ActEV18: Human Activity Detection Evaluation for Extended Videos

Abstract

Video analytic technologies that are able to detect and classify activity are crucial for applications in many domains, such as transportation and public safety. In spite of many data collection efforts and benchmark studies in the computer vision community, there has been a lack of system development that meets practical needs for such specific domain applications. In this paper, we introduce the Activities in Extended Video (ActEV) challenge to facilitate development of video analytic technologies that can automatically detect target activities, and identify and track objects associated with each activity. To benchmark the performance of currently available algorithms, we initiated the ActEV’18 activity-level evaluation along with reference segmentation and leaderboard evaluations. In this paper, we present a summary of results and findings from these evaluations. Fifteen teams from academia and industry participated in the ActEV18 evaluations using 19 activities from the VIRAT V1 dataset.