Event Probability Mask (EPM) and Event Denoising Convolutional Neural Network (EDnCNN) for Neuromorphic Cameras
This addresses the lack of labeled data for noise removal in neuromorphic cameras, which is crucial for improving their reliability in applications like robotics and vision systems, though it is incremental as it builds on existing denoising methods.
The paper tackles the problem of labeling real-world neuromorphic camera data by introducing an event probability mask (EPM) to calculate event likelihoods, resulting in the creation of the first labeled dataset (DVSNOISE20) for noise removal and enabling applications like benchmarking and neural network training.
This paper presents a novel method for labeling real-world neuromorphic camera sensor data by calculating the likelihood of generating an event at each pixel within a short time window, which we refer to as "event probability mask" or EPM. Its applications include (i) objective benchmarking of event denoising performance, (ii) training convolutional neural networks for noise removal called "event denoising convolutional neural network" (EDnCNN), and (iii) estimating internal neuromorphic camera parameters. We provide the first dataset (DVSNOISE20) of real-world labeled neuromorphic camera events for noise removal.