Activity recognition from videos with parallel hypergraph matching on GPUs

TL;DR

This paper introduces a GPU-accelerated hypergraph matching method for activity recognition in videos, leveraging temporal properties for fast, exact solutions that outperform traditional approximate algorithms.

Contribution

It presents a novel parallel GPU algorithm for exact hypergraph matching tailored for activity recognition, exploiting temporal data properties for efficiency.

Findings

Achieves faster-than-real-time performance on medium-end GPUs.

Provides exact solutions to hypergraph matching problems in activity recognition.

Simplifies and regularizes graphical structures for efficient recursive minimization.

Abstract

In this paper, we propose a method for activity recognition from videos based on sparse local features and hypergraph matching. We benefit from special properties of the temporal domain in the data to derive a sequential and fast graph matching algorithm for GPUs. Traditionally, graphs and hypergraphs are frequently used to recognize complex and often non-rigid patterns in computer vision, either through graph matching or point-set matching with graphs. Most formulations resort to the minimization of a difficult discrete energy function mixing geometric or structural terms with data attached terms involving appearance features. Traditional methods solve this minimization problem approximately, for instance with spectral techniques. In this work, instead of solving the problem approximatively, the exact solution for the optimal assignment is calculated in parallel on GPUs. The graphical structure is simplified and regularized, which allows to derive an efficient recursive minimization algorithm. The algorithm distributes subproblems over the calculation units of a GPU, which solves them in parallel, allowing the system to run faster than real-time on medium-end GPUs.