Insights into Batch Selection for Event-Camera Motion Estimation
Open Access
Abstract
Event cameras measure scene changes with high temporal resolutions, making them well-suited for visual motion estimation. The activation of pixels results in an asynchronous stream of digital data (events), which rolls continuously over time without the discrete temporal boundaries typical of frame-based cameras (where a data packet or frame is emitted at a fixed temporal rate). As such, it is not trivial to define a priori how to group/accumulate events in a way that is sufficient for computation. The suitable number of events can greatly vary for different environments, motion patterns, and tasks. In this paper, we use neural networks for rotational motion estimation as a scenario to investigate the appropriate selection of event batches to populate input tensors. Our results show that batch selection has a large impact on the results: training should be performed on a wide variety of different batches, regardless of the batch selection method; a simple fixed-time window is a good choice for inference with respect to fixed-count batches, and it also demonstrates comparable performance to more complex methods. Our initial hypothesis that a minimal amount of events is required to estimate motion (as in contrast maximization) is not valid when estimating motion with a neural network.Keywords
This publication has 35 references indexed in Scilit:
- Event-Based, 6-DOF Camera Tracking from Photometric Depth MapsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- UnrealCV2017
- Event-Based Visual Inertial Odometry2017
- DeepVO: Towards end-to-end visual odometry with deep Recurrent Convolutional Neural Networks2017
- Accurate Angular Velocity Estimation With an Event CameraIEEE Robotics and Automation Letters, 2017
- EVO: A Geometric Approach to Event-Based 6-DOF Parallel Tracking and Mapping in Real TimeIEEE Robotics and Automation Letters, 2016
- SVO: Fast semi-direct monocular visual odometry2014
- Optical flow in the presence of spatially-varying motion blur2012
- Visual Odometry [Tutorial]IEEE Robotics & Automation Magazine, 2011
- A 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision SensorIEEE Journal of Solid-State Circuits, 2008