In this work, we present an optical space imaging dataset using a range of event-based neuromorphic vision sensors. The unique method of operation of event-based sensors makes them ideal for space situational awareness (SSA) applications due to the sparseness inherent in space imaging data. These sensors offer significantly lower bandwidth and power requirements making them particularly well suited for use in remote locations and space-based platforms. We present the first publicly-accessible event-based space imaging dataset including recordings using sensors from multiple providers, greatly lowering the barrier to entry for other researchers given the scarcity of such sensors and the expertise required to operate them for SSA applications. The dataset contains both day time and night time recordings, including simultaneous co-collections from different event-based sensors. Recorded at a remote site, and containing 572 labeled targets with a wide range of sizes, trajectories, and signal-tonoise ratios, this real-world event-based dataset represents a challenging detection and tracking task that is not readily solved using previously proposed methods. We propose a highly optimized and robust feature-based detection and tracking method, designed specifically for SSA applications, and implemented via a cascade of increasingly selective event filters. These filters rapidly isolate events associated with space objects, maintaining the high temporal resolution of the sensors. The results from this simple yet highly optimized algorithm on the space imaging dataset demonstrate robust high-speed event-based detection and tracking which can readily be implemented on sensor platforms in space as well as terrestrial environments.

The advent of large scale neural computational platforms has highlighted the lack of algorithms for synthesis of neural structures to perform predefined cognitive tasks. The Neural Engineering Framework (NEF) offers one such synthesis, but it is most effective for a spike rate representation of neural information, and it requires a large number of neurons to implement simple functions. We describe a neural network synthesis method that generates synaptic connectivity for neurons which process time-encoded neural signals, and which makes very sparse use of neurons. The method allows the user to specify—arbitrarily—neuronal characteristics such as axonal and dendritic delays, and synaptic transfer functions, and then solves for the optimal input-output relationship using computed dendritic weights. The method may be used for batch or online learning and has an extremely fast optimization process. We demonstrate its use in generating a network to recognize speech which is sparsely encoded as spike times.

Unsupervised feature extraction algorithms form one of the most important building blocks in machine learning systems. These algorithms are often adapted to the event-based domain to perform online learning in neuromorphic hardware. However, not designed for the purpose, such algorithms typically require significant simplification during implementation to meet hardware constraints, creating trade offs with performance. Furthermore, conventional feature extraction algorithms are not designed to generate useful intermediary signals which are valuable only in the context of neuromorphic hardware limitations. In this work a novel event-based feature extraction method is proposed that focuses on these issues. The algorithm operates via simple adaptive selection thresholds which allow a simpler implementation of network homeostasis than previous works by trading off a small amount of information loss in the form of missed events that fall outside the selection thresholds. The behavior of the selection thresholds and the output of the network as a whole are shown to provide uniquely useful signals indicating network weight convergence without the need to access network weights. A novel heuristic method for network size selection is proposed which makes use of noise events and their feature representations. The use of selection thresholds is shown to produce network activation patterns that predict classification accuracy allowing rapid evaluation and optimization of system parameters without the need to run back-end classifiers. The feature extraction method is tested on both the N-MNIST (Neuromorphic-MNIST) benchmarking dataset and a dataset of airplanes passing through the field of view. Multiple configurations with different classifiers are tested with the results quantifying the resultant performance gains at each processing stage.

In this work, we investigate event-based feature extraction through a rigorous framework of testing. We test a hardware efficient variant of Spike Timing Dependent Plasticity (STDP) on a range of spatio-temporal kernels with different surface decaying methods, decay functions, receptive field sizes, feature numbers, and back end classifiers. This detailed investigation can provide helpful insights and rules of thumb for performance vs. complexity trade-offs in more generalized networks, especially in the context of hardware implementation, where design choices can incur significant resource costs. The investigation is performed using a new dataset consisting of model airplanes being dropped free-hand close to the sensor. The target objects exhibit a wide range of relative orientations and velocities. This range of target velocities, analyzed in multiple configurations, allows a rigorous comparison of time-based decaying surfaces (time surfaces) vs. event index-based decaying surface (index surfaces), which are used to perform unsupervised feature extraction, followed by target detection and recognition. We examine each processing stage by comparison to the use of raw events, as well as a range of alternative layer structures, and the use of random features. By comparing results from a linear classifier and an ELM classifier, we evaluate how each element of the system affects accuracy. To generate time and index surfaces, the most commonly used kernels, namely event binning kernels, linearly, and exponentially decaying kernels, are investigated. Index surfaces were found to outperform time surfaces in recognition when invariance to target velocity was made a requirement. In the investigation of network structure, larger networks of neurons with large receptive field sizes were found to perform best. We find that a small number of event-based feature extractors can project the complex spatio-temporal event patterns of the dataset to an almost linearly separable representation in feature space, with best performing linear classifier achieving 98.75% recognition accuracy, using only 25 feature extracting neurons.

Single Photon Avalanche Diode sensor arrays operating in direct time of flight mode can perform 3D imaging using pulsed lasers. Operating at high frame rates, SPAD imagers typically generate large volumes of noisy and largely redundant spatio-temporal data. This results in communication bottlenecks and unnecessary data processing. In this work, we propose a neuromorphic processing solution to this problem. By processing the spatio-temporal patterns generated by the SPADs in a local, event-based manner, the proposed 128 × 128 pixel sensor-processor system reduces the size of output data from the sensor by orders of magnitude while increasing the utility of the output data in the context of challenging recognition tasks. To test the proposed system, the first large scale complex SPAD imaging dataset is captured using an existing 32 × 32 pixel sensor. The generated dataset consists of 24000 recordings and involves high-speed view-invariant recognition of airplanes with background clutter. The frame-based SPAD imaging dataset is converted via several alternative methods into event-based data streams and processed using the proposed 125 × 125 receptive field neuromorphic processor as well as a range of feature extractor networks and pooling methods. The output of the proposed event generation methods are then processed by an event-based feature extraction and classification system implemented in FPGA hardware. The event-based processing methods are compared to processing the original frame-based dataset via frame-based but otherwise identical architectures. The results show the event-based methods are superior to the frame-based approach both in terms of classification accuracy and output data-rate.

As an emerging approach to space situational awareness and space imaging, the practical use of an event-based camera (EBC) in space imaging for precise source analysis is still in its infancy. The nature of event-based space imaging and data collection needs to be further explored to develop more effective event-based space imaging systems and advance the capabilities of event-based tracking systems with improved target measurement models. Moreover, for event measurements to be meaningful, a framework must be investigated for EBC calibration to project events from pixel array coordinates in the image plane to coordinates in a target resident space object’s reference frame. In this paper, the traditional techniques of conventional astronomy are reconsidered to properly utilise the EBC for space imaging and space situational awareness. This paper presents the techniques and systems used for calibrating an EBC for reliable and accurate measurement acquisition. These techniques are vital in building event-based space imaging systems capable of real-world space situational awareness tasks. By calibrating sources detected using the EBC, the spatiotemporal characteristics of detected sources or “event sources” can be related to the photometric characteristics of the underlying astrophysical objects. Finally, these characteristics are analysed to establish a foundation for principled processing and observing techniques which appropriately exploit the capabilities of the EBC.