Graph-Based Spatio-Temporal Feature Learning for Neuromorphic Vision Sensing

Abstract

Neuromorphic vision sensing (NVS) devices represent visual information as sequences of asynchronous discrete events (a.k.a., "spikes") in response to changes in scene reflectance. Unlike conventional active pixel sensing (APS), NVS allows for significantly higher event sampling rates at substantially increased energy efficiency and robustness to illumination changes. However, feature representation for NVS is far behind its APS-based counterparts, resulting in lower performance in high-level computer vision tasks. To fully utilize its sparse and asynchronous nature, we propose a compact graph representation for NVS, which allows for end-to-end learning with graph convolution neural networks. We couple this with a novel end-to-end feature learning framework that accommodates both appearancebased and motion-based tasks. The core of our framework comprises a spatial feature learning module, which utilizes residual-graph convolutional neural networks (RG-CNN), for end-to-end learning of appearance-based features directly from graphs. We extend this with our proposed Graph2Grid block and temporal feature learning module for efficiently modelling temporal dependencies over multiple graphs and a long temporal extent. We show how our framework can be configured for object classification, action recognition and action similarity labeling. Importantly, our approach preserves the spatial and temporal coherence of spike events, while requiring less computation and memory. The experimental validation shows that our proposed framework outperforms all recent methods on standard datasets. Finally, to address the absence of large real-world NVS datasets for complex recognition tasks, we introduce, evaluate and make available the American Sign Language letters (ASL-DVS), as well as human action dataset (UCF101-DVS, HMDB51-DVS and ASLAN-DVS). Index Terms-Neuromorphic vision sensing, spatio-temporal feature learning, graph convolutional neural networks, object classification, human action recognition I. INTRODUCTION With the prevalence and advances of CMOS active pixel sensing (APS) and deep learning, researchers have achieved good performance in APS-based computer vision tasks, such as object detection [1], [2], object recognition [3], [4] and action recognition [5], [6]. However, APS cameras suffer from limited frame rate, high redundancy between frames, blurriness YB, AC, AA and YA are with the Electronic and Electrical Engineer

Making Sense of Neuromorphic Event Data for Human Action Recognition

“…Finally, the feature vectors constructed from BoVV are used to train the linear SVM. Also Graph CNN based methods were reported for NVS-domain object recognition, with case studies on HAR in [42].…”

Human Action Recognition from Various Data Modalities: A Review

“…Huang et al [299] utilized timestamp image encoding, to encode the event data sequence into framebased representations for HAR. Bi et al [300] proposed a compact graph representation for end-to-end learning with Residual-Graph CNN (RG-CNN). Event cameras have also been used for gesture recognition in [301], which achieved promising results.…”

E$^2$(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition

“…While traditional cameras are capable of providing very rich visual information at the tradeoff of slow and often redundant updates, event-based cameras are asynchronous and spatially sparse, and capable of microseconds temporal resolution. Event-based systems range from designs that focus on exploiting and maintaining event-camera sparsity during computation [4,85,107], to algorithms that combine events with standard cameras [7,35,46,78,99], exploiting the complementarity of the two. With the goal of achieving minimum-delay computing, research has also focused on asynchronous designs, either by modifying regular CNNs [5,69] or by utilizing specific hardware solutions [2,21,29], often leveraging on bio-inspired computing frameworks [68].…”