TY - GEN
T1 - Video Object Detection Method Using Single-Frame Detection and Motion Vector Tracking
AU - Nohara, Masato
AU - Nishi, Hiroaki
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported by JST CREST Grant Number JPMJCR19K1, and the commissioned research by National Institute of Information and Communications Technology (NICT, Grant Number 22004) , JAPAN.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/7/20
Y1 - 2020/7/20
N2 - Video traffic on the Internet has been increasing rapidly and accounts for a large percentage of the total traffic. To process the increasing number of videos, edge computing is preferable for load balancing and bandwidth reduction. However, edge areas have less computational resources than cloud areas, and high-performance GPUs for processing videos at high speed are not always present. Therefore, a memory-saving and high-Throughput video analysis method is necessary for analyzing videos in edge areas. In this paper, a video object detection method using single-frame detection and motion vector tracking is proposed. This method is classified as a pixel and compressed domain analysis method and is realized by compensating motion using the motion vectors that already exist in the compressed domain. This method is divided into two processes: CNN-based object detection and motion vector-based object detection. In addition, a network-Transparent platform for video reconstruction in edge areas is constructed. The network-Transparent service can be installed without modifying the existing end-device network settings, network configuration, and routing. The platform enables video object detection services to be added on without modification of these settings.
AB - Video traffic on the Internet has been increasing rapidly and accounts for a large percentage of the total traffic. To process the increasing number of videos, edge computing is preferable for load balancing and bandwidth reduction. However, edge areas have less computational resources than cloud areas, and high-performance GPUs for processing videos at high speed are not always present. Therefore, a memory-saving and high-Throughput video analysis method is necessary for analyzing videos in edge areas. In this paper, a video object detection method using single-frame detection and motion vector tracking is proposed. This method is classified as a pixel and compressed domain analysis method and is realized by compensating motion using the motion vectors that already exist in the compressed domain. This method is divided into two processes: CNN-based object detection and motion vector-based object detection. In addition, a network-Transparent platform for video reconstruction in edge areas is constructed. The network-Transparent service can be installed without modifying the existing end-device network settings, network configuration, and routing. The platform enables video object detection services to be added on without modification of these settings.
KW - compressed domain analysis
KW - edge computing
KW - motion vector
KW - moving detection
KW - network transparency
KW - video object detection
UR - http://www.scopus.com/inward/record.url?scp=85111098203&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85111098203&partnerID=8YFLogxK
U2 - 10.1109/INDIN45582.2020.9442163
DO - 10.1109/INDIN45582.2020.9442163
M3 - Conference contribution
AN - SCOPUS:85111098203
T3 - IEEE International Conference on Industrial Informatics (INDIN)
SP - 119
EP - 125
BT - Proceedings - 2020 IEEE 18th International Conference on Industrial Informatics, INDIN 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE International Conference on Industrial Informatics, INDIN 2020
Y2 - 21 July 2020 through 23 July 2020
ER -