Translation and Scale Invariance for Event-Based Object tracking
Open Access
- 11 April 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 79-85
Abstract
Without temporal averaging, such as rate codes, it remains challenging to train spiking neural networks for temporal regression tasks. In this work, we present a novel method to accurately predict spatial coordinates from event data with a fully spiking convolutional neural network (SCNN) without temporal averaging. Our method performs on-par with artificial neural networks (ANN) of similar complexity. Additionally, we demonstrate faster convergence in half the time using translation- and scale-invariant receptive fields. To permit comparison with conventional frame-based ANNs, we base our results on a simulated event-based dataset with an unrealistic high density. Therefore, we hypothesize that our method significantly outperform ANNs in settings with lower event density, as seen in real-life event-based data. Our model is fully spiking and can be ported directly to neuromorphic hardware.Keywords
This publication has 24 references indexed in Scilit:
- Neuromorophic vision sensing and processing2016
- HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Direct face detection and video reconstruction from event cameras2016
- Real-Time Gesture Interface Based on Event-Driven Processing From Stereo Silicon RetinasIEEE Transactions on Neural Networks and Learning Systems, 2014
- CAVIAR: A 45k Neuron, 5M Synapse, 12G Connects/s AER Hardware Sensory–Processing– Learning–Actuating System for High-Speed Visual Object Recognition and TrackingIEEE Transactions on Neural Networks, 2009
- A 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision SensorIEEE Journal of Solid-State Circuits, 2008
- Learning methods for generic object recognition with invariance to pose and lighting2004
- Lapicque’s introduction of the integrate-and-fire model neuron (1907)Brain Research Bulletin, 1999
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Networks of spiking neurons: The third generation of neural network modelsNeural Networks, 1997