Multi-View Region Adaptive Multi-temporal DMM and RGB Action Recognition

TL;DR

This paper introduces a multi-view, multi-resolution deep learning framework for human action recognition that combines depth motion maps and RGB appearance data, achieving robust multi-view and multi-resolution performance.

Contribution

It proposes a novel multi-view, multi-resolution Depth Motion Map formulation combined with appearance information and multi-stream 3D CNNs for improved action recognition.

Findings

Outperforms state-of-the-art algorithms on public datasets.

Demonstrates robustness to view variations and small object interactions.

Effectively recognizes human actions and human-object interactions.

Abstract

Human action recognition remains an important yet challenging task. This work proposes a novel action recognition system. It uses a novel Multiple View Region Adaptive Multi-resolution in time Depth Motion Map (MV-RAMDMM) formulation combined with appearance information. Multiple stream 3D Convolutional Neural Networks (CNNs) are trained on the different views and time resolutions of the region adaptive Depth Motion Maps. Multiple views are synthesised to enhance the view invariance. The region adaptive weights, based on localised motion, accentuate and differentiate parts of actions possessing faster motion. Dedicated 3D CNN streams for multi-time resolution appearance information (RGB) are also included. These help to identify and differentiate between small object interactions. A pre-trained 3D-CNN is used here with fine-tuning for each stream along with multiple class Support Vector Machines (SVM)s. Average score fusion is used on the output. The developed approach is capable of recognising both human action and human-object interaction. Three public domain datasets including: MSR 3D Action,Northwestern UCLA multi-view actions and MSR 3D daily activity are used to evaluate the proposed solution. The experimental results demonstrate the robustness of this approach compared with state-of-the-art algorithms.