Published: July 31, 2017
Haiying Guan, Daniel F. Zhou, Jonathan G. Fiscus, John S. Garofolo, James M. Horan
In this report we describe a novel framework for evaluation of video analytics which uses video quality metric prediction as a measurement of the system performance. This system is used to improve overall video analytics system performance. The primary concept of this approach is to create an evaluation infrastructure that can promote the study of video quality metrics, and at the same time promote the research of video analytics. The achievements in both domains will have significant impacts on many application areas, such as public safety, homeland security, video surveillance applications, geographic applications and entertainment video.
Citation: NIST Interagency/Internal Report (NISTIR) - 8187Report Number:
NIST Pub Series: NIST Interagency/Internal Report (NISTIR)
Pub Type: NIST Pubs
Video Quality Metric (VQM), Video Analytics (VA), Multimedia Event Detection (MED), TREC Video Retrieval Evaluation (TRECVID), Point and Shoot Face Recognition Challenge (PaSC), Face Recognition, Detection Analysis Pipeline Resources (DAPR), Scorer-centric Evaluation, Analysis- Centric Evaluation, National Imagery Interpretability Rating Scale (NIIRS), Video-National Imagery Interpretability Rating Scale (VNIIRS), Mean opinion score (MOS), Difference Mean opinion score (DMOS).
Created July 31, 2017, Updated July 31, 2017