Event cameras are bio-inspired sensors that differ from conventional frame cameras: Instead of capturing images at a fixed rate, they asynchronously measure per-pixel brightness changes, and output a stream of events that encode the time, location and sign of the brightness changes. Event cameras offer attractive properties compared to traditional cameras: high temporal resolution (in the order of μs), very high dynamic range (140 dB versus 60 dB), low power consumption, and high pixel bandwidth (on the order of kHz) resulting in reduced motion blur. Hence, event cameras have a large potential for robotics and computer vision in challenging scenarios for traditional cameras, such as low-latency, high speed, and high dynamic range. However, novel methods are required to process the unconventional output of these sensors in order to unlock their potential. This paper provides a comprehensive overview of the emerging field of event-based vision, with a focus on the applications and the algorithms developed to unlock the outstanding properties of event cameras. We present event cameras from their working principle, the actual sensors that are available and the tasks that they have been used for, from low-level vision (feature detection and tracking, optic flow, etc.) to high-level vision (reconstruction, segmentation, recognition). We also discuss the techniques developed to process events, including learning-based techniques, as well as specialized processors for these novel sensors, such as spiking neural networks. Additionally, we highlight the challenges that remain to be tackled and the opportunities that lie ahead in the search for a more efficient, bio-inspired way for machines to perceive and interact with the world.

Deep artificial neural networks apply principles of the brain's information processing that led to breakthroughs in machine learning spanning many problem domains. Neuromorphic computing aims to take this a step further to chips more directly inspired by the form and function of biological neural circuits, so they can process new knowledge, adapt, behave, and learn in real time at low power levels. Despite several decades of research, until recently, very few published results have shown that today's neuromorphic chips can demonstrate quantitative computational value. This is now changing with the advent of Intel's Loihi, a neuromorphic research processor designed to support a broad range of spiking neural networks with sufficient scale, performance, and features to deliver competitive results compared to state-of-the-art contemporary computing architectures. This survey reviews results that are obtained to date with Loihi across the major algorithmic domains under study, including deep learning approaches and novel approaches that aim to more directly harness the key features of spike-based neuromorphic hardware. While conventional feedforward deep neural networks show modest if any benefit on Loihi, more brain-inspired networks using recurrence, precise spike-timing relationships, synaptic plasticity, stochasticity, and sparsity perform certain computation with orders of magnitude lower latency and energy compared to state-of-the-art conventional approaches. These compelling neuromorphic networks solve a diverse range of problems representative of brain-like computation, such as event-based data processing, adaptive control, constrained optimization, sparse feature regression, and graph search.

This paper presents a long-term object tracking framework with a moving event camera under general tracking conditions. A first of its kind for these revolutionary cameras, the tracking framework uses a discriminative representation for the object with online learning, and detects and re-tracks the object when it comes back into the field-of-view. One of the key novelties is the use of an event-basedlocal sliding windowtechnique that tracks reliably in scenes with cluttered and textured background. In addition, Bayesian bootstrapping is used to assist real-time processing and boost the discriminative power of the object representation. On the other hand, when the object re-enters the field-of-view of the camera, adata-driven, global sliding windowdetector locates the object for subsequent tracking. Extensive experiments demonstrate the ability of the proposed framework to track and detect arbitrary objects of various shapes and sizes, including dynamic objects such as a human. This is a significant improvement compared to earlier works that simply track objects as long as they are visible under simpler background settings. Using the ground truth locations for five different objects under three motion settings, namely translation, rotation and 6-DOF, quantitative measurement is reported for the event-based tracking framework with critical insights on various performance issues. Finally, real-time implementation in C++ highlights tracking ability under scale, rotation, view-point and occlusion scenarios in a lab setting.

We introduce a generic visual descriptor, termed as distribution aware retinal transform (DART), that encodes the structural context using log-polar grids for event cameras. The DART descriptor is applied to four different problems, namely object classification, tracking, detection and feature matching: (1) The DART features are directly employed as local descriptors in a bag-of-words classification framework and testing is carried out on four standard event-based object datasets (N-MNIST, MNIST-DVS, CIFAR10-DVS, NCaltech-101); (2) Extending the classification system, tracking is demonstrated using two key novelties: (i) Statistical bootstrapping is leveraged with online learning for overcoming the low-sample problem during the one-shot learning of the tracker, (ii) Cyclical shifts are induced in the log-polar domain of the DART descriptor to achieve robustness to object scale and rotation variations; (3) To solve the long-term object tracking problem, an object detector is designed using the principle of cluster majority voting. The detection scheme is then combined with the tracker to result in a high intersection-over-union score with augmented ground truth annotations on the publicly available event camera dataset; (4) Finally, the event context encoded by DART greatly simplifies the feature correspondence problem, especially for spatio-temporal slices far apart in time, which has not been explicitly tackled in the event-based vision domain.

In this article, we present a systematic computational model to explore brain-based computation for object recognition. The model extracts temporal features embedded in address-event representation (AER) data and discriminates different objects by using spiking neural networks (SNNs). We use multispike encoding to extract temporal features contained in the AER data. These temporal patterns are then learned through the tempotron learning rule. The presented model is consistently implemented in a temporal learning framework, where the precise timing of spikes is considered in the feature-encoding and learning process. A noise-reduction method is also proposed by calculating the correlation of an event with the surrounding spatial neighborhood based on the recently proposed time-surface technique. The model evaluated on wide spectrum data sets (MNIST, N-MNIST, MNIST-DVS, AER Posture, and Poker Card) demonstrates its superior recognition performance, especially for the events with noise.

Optical flow is a useful signal for mobile agents, both biological and artificial. In this paper we present modification and implementation of a well known "plane-fitting" approach to event-based optical flow estimation for Dynamic Vision Sensors. The optical flow algorithm, as well as all required preprocessing steps are implemented in FPGA. The algorithm achieves sub microsecond latency and is fully pipelined, capable of performing 100M 3 × 3 pixel plane fits per second. The tradeoff between Average Absolute Endpoint Error and the density of optical flow estimates is analyzed and presented, and the FPGA implementation is shown to perform similarly to the previously published full precision software implementation.

Interest in event-based vision sensors has proliferated in recent years, with innovative technology becoming more accessible to new researchers and highlighting such sensors' potential to enable low-latency sensing at low computational cost. These sensors can outperform frame-based vision sensors regarding data compression, dynamic range, temporal resolution and power efficiency. However, available mature frame-based processing methods by using Artificial Neural Networks (ANNs) surpass Spiking Neural Networks (SNNs) in terms of accuracy of recognition. In this paper, we introduce a Hybrid Neural Network which is an intermediate solution to exploit advantages of both event-based and frame-based processing. We have implemented this network in FPGA and benchmarked its performance by using different event-based versions of MNIST dataset. HDL codes for this project are available for academic purpose upon request.

Configuring deep Spiking Neural Networks (SNNs) is an exciting research avenue for low power spike event based computation. However, the spike generation function is non-differentiable and therefore not directly compatible with the standard error backpropagation algorithm. In this paper, we introduce a new general backpropagation mechanism for learning synaptic weights and axonal delays which overcomes the problem of non-differentiability of the spike function and uses a temporal credit assignment policy for backpropagating error to preceding layers. We describe and release a GPU accelerated software implementation of our method which allows training both fully connected and convolutional neural network (CNN) architectures. Using our software, we compare our method against existing SNN based learning approaches and standard ANN to SNN conversion techniques and show that our method achieves state of the art performance for an SNN on the MNIST, NMNIST, DVS Gesture, and TIDIGITS datasets.

As the interest in event-based vision sensors for mobile and aerial applications grows, there is an increasing need for high-speed and highly robust algorithms for performing visual tasks using event-based data. As event rate and network structure have a direct impact on the power consumed by such systems, it is important to explore the efficiency of the event-based encoding used by these sensors. The work presented in this paper represents the first study solely focused on the effects of both spatial and temporal downsampling on event-based vision data and makes use of a variety of data sets chosen to fully explore and characterize the nature of downsampling operations. The results show that both spatial downsampling and temporal downsampling produce improved classification accuracy and, additionally, a lower overall data rate. A finding is particularly relevant for bandwidth and power constrained systems. For a given network containing 1000 hidden layer neurons, the spatially downsampled systems achieved a best case accuracy of 89.38% on N-MNIST as opposed to 81.03% with no downsampling at the same hidden layer size. On the N-Caltech101 data set, the downsampled system achieved a best case accuracy of 18.25%, compared with 7.43% achieved with no downsampling. The results show that downsampling is an important preprocessing technique in event-based visual processing, especially for applications sensitive to power consumption and transmission bandwidth.

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.

Summary form only given. The IBM TrueNorth (TN) Neurosynaptic System, is a chip multi processor with a tightly coupled processor/memory architecture, that results in energy efficient neurocomputing and it is a significant milestone to over 30 years of neuromorphic engineering! It comprises of 4096 cores each core with 65K of local memory (6T SRAM)-synapses- and 256 arithmetic logic units - neurons-that operate on a unary number representation and compute by counting up to a maximum of 19 bits. The cores are event-driven using custom asynchronous and synchronous logic, and they are globally connected through an asynchronous packet switched mesh network on chip (NOC). The chip development board, includes a Zyng Xilinx FPGA that does the housekeeping and provides support for standard communication support through an Ethernet UDP interface. The asynchronous Addressed Event Representation (AER) in the NOC is al so exposed to the user for connection to AER based peripherals through a packet with bundled data full duplex interface. The unary data values represented on the system buses can take on a wide variety of spatial and temporal encoding schemes. Pulse density coding (the number of events Ne represents a number N), thermometer coding, time-slot encoding, and stochastic encoding are examples. Additional low level interfaces are available for communicating directly with the TrueNorth chip to aid programming and parameter setting. A hierarchical, compositional programming language, Corelet, is available to aid the development of TN applications. IBM provides support and a development system as well as “Compass” a scalable simulator. The software environment runs under standard Linux installations (Red Hat, CentOS and Ubuntu) and has standard interfaces to Matlab and to Caffe that is employed to train deep neural network models. The TN architecture can be interfaced using native AER to a number of bio-inspired sensory devices developed over many years of neuromorphic engineering (silicon retinas and silicon cochleas). In addition the architecture is well suited for implementing deep neural networks with many applications in computer vision, speech recognition and language processing. In a sensory information processing system architecture one desires both pattern processing in space and time to extract features in symbolic sub-spaces as well as natural language processing to provide contextual and semantic information in the form of priors. In this paper we discuss results from ongoing experimental work on real-time sensory information processing using the TN architecture in three different areas (i) spatial pattern processing -computer vision(ii) temporal pattern processing -speech processing and recognition(iii) natural language processing -word similarity-. A real-time demonstration will be done at ISCAS 2016 using the TN system and neuromorphic event based sensors for audition (silicon cochlea) and vision (silicon retina).

This paper describes an open-source implementation of an event-based dynamic and active pixel vision sensor (DAVIS) for racing human vs. computer on a slot car track. The DAVIS is mounted in "eye-of-god" view. The DAVIS image frames are only used for setup and are subsequently turned off because they are not needed. The dynamic vision sensor (DVS) events are then used to track both the human and computer controlled cars. The precise control of throttle and braking afforded by the low latency of the sensor output enables consistent outperformance of human drivers at a laptop CPU load of <;3% and update rate of 666Hz. The sparse output of the DVS event stream results in a data rate that is about 1000 times smaller than from a frame-based camera with the same resolution and update rate. The scaled average lap speed of the 1/64 scale cars is about 450km/h which is twice as fast as the fastest Formula 1 lap speed. A feedbackcontroller mode allows competitive racing by slowing the computer controlled car when it is ahead of the human. In tests of human vs. computer racing the computer still won more than 80% of the races.

This live demonstration shows real-time visual object recognition based on a spiking neural network adaptation of the HMAX model running on a purely event-based computational hardware platform. Visual input to the system is provided by an ATIS spiking silicon retina sensor. A SpiNNaker board processes the event-encoded visual information from the scene. Using a Leaky Integrate-and-Fire (LIF) neuron model implemented on SpiNNaker, an event-driven, multi-layer network is created that performs real-time orientation extraction and recombination. In this demonstration, the network will be tuned to recognize complex objects such as printed characters.

This paper presents a real-time spiking neural network adaptation of the HMAX object recognition model on an event-driven platform. Visual input is provided by a spiking silicon retina, while the SpiNNaker system is used as a computational hardware platform for implementation. We show the implementation of a simple Leaky Integrate-and-Fire (LIF) neuron model on SpiNNaker to create an event driven network, where a neuron only updates when it receives an interrupt indicating that a new input spike has been received. The model output consists of view tuned neurons which respond selectively to a particular view of an object. The network can be used to discriminate between objects, or between the same object at different views. On a 26 class character recognition task, the correct class is always assigned the highest probability (69.42% on average).

This paper introduces a spiking hierarchical model for object recognition which utilizes the precise timing information inherently present in the output of biologically inspired asynchronous address event representation (AER) vision sensors. The asynchronous nature of these systems frees computation and communication from the rigid predetermined timing enforced by system clocks in conventional systems. Freedom from rigid timing constraints opens the possibility of using true timing to our advantage in computation. We show not only how timing can be used in object recognition, but also how it can in fact simplify computation. Specifically, we rely on a simple temporal-winner-take-all rather than more computationally intensive synchronous operations typically used in biologically inspired neural networks for object recognition. This approach to visual computation represents a major paradigm shift from conventional clocked systems and can find application in other sensory modalities and computational tasks. We showcase effectiveness of the approach by achieving the highest reported accuracy to date (97.5% ± 3.5%) for a previously published four class card pip recognition task and an accuracy of 84.9% ± 1.9% for a new more difficult 36 class character recognition task.

This paper presents a frame-free time-domain imaging approach designed to alleviate the non-ideality of finite exposure measurement time (intrinsic to all integrating imagers), limiting the temporal resolution of the ATIS asynchronous time-based image sensor concept. The method uses the time-domain correlated double sampling (TCDS) and change detection circuitry already present in the data-driven autonomous ATIS pixels and does not involve any additional data to be transmitted by the sensor, but is entirely based on the data available in normal operation. Three consecutive exposure estimation / measurement steps apply different trade-offs between measurement speed, accuracy and noise. The early estimates yield between 10 and 100 times faster pixel updates than the standard full-swing integrating exposure measurement operation. The results from the three individual measurement steps can be used separately or in combination, enabling event-driven asynchronous high-speed imaging at moderate light levels.

Visual motion estimation is a computationally intensive, but important task for sighted animals. Replicating the robustness and efficiency of biological visual motion estimation in artificial systems would significantly enhance the capabilities of future robotic agents. Twenty five years ago, in this very journal, Carver Mead outlined his argument for replicating biological processing in silicon circuits. His vision served as the foundation for the field of neuromorphic engineering, which has experienced a rapid growth in interest over recent years as the ideas and technologies mature. Replicating biological visual sensing was one of the first tasks attempted in the neuromorphic field. In this paper, we focus specifically on the task of visual motion estimation. We describe the task itself, present the progression of works from the early first attempts through to the modern day state-of-the-art, and provide an outlook for future directions in the field.

Recognition of objects in still images has traditionally been regarded as a difficult computational problem. Although modern automated methods for visual object recognition have achieved steadily increasing recognition accuracy, even the most advanced computational vision approaches are unable to obtain performance equal to that of humans. This has led to the creation of many biologically inspired models of visual object recognition, among them the hierarchical model and X (HMAX) model. HMAX is traditionally known to achieve high accuracy in visual object recognition tasks at the expense of significant computational complexity. Increasing complexity, in turn, increases computation time, reducing the number of images that can be processed per unit time. In this paper we describe how the computationally intensive and biologically inspired HMAX model for visual object recognition can be modified for implementation on a commercial field-programmable aate Array, specifically the Xilinx Virtex 6 ML605 evaluation board with XC6VLX240T FPGA. We show that with minor modifications to the traditional HMAX model we can perform recognition on images of size 128 × 128 pixels at a rate of 190 images per second with a less than 1% loss in recognition accuracy in both binary and multiclass visual object recognition tasks.

Spiking neurons and spiking neural circuits are finding uses in a multitude of tasks such as robotic locomotion control, neuroprosthetics, visual sensory processing, and audition. The desired neural output is achieved through the use of complex neuron models, or by combining multiple simple neurons into a network. In either case, a means for configuring the neuron or neural circuit is required. Manual manipulation of parameters is both time consuming and non-intuitive due to the nonlinear relationship between parameters and the neuron's output. The complexity rises even further as the neurons are networked and the systems often become mathematically intractable. In large circuits, the desired behavior and timing of action potential trains may be known but the timing of the individual action potentials is unknown and unimportant, whereas in single neuron systems the timing of individual action potentials is critical. In this paper, we automate the process of finding parameters. To configure a single neuron we derive a maximum likelihood method for configuring a neuron model, specifically the Mihalas-Niebur Neuron. Similarly, to configure neural circuits, we show how we use genetic algorithms (GAs) to configure parameters for a network of simple integrate and fire with adaptation neurons. The GA approach is demonstrated both in software simulation and hardware implementation on a reconfigurable custom very large scale integration chip.

The cross-correlation function is an important yet computationally intensive processing step in many engineering applications such as wireless communication and object recognition. A neuromorphic approach to this function has been shown to facilitate implementation using a neural-based architecture. Using a custom designed array of silicon neurons on a compact, low-power chip, we demonstrate a cross-correlation system based on two half center oscillators. These preliminary results show the validity of this approach and could provide an elegant solution to wireless communication systems in the next generation of neuroprosthetic devices.

There are various neuron models which can be used to emulate the neural networks responsible for cortical and spinal processes. One example is the Central Pattern Generator (CPG) networks, which are spinal neural circuits responsible for controlling the timing of periodic systems in vertebrates. In order to model the CPG effectively, it is necessary to model not just multiple individual neurons, but also the interactions between them. Due to the complexity of these types of systems, CPG models typically require large numbers (> 10) of parameters making them difficult to understand and control. Genetic Algorithms (GAs) provide a means for optimizing systems with many parameters. We present an automated method that uses a GA to And sets of parameters for a silicon implementation of a neural network capable of producing CPG type signals. This methodology can be used to configure large silicon neural circuits. In this work, constructed networks involving an 18-parameter space, can be used for controlling legged robots and neuroprosthetic devices.

In limbed animals, spinal neural circuits responsible for controlling muscular activities during walking are called central pattern generators (CPG). CPG networks display oscillatory activities that actuates individual or groups of muscles in a coordinated fashion so that the limbs of the animal are flexed and extended at the appropriate time and with the required velocity for the animal to efficiently traverse various types of terrain, and to recover from environmental perturbation. Typically, the CPG networks are constructed with many neurons, each of which has a number of control parameters. As the number of muscles increases, it is often impossible to manually, albeit intelligently, select the network parameters for a particular movement. Furthermore, it is virtually impossible to reconfigure the parameters on-line. This paper describes how genetic algorithms (GA) can be used for on-line (re)configuring of CPG networks for a bipedal robot. We show that the neuron parameters and connection weights/network topology of a canonical walking network can be reconfigured within a few of generations of the GA. The networks, constructed with integrate-and-fire-with-adaptation (IFA) neurons, are implemented with a microcontroller and can be reconfigured to vary walking speed from 0.5Hz to 3.5Hz. The phase relationship between the hips and knees can be arbitrarily set (to within 1 degree) and prescribed complex joint angle profiles are realized. This is a powerful approach to generating complex muscle synergies for robots with multiple joints and distributed actuators.