Edge Camera System Using Dee p Learning Method with Model Compression on Embedded Applications

This paper proposes an edge camera system using a compressed deep learning model for enhanced Video surveillance Management System of Smart City that analyzes existing recorded video. The proposed edge camera at the end terminal of the Video Surveillance Management System send the analyzed image, information and warning to the central system according to the situation analysis based on the information obtained by compressed deep learning for low memory and real-time operation in embedded system. We tested with edge camera installed in street lamp and confirmed stable operating performance and high recognition rate compared to existing system.

[1]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[2]  Rich Caruana,et al.  Do Deep Nets Really Need to be Deep? , 2013, NIPS.

[3]  Vishnu Naresh Boddeti,et al.  In Teacher We Trust: Learning Compressed Models for Pedestrian Detection , 2016, ArXiv.

[4]  Yoshua Bengio,et al.  FitNets: Hints for Thin Deep Nets , 2014, ICLR.

[5]  Yu Wang,et al.  Going Deeper with Embedded FPGA Platform for Convolutional Neural Network , 2016, FPGA.

[6]  Wei-Yang Lin,et al.  Image bit-planes representation for moving object detection in real-time video surveillance , 2016, 2016 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW).

[7]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[8]  Beatriz Blanco-Filgueira,et al.  Deep Learning-Based Multiple Object Visual Tracking on Embedded System for IoT and Mobile Edge Computing Applications , 2018, IEEE Internet of Things Journal.

[9]  Dong Seog Han,et al.  HD-CCTV system with extended transmission distance for smart surveillance system , 2016, 2016 IEEE International Conference on Consumer Electronics (ICCE).

[10]  Dongchil Kim,et al.  An intelligent collaboration framework between edge camera and video analysis system , 2018, 2018 International Conference on Electronics, Information, and Communication (ICEIC).

[11]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[12]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  A. A. Shafie,et al.  Development of a flexible video analysis system for motion detection and alarm generation , 2010, International Conference on Computer and Communication Engineering (ICCCE'10).

[14]  Yu Cao,et al.  Optimizing the Convolution Operation to Accelerate Deep Neural Networks on FPGA , 2018, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[15]  Kuruvilla Varghese,et al.  Runtime Programmable and Memory Bandwidth Optimized FPGA-Based Coprocessor for Deep Convolutional Neural Network , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[16]  Dongchil Kim,et al.  Design and verification of the procedure for interoperability between video surveillance systems , 2017, 2017 IEEE 7th International Conference on Consumer Electronics - Berlin (ICCE-Berlin).