Event-Based Computation for Touch Localization Based on Precise Spike Timing

Precise spike timing and temporal coding are used extensively within the nervous system of insects and in the sensory periphery of higher order animals. However, conventional Artificial Neural Networks (ANNs) and machine learning algorithms cannot take advantage of this coding strategy, due to their rate-based representation of signals. Even in the case of artificial Spiking Neural Networks (SNNs), identifying applications where temporal coding outperforms the rate coding strategies of ANNs is still an open challenge. Neuromorphic sensory-processing systems provide an ideal context for exploring the potential advantages of temporal coding, as they are able to efficiently extract the information required to cluster or classify spatio-temporal activity patterns from relative spike timing. Here we propose a neuromorphic model inspired by the sand scorpion to explore the benefits of temporal coding, and validate it in an event-based sensory-processing task. The task consists in localizing a target using only the relative spike timing of eight spatially-separated vibration sensors. We propose two different approaches in which the SNNs learns to cluster spatio-temporal patterns in an unsupervised manner and we demonstrate how the task can be solved both analytically and through numerical simulation of multiple SNN models. We argue that the models presented are optimal for spatio-temporal pattern classification using precise spike timing in a task that could be used as a standard benchmark for evaluating event-based sensory processing models based on temporal coding.

Effects of pupillary responses to luminance and attention on visual spatial discrimination

The optic quality of the eyes is, at least in part, determined by pupil size. Large pupils let more light enter the eyes, but degrade the point spread function, and thus the spatial resolution that can be achieved (Campbell & Gregory, 1960). In natural conditions, the pupil is mainly driven by the luminance (and possibly the color and contrast) at the gazed location, but is also modulated by attention and cognitive factors. Whether changes in eyes' optics related to pupil size modulation by luminance and attention impacts visual processing was assessed in two experiments. In Experiment 1, we measured pupil size using a constantly visible display made of four disks with different luminance levels, with no other task than fixating the disks in succession. The results confirmed that pupil size depends on the luminance of the gazed stimulus. Experiment 2, using similar settings as Experiment 1, used a two-interval forced-choice design to test whether discriminating high spatial frequencies that requires covert attention to parafoveal stimuli is better during the fixation of bright disks that entails a small pupil size, and hence better eyes' optics, as compared to fixating dark disks that entails a large pupil size, and hence poorer eyes' optics. As in Experiment 1, we observed large modulations of pupil size depending on the luminance of the gazed stimulus, but pupil dynamics was more variable, with marked pupil dilation during stimulus encoding, presumably because the demanding spatial frequency discrimination task engaged attention. However, discrimination performance and mean pupil size were not correlated. Despite this lack of correlation, the slopes of pupil dilation during stimulus encoding were correlated to performance, while the slopes of pupil dilation during decision-making were not. We discuss these results regarding the possible functional roles of pupil size modulations.

Event-Based Color Segmentation With a High Dynamic Range Sensor

This paper introduces a color asynchronous neuromorphic event-based camera and a methodology to process color output from the device to perform color segmentation and tracking at the native temporal resolution of the sensor (down to one microsecond). Our color vision sensor prototype is a combination of three Asynchronous Time-based Image Sensors, sensitive to absolute color information. We devise a color processing algorithm leveraging this information. It is designed to be computationally cheap, thus showing how low level processing benefits from asynchronous acquisition and high temporal resolution data. The resulting color segmentation and tracking performance is assessed both with an indoor controlled scene and two outdoor uncontrolled scenes. The tracking's mean error to the ground truth for the objects of the outdoor scenes ranges from two to twenty pixels.

HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition

This paper describes novel event-based spatio-temporal features called time-surfaces and how they can be used to create a hierarchical event-based pattern recognition architecture. Unlike existing hierarchical architectures for pattern recognition, the presented model relies on a time oriented approach to extract spatio-temporal features from the asynchronously acquired dynamics of a visual scene. These dynamics are acquired using biologically inspired frameless asynchronous event-driven vision sensors. Similarly to cortical structures, subsequent layers in our hierarchy extract increasingly abstract features using increasingly large spatio-temporal windows. The central concept is to use the rich temporal information provided by events to create contexts in the form of time-surfaces which represent the recent temporal activity within a local spatial neighborhood. We demonstrate that this concept can robustly be used at all stages of an event-based hierarchical model. First layer feature units operate on groups of pixels, while subsequent layer feature units operate on the output of lower level feature units. We report results on a previously published 36 class character recognition task and a four class canonical dynamic card pip task, achieving near 100 percent accuracy on each. We introduce a new seven class moving face recognition task, achieving 79 percent accuracy.This paper describes novel event-based spatio-temporal features called time-surfaces and how they can be used to create a hierarchical event-based pattern recognition architecture. Unlike existing hierarchical architectures for pattern recognition, the presented model relies on a time oriented approach to extract spatio-temporal features from the asynchronously acquired dynamics of a visual scene. These dynamics are acquired using biologically inspired frameless asynchronous event-driven vision sensors. Similarly to cortical structures, subsequent layers in our hierarchy extract increasingly abstract features using increasingly large spatio-temporal windows. The central concept is to use the rich temporal information provided by events to create contexts in the form of time-surfaces which represent the recent temporal activity within a local spatial neighborhood. We demonstrate that this concept can robustly be used at all stages of an event-based hierarchical model. First layer feature units operate on groups of pixels, while subsequent layer feature units operate on the output of lower level feature units. We report results on a previously published 36 class character recognition task and a four class canonical dynamic card pip task, achieving near 100 percent accuracy on each. We introduce a new seven class moving face recognition task, achieving 79 percent accuracy.

Event-Based 3D Motion Flow Estimation Using 4D Spatio Temporal Subspaces Properties

State of the art scene flow estimation techniques are based on projections of the 3D motion on image using luminance-sampled at the frame rate of the cameras-as the principal source of information. We introduce in this paper a pure time based approach to estimate the flow from 3D point clouds primarily output by neuromorphic event-based stereo camera rigs, or by any existing 3D depth sensor even if it does not provide nor use luminance. This method formulates the scene flow problem by applying a local piecewise regularization of the scene flow. The formulation provides a unifying framework to estimate scene flow from synchronous and asynchronous 3D point clouds. It relies on the properties of 4D space time using a decomposition into its subspaces. This method naturally exploits the properties of the neuromorphic asynchronous event based vision sensors that allows continuous time 3D point clouds reconstruction. The approach can also handle the motion of deformable object. Experiments using different 3D sensors are presented.

A Motion-Based Feature for Event-Based Pattern Recognition

This paper introduces an event-based luminance-free feature from the output of asynchronous event-based neuromorphic retinas. The feature consists in mapping the distribution of the optical flow along the contours of the moving objects in the visual scene into a matrix. Asynchronous event-based neuromorphic retinas are composed of autonomous pixels, each of them asynchronously generating "spiking" events that encode relative changes in pixels' illumination at high temporal resolutions. The optical flow is computed at each event, and is integrated locally or globally in a speed and direction coordinate frame based grid, using speed-tuned temporal kernels. The latter ensures that the resulting feature equitably represents the distribution of the normal motion along the current moving edges, whatever their respective dynamics. The usefulness and the generality of the proposed feature are demonstrated in pattern recognition applications: local corner detection and global gesture recognition.

Event-Based Tone Mapping for Asynchronous Time-Based Image Sensor

The asynchronous time-based neuromorphic image sensor ATIS is an array of autonomously operating pixels able to encode luminance information with an exceptionally high dynamic range (>143 dB). This paper introduces an event-based methodology to display data from this type of event-based imagers, taking into account the large dynamic range and high temporal accuracy that go beyond available mainstream display technologies. We introduce an event-based tone mapping methodology for asynchronously acquired time encoded gray-level data. A global and a local tone mapping operator are proposed. Both are designed to operate on a stream of incoming events rather than on time frame windows. Experimental results on real outdoor scenes are presented to evaluate the performance of the tone mapping operators in terms of quality, temporal stability, adaptation capability, and computational time.

Skimming Digits: Neuromorphic Classification of Spike-Encoded Images

The growing demands placed upon the field of computer vision have renewed the focus on alternative visual scene representations and processing paradigms. Silicon retinea provide an alternative means of imaging the visual environment, and produce frame-free spatio-temporal data. This paper presents an investigation into event-based digit classification using N-MNIST, a neuromorphic dataset created with a silicon retina, and the Synaptic Kernel Inverse Method (SKIM), a learning method based on principles of dendritic computation. As this work represents the first large-scale and multi-class classification task performed using the SKIM network, it explores different training patterns and output determination methods necessary to extend the original SKIM method to support multi-class problems. Making use of SKIM networks applied to real-world datasets, implementing the largest hidden layer sizes and simultaneously training the largest number of output neurons, the classification system achieved a best-case accuracy of 92.87% for a network containing 10,000 hidden layer neurons. These results represent the highest accuracies achieved against the dataset to date and serve to validate the application of the SKIM method to event-based visual classification tasks. Additionally, the study found that using a square pulse as the supervisory training signal produced the highest accuracy for most output determination methods, but the results also demonstrate that an exponential pattern is better suited to hardware implementations as it makes use of the simplest output determination method based on the maximum value.

Event-Based Computation of Motion Flow on a Neuromorphic Analog Neural Platform

Estimating the speed and direction of moving objects is a crucial component of agents behaving in a dynamic world. Biological organisms perform this task by means of the neural connections originating from their retinal ganglion cells. In artificial systems the optic flow is usually extracted by comparing activity of two or more frames captured with a vision sensor. Designing artificial motion flow detectors which are as fast, robust, and efficient as the ones found in biological systems is however a challenging task. Inspired by the architecture proposed by Barlow and Levick in 1965 to explain the spiking activity of the direction-selective ganglion cells in the rabbit's retina, we introduce an architecture for robust optical flow extraction with an analog neuromorphic multi-chip system. The task is performed by a feed-forward network of analog integrate-and-fire neurons whose inputs are provided by contrast-sensitive photoreceptors. Computation is supported by the precise time of spike emission, and the extraction of the optical flow is based on time lag in the activation of nearby retinal neurons. Mimicking ganglion cells our neuromorphic detectors encode the amplitude and the direction of the apparent visual motion in their output spiking pattern. Hereby we describe the architectural aspects, discuss its latency, scalability, and robustness properties and demonstrate that a network of mismatched delicate analog elements can reliably extract the optical flow from a simple visual scene. This work shows how precise time of spike emission used as a computational basis, biological inspiration, and neuromorphic systems can be used together for solving specific tasks.

Neuromorphic Event-Based 3D Pose Estimation

Pose estimation is a fundamental step in many artificial vision tasks. It consists of estimating the 3D pose of an object with respect to a camera from the object's 2D projection. Current state of the art implementations operate on images. These implementations are computationally expensive, especially for real-time applications. Scenes with fast dynamics exceeding 30-60 Hz can rarely be processed in real-time using conventional hardware. This paper presents a new method for event-based 3D object pose estimation, making full use of the high temporal resolution (1 μs) of asynchronous visual events output from a single neuromorphic camera. Given an initial estimate of the pose, each incoming event is used to update the pose by combining both 3D and 2D criteria. We show that the asynchronous high temporal resolution of the neuromorphic camera allows us to solve the problem in an incremental manner, achieving real-time performance at an update rate of several hundreds kHz on a conventional laptop. We show that the high temporal resolution of neuromorphic cameras is a key feature for performing accurate pose estimation. Experiments are provided showing the performance of the algorithm on real data, including fast moving objects, occlusions, and cases where the neuromorphic camera and the object are both in motion.

Breaking the millisecond barrier on SpiNNaker: implementing asynchronous event-based plastic models with microsecond resolution

Spike-based neuromorphic sensors such as retinas and cochleas, change the way in which the world is sampled. Instead of producing data sampled at a constant rate, these sensors output spikes that are asynchronous and event driven. The event-based nature of neuromorphic sensors implies a complete paradigm shift in current perception algorithms toward those that emphasize the importance of precise timing. The spikes produced by these sensors usually have a time resolution in the order of microseconds. This high temporal resolution is a crucial factor in learning tasks. It is also widely used in the field of biological neural networks. Sound localization for instance relies on detecting time lags between the two ears which, in the barn owl, reaches a temporal resolution of 5 μs. Current available neuromorphic computation platforms such as SpiNNaker often limit their users to a time resolution in the order of milliseconds that is not compatible with the asynchronous outputs of neuromorphic sensors. To overcome these limitations and allow for the exploration of new types of neuromorphic computing architectures, we introduce a novel software framework on the SpiNNaker platform. This framework allows for simulations of spiking networks and plasticity mechanisms using a completely asynchronous and event-based scheme running with a microsecond time resolution. Results on two example networks using this new implementation are presented.

Spatiotemporal features for asynchronous event-based data

Bio-inspired asynchronous event-based vision sensors are currently introducing a paradigm shift in visual information processing. These new sensors rely on a stimulus-driven principle of light acquisition similar to biological retinas. They are event-driven and fully asynchronous, thereby reducing redundancy and encoding exact times of input signal changes, leading to a very precise temporal resolution. Approaches for higher-level computer vision often rely on the reliable detection of features in visual frames, but similar definitions of features for the novel dynamic and event-based visual input representation of silicon retinas have so far been lacking. This article addresses the problem of learning and recognizing features for event-based vision sensors, which capture properties of truly spatiotemporal volumes of sparse visual event information. A novel computational architecture for learning and encoding spatiotemporal features is introduced based on a set of predictive recurrent reservoir networks, competing via winner-take-all selection. Features are learned in an unsupervised manner from real-world input recorded with event-based vision sensors. It is shown that the networks in the architecture learn distinct and task-specific dynamic visual features, and can predict their trajectories over time.

A framework for plasticity implementation on the SpiNNaker neural architecture

Many of the precise biological mechanisms of synaptic plasticity remain elusive, but simulations of neural networks have greatly enhanced our understanding of how specific global functions arise from the massively parallel computation of neurons and local Hebbian or spike-timing dependent plasticity rules. For simulating large portions of neural tissue, this has created an increasingly strong need for large scale simulations of plastic neural networks on special purpose hardware platforms, because synaptic transmissions and updates are badly matched to computing style supported by current architectures. Because of the great diversity of biological plasticity phenomena and the corresponding diversity of models, there is a great need for testing various hypotheses about plasticity before committing to one hardware implementation. Here we present a novel framework for investigating different plasticity approaches on the SpiNNaker distributed digital neural simulation platform. The key innovation of the proposed architecture is to exploit the reconfigurability of the ARM processors inside SpiNNaker, dedicating a subset of them exclusively to process synaptic plasticity updates, while the rest perform the usual neural and synaptic simulations. We demonstrate the flexibility of the proposed approach by showing the implementation of a variety of spike- and rate-based learning rules, including standard Spike-Timing dependent plasticity (STDP), voltage-dependent STDP, and the rate-based BCM rule. We analyze their performance and validate them by running classical learning experiments in real time on a 4-chip SpiNNaker board. The result is an efficient, modular, flexible and scalable framework, which provides a valuable tool for the fast and easy exploration of learning models of very different kinds on the parallel and reconfigurable SpiNNaker system.

On the use of orientation filters for 3D reconstruction in event-driven stereo vision

The recently developed Dynamic Vision Sensors (DVS) sense visual information asynchronously and code it into trains of events with sub-micro second temporal resolution. This high temporal precision makes the output of these sensors especially suited for dynamic 3D visual reconstruction, by matching corresponding events generated by two different sensors in a stereo setup. This paper explores the use of Gabor filters to extract information about the orientation of the object edges that produce the events, therefore increasing the number of constraints applied to the matching algorithm. This strategy provides more reliably matched pairs of events, improving the final 3D reconstruction.