RESUMO
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.
RESUMO
There have been a number of corner detection methods proposed for event cameras in the last years, since event-driven computer vision has become more accessible. Current state-of-the-art have either unsatisfactory accuracy or real-time performance when considered for practical use, for example when a camera is randomly moved in an unconstrained environment. In this paper, we present yet another method to perform corner detection, dubbed look-up event-Harris (luvHarris), that employs the Harris algorithm for high accuracy but manages an improved event throughput. Our method has two major contributions, 1. a novel "threshold ordinal event-surface" that removes certain tuning parameters and is well suited for Harris operations, and 2. an implementation of the Harris algorithm such that the computational load per event is minimised and computational heavy convolutions are performed only 'as-fast-as-possible', i.e., only as computational resources are available. The result is a practical, real-time, and robust corner detector that runs more than 2.6× the speed of current state-of-the-art; a necessity when using a high-resolution event-camera in real-time. We explain the considerations taken for the approach, compare the algorithm to current state-of-the-art in terms of computational performance and detection accuracy, and discuss the validity of the proposed approach for event cameras.
RESUMO
To interact with its environment, a robot working in 3D space needs to organise its visual input in terms of objects or their perceptual precursors, proto-objects. Among other visual cues, depth is a submodality used to direct attention to visual features and objects. Current depth-based proto-object attention models have been implemented for standard RGB-D cameras that produce synchronous frames. In contrast, event cameras are neuromorphic sensors that loosely mimic the function of the human retina by asynchronously encoding per-pixel brightness changes at very high temporal resolution, thereby providing advantages like high dynamic range, efficiency (thanks to their high degree of signal compression), and low latency. We propose a bio-inspired bottom-up attention model that exploits event-driven sensing to generate depth-based saliency maps that allow a robot to interact with complex visual input. We use event-cameras mounted in the eyes of the iCub humanoid robot to directly extract edge, disparity and motion information. Real-world experiments demonstrate that our system robustly selects salient objects near the robot in the presence of clutter and dynamic scene changes, for the benefit of downstream applications like object segmentation, tracking and robot interaction with external objects.
Assuntos
Robótica , Humanos , Movimento (Física)RESUMO
In this work, we present a neuromorphic architecture for head pose estimation and scene representation for the humanoid iCub robot. The spiking neuronal network is fully realized in Intel's neuromorphic research chip, Loihi, and precisely integrates the issued motor commands to estimate the iCub's head pose in a neuronal path-integration process. The neuromorphic vision system of the iCub is used to correct for drift in the pose estimation. Positions of objects in front of the robot are memorized using on-chip synaptic plasticity. We present real-time robotic experiments using 2 degrees of freedom (DoF) of the robot's head and show precise path integration, visual reset, and object position learning on-chip. We discuss the requirements for integrating the robotic system and neuromorphic hardware with current technologies.