DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition

TL;DR

This paper introduces a novel Sparse Weighted Temporal Attention (SWTA) module for drone-based human activity recognition, improving accuracy by effectively utilizing sparsely sampled frames and combining optical flow with RGB data.

Contribution

The paper presents a new SWTA module that enhances existing CNN architectures for activity recognition by capturing temporal information without needing separate temporal streams.

Findings

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

Surpassed previous methods by significant margins on all datasets.

Demonstrated the effectiveness of sparse sampling combined with weighted attention.

Abstract

Human activity recognition (HAR) using drone-mounted cameras has attracted considerable interest from the computer vision research community in recent 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 Attention (SWTA) module to utilize sparsely sampled video frames for obtaining global weighted temporal attention. The proposed SWTA is comprised of two parts. First, temporal segment network that sparsely samples a given set of frames. Second, weighted temporal attention, which incorporates a fusion of attention maps derived from optical flow, with raw RGB images. This is followed by a basenet network, which comprises a convolutional neural network (CNN) module along with fully connected layers that provide us with activity recognition. The SWTA 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 margin of 25.26%, 18.56%, and 2.94%, respectively.