Temporal Binary Representation for Event-Based Action Recognition

18 Oct 2020  ·  Simone Undri Innocenti, Federico Becattini, Federico Pernici, Alberto del Bimbo ·

In this paper we present an event aggregation strategy to convert the output of an event camera into frames processable by traditional Computer Vision algorithms. The proposed method first generates sequences of intermediate binary representations, which are then losslessly transformed into a compact format by simply applying a binary-to-decimal conversion. This strategy allows us to encode temporal information directly into pixel values, which are then interpreted by deep learning models. We apply our strategy, called Temporal Binary Representation, to the task of Gesture Recognition, obtaining state of the art results on the popular DVS128 Gesture Dataset. To underline the effectiveness of the proposed method compared to existing ones, we also collect an extension of the dataset under more challenging conditions on which to perform experiments.

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on Gesture Recognition on DVS128 Gesture (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Gesture Recognition DVS128 Gesture AlexNet+LSTM Accuracy (%) 97.73 # 1

Methods


No methods listed for this paper. Add relevant methods here