Since neuromorphic event-based pixels and cameras were first proposed, the technology has greatly advanced such that there now exists several industrial sensors, processors and toolchains. This has also paved the way for a blossoming new branch of AI dedicated to processing the event-based data these sensors generate. However, there is still much debate about which of these approaches can best harness the inherent sparsity, low-latency and fine spatiotemporal structure of event-data to obtain better performance and do so using the least time and energy. The latter is of particular importance since these algorithms will typically be employed near or inside of the sensor at the edge where the power supply may be heavily constrained. The two predominant methods to process visual events - convolutional and spiking neural networks - are fundamentally opposed in principle. The former converts events into static 2D frames such that they are compatible with 2D convolutions, while the latter computes in an event-driven fashion naturally compatible with the raw data. We review this dichotomy by studying recent algorithmic and hardware advances of both approaches. We conclude with a perspective on an emerging alternative approach whereby events are transformed into a graph data structure and thereafter processed using techniques from the domain of graph neural networks. Despite promising early results, algorithmic and hardware innovations are required before this approach can be applied close or within the Event-based sensor.

Event cameras encode visual information with high temporal precision, low data-rate, and high-dynamic range. Thanks to these characteristics, event cameras are particularly suited for scenarios with high motion, challenging lighting conditions and requiring low latency. However, due to the novelty of the field, the performance of event-based systems on many vision tasks is still lower compared to conventional frame-based solutions. The main reasons for this performance gap are: the lower spatial resolution of event sensors, compared to frame cameras; the lack of large-scale training datasets; the absence of well established deep learning architectures for event-based processing. In this paper, we address all these problems in the context of an event-based object detection task. First, we publicly release the first high-resolution large-scale dataset for object detection. The dataset contains more than 14 hours recordings of a 1 megapixel event camera, in automotive scenarios, together with 25M bounding boxes of cars, pedestrians, and two-wheelers, labeled at high frequency. Second, we introduce a novel recurrent architecture for event-based detection and a temporal consistency loss for better-behaved training. The ability to compactly represent the sequence of events into the internal memory of the model is essential to achieve high accuracy. Our model outperforms by a large margin feed-forward event-based architectures. Moreover, our method does not require any reconstruction of intensity images from events, showing that training directly from raw events is possible, more efficient, and more accurate than passing through an intermediate intensity image. Experiments on the dataset introduced in this work, for which events and gray level images are available, show performance on par with that of highly tuned and studied frame-based detectors.

We propose a learning approach to corner detection for event-based cameras that is stable even under fast and abrupt motions. Event-based cameras offer high temporal resolution, power efficiency, and high dynamic range. However, the properties of event-based data are very different compared to standard intensity images, and simple extensions of corner detection methods designed for these images do not perform well on event-based data. We first introduce an efficient way to compute a time surface that is invariant to the speed of the objects. We then show that we can train a Random Forest to recognize events generated by a moving corner from our time surface. Random Forests are also extremely efficient, and therefore a good choice to deal with the high capture frequency of event-based cameras-our implementation processes up to 1.6Mev/s on a single CPU. Thanks to our time surface formulation and this learning approach, our method is significantly more robust to abrupt changes of direction of the corners compared to previous ones. Our method also naturally assigns a confidence score for the corners, which can be useful for postprocessing. Moreover, we introduce a high-resolution dataset suitable for quantitative evaluation and comparison of corner detection methods for event-based cameras. We call our approach SILC, for Speed Invariant Learned Corners, and compare it to the state-of-the-art with extensive experiments, showing better performance.

Event-based cameras have recently drawn the attention of the Computer Vision community thanks to their advantages in terms of high temporal resolution, low power consumption and high dynamic range, compared to traditional frame-based cameras. These properties make event-based cameras an ideal choice for autonomous vehicles, robot navigation or UAV vision, among others. However, the accuracy of event-based object classification algorithms, which is of crucial importance for any reliable system working in real-world conditions, is still far behind their frame-based counterparts. Two main reasons for this performance gap are: 1. The lack of effective low-level representations and architectures for event-based object classification and 2. The absence of large real-world event-based datasets. In this paper we address both problems. First, we introduce a novel event-based feature representation together with a new machine learning architecture. Compared to previous approaches, we use local memory units to efficiently leverage past temporal information and build a robust event-based representation. Second, we release the first large real-world event-based dataset for object classification. We compare our method to the state-of-the-art with extensive experiments, showing better classification performance and real-time computation.

Finding the centerline and estimating the radius of linear structures is a critical first step in many applications, ranging from road delineation in 2D aerial images to modeling blood vessels, lung bronchi, and dendritic arbors in 3D biomedical image stacks. Existing techniques rely either on filters designed to respond to ideal cylindrical structures or on classification techniques. The former tend to become unreliable when the linear structures are very irregular while the latter often has difficulties distinguishing centerline locations from neighboring ones, thus losing accuracy. We solve this problem by reformulating centerline detection in terms of a regression problem. We first train regressors to return the distances to the closest centerline in scale-space, and we apply them to the input images or volumes. The centerlines and the corresponding scale then correspond to the regressors local maxima, which can be easily identified. We show that our method outperforms state-of-the-art techniques for various 2D and 3D datasets. Moreover, our approach is very generic and also performs well on contour detection. We show an improvement above recent contour detection algorithms on the BSDS500 dataset.

Detection of elongated structures in 2D images and 3D image stacks is a critical prerequisite in many applications and Machine Learning-based approaches have recently been shown to deliver superior performance. However, these methods essentially classify individual locations and do not explicitly model the strong relationship that exists between neighboring ones. As a result, isolated erroneous responses, discontinuities, and topological errors are present in the resulting score maps. We solve this problem by projecting patches of the score map to their nearest neighbors in a set of ground truth training patches. Our algorithm induces global spatial consistency on the classifier score map and returns results that are provably geometrically consistent. We apply our algorithm to challenging datasets in four different domains and show that it compares favorably to state-of-the-art methods.

Learning filters to produce sparse image representations in terms of over-complete dictionaries has emerged as a powerful way to create image features for many different purposes. Unfortunately, these filters are usually both numerous and non-separable, making their use computationally expensive. In this paper, we show that such filters can be computed as linear combinations of a smaller number of separable ones, thus greatly reducing the computational complexity at no cost in terms of performance. This makes filter learning approaches practical even for large images or 3D volumes, and we show that we significantly outperform state-of-the-art methods on the curvilinear structure extraction task, in terms of both accuracy and speed. Moreover, our approach is general and can be used on generic convolutional filter banks to reduce the complexity of the feature extraction step.

We propose a robust and accurate method to extract the centerlines and scale of tubular structures in 2D images and 3D volumes. Existing techniques rely either on filters designed to respond to ideal cylindrical structures, which lose accuracy when the linear structures become very irregular, or on classification, which is inaccurate because locations on centerlines and locations immediately next to them are extremely difficult to distinguish. We solve this problem by reformulating centerline detection in terms of a regression problem. We first train regressors to return the distances to the closest centerline in scale-space, and we apply them to the input images or volumes. The centerlines and the corresponding scale then correspond to the regressors local maxima, which can be easily identified. We show that our method outperforms state-of-the-art techniques for various 2D and 3D datasets.

Learning filters to produce sparse image representations in terms of over complete dictionaries has emerged as a powerful way to create image features for many different purposes. Unfortunately, these filters are usually both numerous and non-separable, making their use computationally expensive. In this paper, we show that such filters can be computed as linear combinations of a smaller number of separable ones, thus greatly reducing the computational complexity at no cost in terms of performance. This makes filter learning approaches practical even for large images or 3D volumes, and we show that we significantly outperform state-of-the-art methods on the linear structure extraction task, in terms of both accuracy and speed. Moreover, our approach is general and can be used on generic filter banks to reduce the complexity of the convolutions.