Enhancing embedded AI-based object detection using multi-view approach - Archive ouverte HAL Access content directly
Conference Papers Year :

Enhancing embedded AI-based object detection using multi-view approach

(1, 2) , (1) , (1, 2) , (3)
1
2
3

Abstract

Object detection based on convolutional neural network (CNN) is widely used in multitude emergent applications. Yet, the deployment of CNNs on embedded devices at the edge with reduced resources and power budget poses a real challenge. In this paper, we address this issue by enhancing the detection performance without impacting the inference speed. We investigate the use of multi-view for the same scene to achieve better detection performance. A novel system of distributed smart cameras is proposed where each camera integrates a CNN for detection. Implementation results show that using light networks on the distributed cameras can lead to better detection performance and a reduction in the overall consumed power.
Fichier principal
Vignette du fichier
Enhancing_embedded_AI_based_object_detection_using_multi_view_approach_Final.pdf (3.37 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03836472 , version 1 (02-11-2022)

Identifiers

  • HAL Id : hal-03836472 , version 1

Cite

Zijie Ning, Mostafa Rizk, Amer Baghdadi, Jean-Philippe Diguet. Enhancing embedded AI-based object detection using multi-view approach. IEEE International Workshop on Rapid System Prototyping (RSP), part of Embedded Systems Week (ESWEEK), Oct 2022, Shanghai, China. ⟨hal-03836472⟩
0 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More