HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors
This work addresses the problem of enabling more robust and efficient HAR for applications like surveillance or robotics by providing a critical dataset and method, though it is incremental in combining existing techniques for a new sensor type.
The authors tackled the lack of a large-scale dataset for human activity recognition (HAR) using event cameras by introducing HARDVS, a dataset with 300 categories and over 100K event sequences, and proposed a novel spatial-temporal framework (ESTF) that achieved validated effectiveness in experiments.
The main streams of human activity recognition (HAR) algorithms are developed based on RGB cameras which are suffered from illumination, fast motion, privacy-preserving, and large energy consumption. Meanwhile, the biologically inspired event cameras attracted great interest due to their unique features, such as high dynamic range, dense temporal but sparse spatial resolution, low latency, low power, etc. As it is a newly arising sensor, even there is no realistic large-scale dataset for HAR. Considering its great practical value, in this paper, we propose a large-scale benchmark dataset to bridge this gap, termed HARDVS, which contains 300 categories and more than 100K event sequences. We evaluate and report the performance of multiple popular HAR algorithms, which provide extensive baselines for future works to compare. More importantly, we propose a novel spatial-temporal feature learning and fusion framework, termed ESTF, for event stream based human activity recognition. It first projects the event streams into spatial and temporal embeddings using StemNet, then, encodes and fuses the dual-view representations using Transformer networks. Finally, the dual features are concatenated and fed into a classification head for activity prediction. Extensive experiments on multiple datasets fully validated the effectiveness of our model. Both the dataset and source code will be released on \url{https://github.com/Event-AHU/HARDVS}.