Video Event Detection and Localization

Du Tran, Junsong Yuan, and David Forsyth

Abstract

We propose a novel algorithm for video event detection and localization as the optimal path discovery problem in spatio-temporal video space. By finding the optimal spatiotemporal path, our method not only detects the starting and ending points of the event, but also accurately locates it in each video frame. Moreover, our method is robust to the scale and intra-class variations of the event, as well as false and missed local detections, therefore improves the overall detection and localization accuracy. The proposed search algorithm obtains the global optimal solution with proven lowest computational complexity. Experiments on realistic video datasets demonstrate that our proposed method can be applied to different types of event detection tasks, such as abnormal event detection and walking pedestrian detection.

Video Results

Datasets

NTU-UIUC Walking Dataset: download (a zip file of ~515MB).

Source Code

Source code (C++): download.
Binary code (Window 32): download.

Publications