Share Email Print

Proceedings Paper

Fast motion detection in coded video streams for a large-scale remote video sensor system
Author(s): Yong-Sung Kim; Gyu-Hee Park; Seung-Hwan Kim; Hyung-Joon Cho
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A large number of remote video sensors are being deployed in the world to collect, store, and analyze the real-world data. Since a remote video sensor produces very large data, the total amount of video data are extremely large in size, complexity, and capacity. Important events from a remote video sensor are closely related to a motion in video. We present, in this paper, a fast motion detection method based on the number of bits used for encoding a video stream and the GOP-level motion detection. A low complexity measurement of the number of bits is performed in the coded video sequence and then, we store and process the coded video stream only if the total bits are larger than a pre-defined threshold. We also use a GOP level motion detection to reduce processing overhead compared to the conventional motion vector-based approach which processes every frame. Manipulating the number of bits is itself a much easier task than full reconstruction of each pixel of a video frame and it can save storage cost because it only stores a coded video sequence with a motion. The proposed method also contributes to reduction of computational complexity compared to the manipulation of motion vectors per 4x4 macro block. To evaluate our method, we deployed a centralized single server connected to H.264 capable remote video sensors. Results on the video sequences showed that the proposed approach can process more video sequences than the conventional compressed domain approach.

Paper Details

Date Published: 15 October 2014
PDF: 6 pages
Proc. SPIE 9247, High-Performance Computing in Remote Sensing IV, 92470F (15 October 2014); doi: 10.1117/12.2067109
Show Author Affiliations
Yong-Sung Kim, Future Technology R&D Division (Korea, Republic of)
Gyu-Hee Park, Future Technology R&D Division (Korea, Republic of)
Seung-Hwan Kim, Future Technology R&D Division (Korea, Republic of)
Hyung-Joon Cho, Future Technology R&D Division (Korea, Republic of)

Published in SPIE Proceedings Vol. 9247:
High-Performance Computing in Remote Sensing IV
Bormin Huang; Sebastian López; Zhensen Wu, Editor(s)

© SPIE. Terms of Use
Back to Top