We introduce the first very large detection dataset for event cameras. The dataset is composed of more than 39 hours of automotive recordings acquired with a 304x240 ATIS sensor. It contains open roads and very diverse driving scenarios, ranging from urban, highway, suburbs and countryside scenes, as well as different weather and illumination conditions. Manual bounding box annotations of cars and pedestrians contained in the recordings are also provided at a frequency between 1 and 4Hz, yielding more than 255,000 labels in total. We believe that the availability of a labeled dataset of this size will contribute to major advances in event-based vision tasks such as object detection and classification. We also expect benefits in other tasks such as optical flow, structure from motion and tracking, where for example, the large amount of data can be leveraged by self-supervised learning methods.
Spiking neural networks (SNNs) represent the most prominent biologically inspired computing model for neuromorphic computing (NC) architectures. However, due to the non-differentiable nature of spiking neuronal functions, the standard error back-propagation algorithm is not directly applicable to SNNs. In this work, we propose a tandem learning framework, that consists of an SNN and an Artificial Neural Network (ANN) coupled through weight sharing. The ANN is an auxiliary structure that facilitates the error back-propagation for the training of the SNN at the spike-train level. To this end, we consider the spike count as the discrete neural representation in the SNN, and design ANN neuronal activation function that can effectively approximate the spike count of the coupled SNN. The proposed tandem learning rule demonstrates competitive pattern recognition and regression capabilities on both the conventional frame-based and event-based vision datasets, with at least an order of magnitude reduced inference time and total synaptic operations over other state-of-the-art SNN implementations. Therefore, the proposed tandem learning rule offers a novel solution to training efficient, low latency, and high accuracy deep SNNs with low computing resources.
Event cameras are novel, bio-inspired visual sensors, whose pixels output asynchronous and independent timestamped spikes at local intensity changes, called 'events'. Event cameras offer advantages over conventional frame-based cameras in terms of latency, high dynamic range (HDR) and temporal resolution. Until recently, event cameras have been limited to outputting events in the intensity channel, however, recent advances have resulted in the development of color event cameras, such as the Color-DAVIS346. In this work, we present and release the first Color Event Camera Dataset (CED), containing 50 minutes of footage with both color frames and events. CED features a wide variety of indoor and outdoor scenes, which we hope will help drive forward event-based vision research. We also present an extension of the event camera simulator ESIM that enables simulation of color events. Finally, we present an evaluation of three state-of-the-art image reconstruction methods that can be used to convert the Color-DAVIS346 into a continuous-time, HDR, color video camera to visualise the event stream, and for use in downstream vision applications.
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 microseconds), very high dynamic range (140 dB vs. 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.
Event cameras are novel vision sensors that output pixel-level brightness changes ("events") instead of traditional video frames. These asynchronous sensors offer several advantages over traditional cameras, such as, high temporal resolution, very high dynamic range, and no motion blur. To unlock the potential of such sensors, motion compensation methods have been recently proposed. We present a collection and taxonomy of twenty two objective functions to analyze event alignment in motion compensation approaches (Fig. 1). We call them Focus Loss Functions since they have strong connections with functions used in traditional shape-from-focus applications. The proposed loss functions allow bringing mature computer vision tools to the realm of event cameras. We compare the accuracy and runtime performance of all loss functions on a publicly available dataset, and conclude that the variance, the gradient and the Laplacian magnitudes are among the best loss functions. The applicability of the loss functions is shown on multiple tasks: rotational motion, depth and optical flow estimation. The proposed focus loss functions allow to unlock the outstanding properties of event cameras.
Neuromorphic image sensors produce activity-driven spiking output at every pixel. These low-power consuming imagers which encode visual change information in the form of spikes help reduce computational overhead and realize complex real-time systems; object recognition and pose-estimation to name a few. However, there exists a lack of algorithms in event-based vision aimed towards capturing invariance to transformations. In this work, we propose a methodology for recognizing objects invariant to their pose with the Dynamic Vision Sensor (DVS). A novel slow-ELM architecture is proposed which combines the effectiveness of Extreme Learning Machines and Slow Feature Analysis. The system, tested on an Intel Core i5-4590 CPU, can perform 10,000 classifications per second and achieves 1% classification error for 8 objects with views accumulated over 90 degrees of 2D pose.
Unlike conventional frame-based sensors, event-based visual sensors output information through spikes at a high temporal resolution. By only encoding changes in pixel intensity, they showcase a low-power consuming, low-latency approach to visual information sensing. To use this information for higher sensory tasks like object recognition and tracking, an essential simplification step is the extraction and learning of features. An ideal feature descriptor must be robust to changes involving (i) local transformations and (ii) re-appearances of a local event pattern. To that end, we propose a novel spatiotemporal feature representation learning algorithm based on slow feature analysis (SFA). Using SFA, smoothly changing linear projections are learnt which are robust to local visual transformations. In order to determine if the features can learn to be invariant to various visual transformations, feature point tracking tasks are used for evaluation. Extensive experiments across two datasets demonstrate the adaptability of the spatiotemporal feature learner to translation, scaling and rotational transformations of the feature points. More importantly, we find that the obtained feature representations are able to exploit the high temporal resolution of such event-based cameras in generating better feature tracks.
The combination of spiking neural networks and event-based vision sensors holds the potential of highly efficient and high-bandwidth optical flow estimation. This paper presents the first hierarchical spiking architecture in which motion (direction and speed) selectivity emerges in an unsupervised fashion from the raw stimuli generated with an event-based camera. A novel adaptive neuron model and stable spike-timing-dependent plasticity formulation are at the core of this neural network governing its spike-based processing and learning, respectively. After convergence, the neural architecture exhibits the main properties of biological visual motion systems, namely feature extraction and local and global motion perception. Convolutional layers with input synapses characterized by single and multiple transmission delays are employed for feature and local motion perception, respectively; while global motion selectivity emerges in a final fully-connected layer. The proposed solution is validated using synthetic and real event sequences. Along with this paper, we provide the cuSNN library, a framework that enables GPU-accelerated simulations of large-scale spiking neural networks. Source code and samples are available at https://github.com/tudelft/cuSNN.
Event-based cameras are neuromorphic sensors capable of efficiently encoding visual information in the form of sparse sequences of events. Being biologically inspired, they are commonly used to exploit some of the computational and power consumption benefits of biological vision. In this paper we focus on a specific feature of vision: visual attention. We propose two attentive models for event based vision: an algorithm that tracks events activity within the field of view to locate regions of interest and a fully-differentiable attention procedure based on DRAW neural model. We highlight the strengths and weaknesses of the proposed methods on four datasets, the Shifted N-MNIST, Shifted MNIST-DVS, CIFAR10-DVS and N-Caltech101 collections, using the Phased LSTM recognition network as a baseline reference model obtaining improvements in terms of both translation and scale invariance.
Clustering is crucial for many computer vision applications such as robust tracking, object detection and segmentation. This work presents a real-time clustering technique that takes advantage of the unique properties of event-based vision sensors. Since event-based sensors trigger events only when the intensity changes, the data is sparse, with low redundancy. Thus, our approach redefines the well-known mean-shift clustering method using asynchronous events instead of conventional frames. The potential of our approach is demonstrated in a multi-target tracking application using Kalman filters to smooth the trajectories. We evaluated our method on an existing dataset with patterns of different shapes and speeds, and a new dataset that we collected. The sensor was attached to the Baxter robot in an eye-in-hand setup monitoring real-world objects in an action manipulation task. Clustering accuracy achieved an F-measure of 0.95, reducing the computational cost by 88% compared to the frame-based method. The average error for tracking was 2.5 pixels and the clustering achieved a consistent number of clusters along time.
Event-based vision sensors mimic the operation of biological retina and they represent a major paradigm shift from traditional cameras. Instead of providing frames of intensity measurements synchronously, at artificially chosen rates, event-based cameras provide information on brightness changes asynchronously, when they occur. Such non-redundant pieces of information are called "events". These sensors overcome some of the limitations of traditional cameras (response time, bandwidth and dynamic range) but require new methods to deal with the data they output. We tackle the problem of event-based camera localization in a known environment, without additional sensing, using a probabilistic generative event model in a Bayesian filtering framework. Our main contribution is the design of the likelihood function used in the filter to process the observed events. Based on the physical characteristics of the sensor and on empirical evidence of the Gaussian-like distribution of spiked events with respect to the brightness change, we propose to use the contrast residual as a measure of how well the estimated pose of the event-based camera and the environment explain the observed events. The filter allows for localization in the general case of six degrees-of-freedom motions.
Deep spiking neural networks (SNNs) hold great potential for improving the latency and energy efficiency of deep neural networks through event-based computation. However, training such networks is difficult due to the non-differentiable nature of asynchronous spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are only considered as noise. This enables an error backpropagation mechanism for deep SNNs, which works directly on spike signals and membrane potentials. Thus, compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statics of spikes more precisely. Our novel framework outperforms all previously reported results for SNNs on the permutation invariant MNIST benchmark, as well as the N-MNIST benchmark recorded with event-based vision sensors.
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-features 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) For overcoming the low-sample problem for the one-shot learning of a binary classifier, statistical bootstrapping is leveraged with online learning; (ii) To achieve tracker robustness, the scale and rotation equivariance property of the DART descriptors is exploited for the one-shot learning. (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.
Event-based vision sensors, such as the Dynamic Vision Sensor (DVS), are ideally suited for real-time motion analysis. The unique properties encompassed in the readings of such sensors provide high temporal resolution, superior sensitivity to light and low latency. These properties provide the grounds to estimate motion extremely reliably in the most sophisticated scenarios but they come at a price - modern event-based vision sensors have extremely low resolution and produce a lot of noise. Moreover, the asynchronous nature of the event stream calls for novel algorithms. This paper presents a new, efficient approach to object tracking with asynchronous cameras. We present a novel event stream representation which enables us to utilize information about the dynamic (temporal) component of the event stream, and not only the spatial component, at every moment of time. This is done by approximating the 3D geometry of the event stream with a parametric model; as a result, the algorithm is capable of producing the motion-compensated event stream (effectively approximating egomotion), and without using any form of external sensors in extremely low-light and noisy conditions without any form of feature tracking or explicit optical flow computation. We demonstrate our framework on the task of independent motion detection and tracking, where we use the temporal model inconsistencies to locate differently moving objects in challenging situations of very fast motion.
Super-resolution (SR) is a useful technology to generate a high-resolution (HR) visual output from the low-resolution (LR) visual inputs overcoming the physical limitations of the cameras. However, SR has not been applied to enhance the resolution of spatiotemporal event-stream images captured by the frame-free dynamic vision sensors (DVSs). SR of event-stream image is fundamentally different from existing frame-based schemes since basically each pixel value of DVS images is an event sequence. In this work, a two-stage scheme is proposed to solve the SR problem of the spatiotemporal event-stream image. We use a nonhomogeneous Poisson point process to model the event sequence, and sample the events of each pixel by simulating a nonhomogeneous Poisson process according to the specified event number and rate function. Firstly, the event number of each pixel of the HR DVS image is determined with a sparse signal representation based method to obtain the HR event-count map from that of the LR DVS recording. The rate function over time line of the point process of each HR pixel is computed using a spatiotemporal filter on the corresponding LR neighbor pixels. Secondly, the event sequence of each new pixel is generated with a thinning based event sampling algorithm. Two metrics are proposed to assess the event-stream SR results. The proposed method is demonstrated through obtaining HR event-stream images from a series of DVS recordings with the proposed method. Results show that the upscaled HR event streams has perceptually higher spatial texture detail than the LR DVS images. Besides, the temporal properties of the upscaled HR event streams match that of the original input very well. This work enables many potential applications of event-based vision.
Object tracking based on retina-inspired and event-based dynamic vision sensor (DVS) is challenging for the noise events, rapid change of event-stream shape, chaos of complex background textures, and occlusion. To address these challenges, this paper presents a robust event-stream pattern tracking method based on correlative filter mechanism. In the proposed method, rate coding is used to encode the event-stream object in each segment. Feature representations from hierarchical convolutional layers of a deep convolutional neural network (CNN) are used to represent the appearance of the rate encoded event-stream object. The results prove that our method not only achieves good tracking performance in many complicated scenes with noise events, complex background textures, occlusion, and intersected trajectories, but also is robust to variable scale, variable pose, and non-rigid deformations. In addition, this correlative filter based event-stream tracking has the advantage of high speed. The proposed approach will promote the potential applications of these event-based vision sensors in self-driving, robots and many other high-speed scenes.
Event cameras are bio-inspired vision sensors that naturally capture the dynamics of a scene, filtering out redundant information. This paper presents a deep neural network approach that unlocks the potential of event cameras on a challenging motion-estimation task: prediction of a vehicle's steering angle. To make the best out of this sensor-algorithm combination, we adapt state-of-the-art convolutional architectures to the output of event sensors and extensively evaluate the performance of our approach on a publicly available large scale event-camera dataset (~1000 km). We present qualitative and quantitative explanations of why event cameras allow robust steering prediction even in cases where traditional cameras fail, e.g. challenging illumination conditions and fast motion. Finally, we demonstrate the advantages of leveraging transfer learning from traditional to event-based vision, and show that our approach outperforms state-of-the-art algorithms based on standard cameras.
행동 인식(action recognition)은 로보틱스, 환자 모니터링, 감시와 같은 분야에서 중요한 과제이다. 최근 이벤트 카메라가 빠른 움직임을 포착할 수 있는 능력과 기존 비전 카메라에 비해 개선된 프라이버시를 제공한다는 점 때문에 이벤트 기반 행동 인식이 큰 주목을 받고 있다. 프레임 기반 이벤트 표현은 짧은 이벤트 시퀀스에서는 잘 동작하지만, 더 길고 복잡한 이벤트 시퀀스에서는 판별력이 급격히 저하된다. 본 연구에서는 단일 프레임 표현에 비해 인식 성능을 크게 향상시키는 멀티프레임 표현을 제안한다. 우리는 다운스트림 성능을 개선하고 계산 복잡도를 제어하기 위해 희소성(sparsity)을 고려한 마스킹 알고리즘과 토큰 선택 메커니즘을 사용하여 비전 트랜스포머(Vision Transformer)를 사전학습하는 마스크드 오토인코딩(masked auto-encoding) 프레임워크를 채택한다. 또한 위치 인식 어텐션 메커니즘을 갖춘 디코더용 다중 마스크 토큰을 도입하여 성능을 더욱 향상시킨다. 제안하는 방법은 도전적인 장시간의 복잡한 이벤트 시퀀스에서 인상적인 성능을 보이며, THU-EACT-50 CHL 및 DailyDVS-200에서 최신 기술(state-of-the-art) 수준의 성능을 달성한다.
본 논문에서는 미래 모션 필드(motion field)를 명시적으로 모델링하면서 기존 방식처럼 긴 이력이나 제어 사전 정보(prior)를 요구하지 않고, 단일 이벤트-RGB 쌍으로부터 미래 4D 동적 장면(RGB, 깊이, 광학 흐름)을 생성하는 디퓨전(diffusion) 기반 프레임워크인 UniDynamics를 제안합니다. 핵심 아이디어는 이벤트 스트림을 활용하여 단일 RGB 외삽(extrapolation)을 위한 대안적 모션 사전 정보를 제공하고, 멀티모달 모델링을 통해 생성 전반에 걸쳐 기하학적 및 모션 제약 조건을 강제하는 것입니다. 구체적으로, 이벤트 잠재 표현을 정렬하고 강화하여 디퓨전에 주입 가능한 조건화 피처로 변환하는 이벤트 잠재 강화(ELE, Event Latent Enhancement) 모듈을 설계하여 강건한 초기 모션 사전 정보와 신뢰할 수 있는 텍스처/구조 단서를 제공합니다. 나아가 멀티스케일 U-Net에 임베딩된 지각 동역학 공간(PDS, Perceptual Dynamics Space)을 도입하여 깊이와 흐름을 분리하고 적응적으로 상호작용하도록 하는 동시에 외형 피처에 제약 조건을 지속적으로 피드백함으로써 기하학적-모션 일관성을 향상시켜 물리적으로 타당하고 시공간적으로 일관된 예측을 가능하게 합니다. VKitti2 및 DSEC 데이터셋에 대한 실험은 최첨단(state-of-the-art) 성능을 입증하며, 특히 까다로운 고속 모션 블러 환경에서도 고품질의 시간적으로 일관되고 4D 일관성을 갖춘 미래 예측을 생성함을 보여줍니다.
이벤트 카메라는 고속 로봇 시스템에서 낮은 지연의 인지를 약속하지만, 짧은 지연조차도 검출 결과가 하위 로봇 의사결정에 반영될 때쯤에는 이미 낡은 정보가 될 수 있다. 그럼에도 최신 이벤트 검출기는 예측이 사용 가능해지기까지 수십 밀리초의 연산을 여전히 요구한다. 기존 평가는 관측 시각의 주석과 예측을 비교하여 이 지연을 무시하는데, 실제로는 그 예측이 생성될 때쯤 장면이 이미 바뀌었을 수 있다. 본 연구는 이벤트 기반 다중 객체 검출에서 이러한 관측–가용성 불일치를 분석하고, 최신 이벤트 검출기가 관측 시각이 아니라 예측 가용 시각 기준으로 평가할 때 성능이 크게 저하됨을 보인다. 이를 해결하기 위해 ChronoFuse를 제안한다. ChronoFuse는 입력이 관측된 시각이 아니라 출력이 사용 가능해지는 시각의 객체 상태를 예측하는 인과적 가용-시각 검출기이다. ChronoFuse는 다중 스케일 특징 계층에 걸친 인과적 교차-시간 융합을 수행하여, 캐시된 시간적 특징과 현재 표현을 결합함으로써 미래 관측을 사용하지 않고 단기 시간적 단서를 드러낸다. 융합 경로는 경량이며, 평균 end-to-end 지연 오버헤드는 0.17백만 개의 파라미터와 0.84 ms만 추가한다. ChronoFuse는 1Mpx 주행 데이터에서 지연으로 인한 정확도 손실의 71%를 회복하고, FRED의 급격한 드론 움직임에서는 90.8%를 회복하여 거의 무지연 성능에 가깝게 복원한다. EV-Flying의 극한적인 움직임에서는 ChronoFuse가 20.95 sAP에 도달하며, 가장 강한 표준 이벤트 검출기의 2.25 대비 9.3배 향상을 보인다. 이 결과는 자율주행, 민첩 비행, 로봇 요격 등 빠르게 변하는 장면에서 동작하는 로봇에게 선행 예측이 핵심적일 수 있음을 보여준다.