A point-based network learns per-event normal flow from raw event camera data and, with IMU data, estimates egomotion; it transfers across datasets better than frame-based optical flow methods.
Event-based Optical Flow on Neuromorphic Processor: ANN vs. SNN Comparison based on Activation Sparsification
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Spiking neural networks (SNNs) for event-based optical flow are claimed to be computationally more efficient than their artificial neural networks (ANNs) counterparts, but a fair comparison is missing in the literature. In this work, we propose an event-based optical flow solution based on activation sparsification and a neuromorphic processor, SENECA. SENECA has an event-driven processing mechanism that can exploit the sparsity in ANN activations and SNN spikes to accelerate the inference of both types of neural networks. The ANN and the SNN for comparison have similar low activation/spike density (~5%) thanks to our novel sparsification-aware training. In the hardware-in-loop experiments designed to deduce the average time and energy consumption, the SNN consumes 44.9ms and 927.0 microjoules, which are 62.5% and 75.2% of the ANN's consumption, respectively. We find that SNN's higher efficiency attributes to its lower pixel-wise spike density (43.5% vs. 66.5%) that requires fewer memory access operations for neuron states.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Learning Normal Flow Directly From Event Neighborhoods
A point-based network learns per-event normal flow from raw event camera data and, with IMU data, estimates egomotion; it transfers across datasets better than frame-based optical flow methods.