother place, using IOT the auto capturing, and the detection of object along will label of name is achieved with one of the pre-trained neural networks in deep learning called Google net. So as to reduce the training time and the accurate prediction of the object can be obtained. The object detection is probability checked out or compared out between the prediction accuracy inside state and the other state. And the time taken for the prediction of the objects is also made into concern. In this paper the simple smart phones which can be available with everyone's hand the object detection is handled out in the real-time and predicted with the personal computer with the booming technologies.

show abstract

Section: Objectivesmentioning

confidence: 99%

Real-time Object Prediction by Collaboration of IOT and Deep Learning

Parimala,

Bhoopal,

kumar

et al. 2022

Proceedings of the International Conference on Industrial Engineering and Operations Management

View full text Add to dashboard Cite

show abstract

“…However, some advanced IoT devices with edge intelligence, e.g. Raspberry Pis and the Jetson series toolkit from Nvidia, can now be programmed to promptly respond to changes in the external environment [9], [10], and can also be deployed with deep learning algorithms to satisfy stringent low-latency transmission requirements for time-sensitive IoT applications [11], [12]. This approach does not sufficiently cater for a practical situation where groups of IoT devices may work collaboratively with limited operational resources enforced by the external environment.…”

Section: Introductionmentioning

confidence: 99%