Bi, Y;
Chadha, A;
Abbas, A;
Bourtsoulatze, E;
Andreopoulos, Y;
(2019)
Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision Sensing.
IEEE Transactions on Image Processing
, 29
pp. 9084-9098.
10.1109/TIP.2020.3023597.
Preview |
Text
TIP1.pdf - Accepted Version Download (3MB) | Preview |
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 appearance-based 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).
| Type: | Article |
|---|---|
| Title: | Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision Sensing. |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/TIP.2020.3023597 |
| Publisher version: | https://doi.org/10.1109/TIP.2020.3023597 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Neuromorphic vision sensing, spatio-temporal feature learning, graph convolutional neural networks, object classification, human action recognition |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10111582 |
Archive Staff Only
 |
View Item |
