SWTF: Sparse Weighted Temporal Fusion for Drone-Based Activity Recognition

TL;DR

This paper introduces SWTF, a novel module that efficiently fuses sparse video frames and optical flow for drone-based activity recognition, improving accuracy over previous methods.

Contribution

The paper proposes a plug-in SWTF module that enhances deep CNNs for activity recognition by effectively capturing temporal information without separate streams.

Findings

Achieved state-of-the-art accuracy on three benchmark datasets.

Effectively utilizes sparse frames and optical flow for improved recognition.

Surpassed previous performance benchmarks significantly.

Abstract

Drone-camera based human activity recognition (HAR) has received significant attention from the computer vision research community in the past few years. A robust and efficient HAR system has a pivotal role in fields like video surveillance, crowd behavior analysis, sports analysis, and human-computer interaction. What makes it challenging are the complex poses, understanding different viewpoints, and the environmental scenarios where the action is taking place. To address such complexities, in this paper, we propose a novel Sparse Weighted Temporal Fusion (SWTF) module to utilize sparsely sampled video frames for obtaining global weighted temporal fusion outcome. The proposed SWTF is divided into two components. First, a temporal segment network that sparsely samples a given set of frames. Second, weighted temporal fusion, that incorporates a fusion of feature maps derived from optical flow, with raw RGB images. This is followed by base-network, which comprises a convolutional neural network module along with fully connected layers that provide us with activity recognition. The SWTF network can be used as a plug-in module to the existing deep CNN architectures, for optimizing them to learn temporal information by eliminating the need for a separate temporal stream. It has been evaluated on three publicly available benchmark datasets, namely Okutama, MOD20, and Drone-Action. The proposed model has received an accuracy of 72.76%, 92.56%, and 78.86% on the respective datasets thereby surpassing the previous state-of-the-art performances by a significant margin.