Online Localization and Prediction of Actions and Interactions

TL;DR

This paper introduces an online, person-centric method for real-time localization and prediction of actions and interactions in videos, addressing the limitations of offline approaches by updating models continuously.

Contribution

It presents a novel online framework combining pose estimation, appearance modeling, and structured SVM-based prediction for timely action detection and forecasting.

Findings

Achieves competitive accuracy with offline methods using only a few frames

Effectively handles pose estimation noise and visual drift online

Provides a unified approach for detection and prediction in real-time

Abstract

This paper proposes a person-centric and online approach to the challenging problem of localization and prediction of actions and interactions in videos. Typically, localization or recognition is performed in an offline manner where all the frames in the video are processed together. This prevents timely localization and prediction of actions and interactions - an important consideration for many tasks including surveillance and human-machine interaction. In our approach, we estimate human poses at each frame and train discriminative appearance models using the superpixels inside the pose bounding boxes. Since the pose estimation per frame is inherently noisy, the conditional probability of pose hypotheses at current time-step (frame) is computed using pose estimations in the current frame and their consistency with poses in the previous frames. Next, both the superpixel and pose-based foreground likelihoods are used to infer the location of actors at each time through a Conditional Random. The issue of visual drift is handled by updating the appearance models, and refining poses using motion smoothness on joint locations, in an online manner. For online prediction of action (interaction) confidences, we propose an approach based on Structural SVM that operates on short video segments, and is trained with the objective that confidence of an action or interaction increases as time progresses. Lastly, we quantify the performance of both detection and prediction together, and analyze how the prediction accuracy varies as a time function of observed action (interaction) at different levels of detection performance. Our experiments on several datasets suggest that despite using only a few frames to localize actions (interactions) at each time instant, we are able to obtain competitive results to state-of-the-art offline methods.