TY - GEN
T1 - Lightweight Super-resolution Learning Model for Extremely Exposed Images
AU - Chen, Tzu Hsiu
AU - Huang, Chung Hsun
AU - Chu, Yuan Sun
N1 - Publisher Copyright:
© 2020 ACM.
PY - 2020/4/15
Y1 - 2020/4/15
N2 - Video surveillance system adopting wireless sensor network (WSN) becomes more and more popular. To achieve energy efficiency and low transmitting bandwidth, low-cost and low-resolution video camera may be used. However, captured image/video with low resolution may cause information loss; for example, suspicious objects such as a bomb, and emergent events such as fire emergency. Moreover, it is getting deteriorated in case an extremely exposed scene is presented. In this paper, a lightweight learning-based super-resolution (LLBSR) image reconstruction algorithm is proposed for the control center of surveillance system to recover information details from low-resolution images with extremely exposed scenes. The captured video sequences were processed via a simplified difference residual network (DRN) to improve contrast first. Then the pre-processed video sequences were scaled up via a lightweight SR neural network (LSRNN).
AB - Video surveillance system adopting wireless sensor network (WSN) becomes more and more popular. To achieve energy efficiency and low transmitting bandwidth, low-cost and low-resolution video camera may be used. However, captured image/video with low resolution may cause information loss; for example, suspicious objects such as a bomb, and emergent events such as fire emergency. Moreover, it is getting deteriorated in case an extremely exposed scene is presented. In this paper, a lightweight learning-based super-resolution (LLBSR) image reconstruction algorithm is proposed for the control center of surveillance system to recover information details from low-resolution images with extremely exposed scenes. The captured video sequences were processed via a simplified difference residual network (DRN) to improve contrast first. Then the pre-processed video sequences were scaled up via a lightweight SR neural network (LSRNN).
UR - https://www.scopus.com/pages/publications/85085916183
UR - https://www.scopus.com/pages/publications/85085916183#tab=citedBy
U2 - 10.1145/3390525.3390529
DO - 10.1145/3390525.3390529
M3 - Conference contribution
AN - SCOPUS:85085916183
T3 - ACM International Conference Proceeding Series
SP - 58
EP - 62
BT - Proceedings of the 2020 8th International Conference on Communications and Broadband Networking, ICCBN 2020
PB - Association for Computing Machinery
T2 - 8th International Conference on Communications and Broadband Networking, ICCBN 2020 and its Workshop on 2020 3rd International Conference on Communication Engineering and Technology, ICCET 2020
Y2 - 15 April 2020 through 18 April 2020
ER -