The bio-inspired event cameras or dynamic vision sensors are capable of asynchronously capturing per-pixel brightness changes (called event-streams) in high temporal resolution and high dynamic range. However, the non-structural spatial-temporal event-streams make it challenging for providing intuitive visualization with rich semantic information for human vision. It calls for events-to-video (E2V) solutions which take event-streams as input and generate high quality video frames for intuitive visualization. However, current solutions are predominantly data-driven without considering the prior knowledge of the underlying statistics relating event-streams and video frames. It highly relies on the non-linearity and generalization capability of the deep neural networks, thus, is struggling on reconstructing detailed textures when the scenes are complex. In this work, we propose \textbf{E2HQV}, a novel E2V paradigm designed to produce high-quality video frames from events. This approach leverages a model-aided deep learning framework, underpinned by a theory-inspired E2V model, which is meticulously derived from the fundamental imaging principles of event cameras. To deal with the issue of state-reset in the recurrent components of E2HQV, we also design a temporal shift embedding module to further improve the quality of the video frames. Comprehensive evaluations on the real world event camera datasets validate our approach, with E2HQV, notably outperforming state-of-the-art approaches, e.g., surpassing the second best by over 40\% for some evaluation metrics.
University of Washington（华盛顿大学）；Electronics and Telecommunications Research Institute（电子通信研究院）
In this paper, we propose a novel framework for multi-target multi-camera tracking (MTMCT) of vehicles based on metadata-aided re-identification (MA-ReID) and the trajectory-based camera link model (TCLM). Given a video sequence and the corresponding frame-by-frame vehicle detections, we first address the isolated tracklets issue from single camera tracking (SCT) by the proposed traffic-aware single-camera tracking (TSCT). Then, after automatically constructing the TCLM, we solve MTMCT by the MA-ReID. The TCLM is generated from camera topological configuration to obtain the spatial and tempora…
Camera calibration for estimating the intrinsic parameters and lens distortion is a prerequisite for various monocular vision applications including feature tracking and video stabilization. This application paper proposes a model for estimating the parameters on the fly by fusing gyroscope and camera data, both readily available in modern day smartphones. The model is based on joint estimation of visual feature positions, camera parameters, and the camera pose, the movement of which is assumed to follow the movement predicted by the gyroscope. Our model assumes the camera movement to be free,…
Event cameras are bio-inspired cameras which can measure the change of intensity asynchronously with high temporal resolution. One of the event cameras' advantages is that they do not suffer from motion blur when recording high-speed scenes. In this paper, we formulate the deblurring task on traditional cameras directed by events to be a residual learning one, and we propose corresponding network architectures for effective learning of deblurring and high frame rate video generation tasks. We first train a modified U-Net network to restore a sharp image from a blurry image using corresponding …
The rolling shutter camera has received great attention due to its low cost imaging capability, however, the estimation of relative pose between rolling shutter cameras still remains a difficult problem owing to its line-by-line image capturing characteristics. To alleviate this problem, we exploit gyroscope measurements, angular velocity, along with image measurement to compute the relative pose between rolling shutter cameras. The gyroscope measurements provide the information about instantaneous motion that causes the rolling shutter distortion. Having gyroscope measurements in one hand, we…
Millimeter wave (mmWave) and terahertz (THz) drones have the potential to enable several futuristic applications such as coverage extension, enhanced security monitoring, and disaster management. However, these drones need to deploy large antenna arrays and use narrow directive beams to maintain a sufficient link budget. The large beam training overhead associated with these arrays makes adjusting these narrow beams challenging for highly-mobile drones. To address these challenges, this paper proposes a vision-aided machine learning-based approach that leverages visual data collected from came…
Gwangju Institute of Science Technology (GIST)（光州科学技术院）
Relative pose estimation is a fundamental problem in computer vision and it has been studied for conventional global shutter cameras for decades. However, recently, a rolling shutter camera has been widely used due to its low cost imaging capability and, since the rolling shutter camera captures the image line-by-line, the relative pose estimation of a rolling shutter camera is more difficult than that of a global shutter camera. In this paper, we propose to exploit inertial measurements (gravity and angular velocity) for the rolling shutter relative pose estimation problem. The inertial measu…
Semantic grids are a useful representation of the environment around a robot. They can be used in autonomous vehicles to concisely represent the scene around the car, capturing vital information for downstream tasks like navigation or collision assessment. Information from different sensors can be used to generate these grids. Some methods rely only on RGB images, whereas others choose to incorporate information from other sensors, such as radar or LiDAR. In this paper, we present an architecture that fuses LiDAR and camera information to generate semantic grids. By using the 3D information fr…
We investigate the problem of wireless beam tracking on mmWave bands with the assistance of camera images. In particular, based on the user's beam indices used and camera images taken in the trajectory, we predict the optimal beam indices in the next few time spots. To resolve this problem, we first reformulate the "ViWi" dataset in [1] to get rid of the image repetition problem. Then we develop a deep learning approach and investigate various model components to achieve the best performance. Finally, we explore whether, when, and how to use the image for better beam prediction. To answer this…
Hong Kong University of Science and Technology（香港科技大学）；ETH Zurich（苏黎世联邦理工学院）
In this paper, we introduce a method for visual relocalization using the geometric information from a 3D surfel map. A visual database is first built by global indices from the 3D surfel map rendering, which provides associations between image points and 3D surfels. Surfel reprojection constraints are utilized to optimize the keyframe poses and map points in the visual database. A hierarchical camera relocalization algorithm then utilizes the visual database to estimate 6-DoF camera poses. Learned descriptors are further used to improve the performance in challenging cases. We present evaluati…
Fraunhofer Institute for Integrated Circuits IIS（弗劳恩霍夫集成电路研究所）；FAU Erlangen-Nuremberg（埃尔朗根-纽伦堡大学）；Ludwig-Maximilians-University (LMU)（慕尼黑大学）
Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks. Although Convolutional Neural Networks (CNNs) improve VO in various aspects, VO still suffers from moving obstacles, discontinuous observation of features, and poor textures or visual information. While recent approaches estimate a 6DoF pose either directly from (a series of) images or by merging depth maps with optical flow (OF), research that combines absolute pose regression with OF is limited. We propose ViPR, a novel modular architecture for long-term 6DoF VO that leverages temporal information and sy…
Monocular depth estimation has been actively studied in fields such as robot vision, autonomous driving, and 3D scene understanding. Given a sequence of color images, unsupervised learning methods based on the framework of Structure-From-Motion (SfM) simultaneously predict depth and camera relative pose. However, dynamically moving objects in the scene violate the static world assumption, resulting in inaccurate depths of dynamic objects. In this work, we propose a new method to address such dynamic object movements through monocular 3D object detection. Specifically, we first detect 3D object…
University of Trento（特伦托大学）；University of Vigo（维戈大学）
Video stabilization is an in-camera processing commonly applied by modern acquisition devices. While significantly improving the visual quality of the resulting videos, it has been shown that such operation typically hinders the forensic analysis of video signals. In fact, the correct identification of the acquisition source usually based on Photo Response non-Uniformity (PRNU) is subject to the estimation of the transformation applied to each frame in the stabilization phase. A number of techniques have been proposed for dealing with this problem, which however typically suffer from a high co…
Peking University（北京大学）；Capital Medical University（首都医科大学）
Spike camera mimicking the retina fovea can report per-pixel luminance intensity accumulation by firing spikes. As a bio-inspired vision sensor with high temporal resolution, it has a huge potential for computer vision. However, the sampling model in current Spike camera is so susceptible to quantization and noise that it cannot capture the texture details of objects effectively. In this work, a robust visual sampling model inspired by receptive field (RVSM) is proposed where wavelet filter generated by difference of Gaussian (DoG) and Gaussian filter are used to simulate receptive field. Usin…
AIT Austrian Institute of Technology（奥地利理工学院）；University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；Western Sydney University（西悉尼大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
The stomatopod (mantis shrimp) visual system has recently provided a blueprint for the design of paradigm-shifting polarization and multispectral imaging sensors, enabling solutions to challenging medical and remote sensing problems. However, these bioinspired sensors lack the high dynamic range (HDR) and asynchronous polarization vision capabilities of the stomatopod visual system, limiting temporal resolution to \~12 ms and dynamic range to \~ 72 dB. Here we present a novel stomatopod-inspired polarization camera which mimics the sustained and transient biological visual pathways to save pow…
With increasing physical threats in recent years targeted at critical infrastructures, it is crucial to establish a reliable threat monitoring system integrating video surveillance and digital sensors based on cutting-edge technologies. A physical threat monitoring solution unifying the floorplan, cameras, and sensors for smart buildings has been set up in our study. Computer vision and deep learning models are used for video streams analysis. When a threat is detected by a rule engine based on the real-time analysis results combining with feedback from related digital sensors, an alert is sen…
University of Maryland（马里兰大学）；Zhejiang University（浙江大学）；Huzhou Institute of Zhejiang University（浙江大学湖州研究院）；Hong Kong University of Science and Technology（香港科技大学）
University of Turku（图尔库大学）；Royal Institute of Technology (KTH)（瑞典皇家理工学院（KTH））；King Faisal University（费萨尔国王大学）
Moving towards autonomy, unmanned vehicles rely heavily on state-of-the-art collision avoidance systems (CAS). However, the detection of obstacles especially during night-time is still a challenging task since the lighting conditions are not sufficient for traditional cameras to function properly. Therefore, we exploit the powerful attributes of event-based cameras to perform obstacle detection in low lighting conditions. Event cameras trigger events asynchronously at high output temporal rate with high dynamic range of up to 120 $dB$. The algorithm filters background activity noise and extrac…
National Key Laboratory of Parallel and Distributed Processing（并行与分布式处理国家重点实验室）；National Key Laboratory of Integrated Automation of Process Industry（流程工业综合自动化国家重点实验室）；National University of Defense Technology（国防科技大学）；Northeastern University（东北大学）
The RGB-D camera maintains a limited range for working and is hard to accurately measure the depth information in a far distance. Besides, the RGB-D camera will easily be influenced by strong lighting and other external factors, which will lead to a poor accuracy on the acquired environmental depth information. Recently, deep learning technologies have achieved great success in the visual SLAM area, which can directly learn high-level features from the visual inputs and improve the estimation accuracy of the depth information. Therefore, deep learning technologies maintain the potential to ext…
Event-Aided Time-to-Collision Estimation for Autonomous Driving
School of Robotics, Hunan University（湖南大学机器人学院）；School of Engineering, Westlake University（西湖大学工程学院）；Dept. of ECE, Hong Kong University of Science and Technology（香港科技大学电子与计算机工程系）
ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Beijing Innovation Center of Humanoid Robotics Co., Ltd.（北京人形机器人创新中心有限公司）；Zhejiang University（浙江大学）
We present an unsupervised deep neural network approach to the fusion of RGB-D imagery with inertial measurements for absolute trajectory estimation. Our network, dubbed the Visual-Inertial-Odometry Learner (VIOLearner), learns to perform visual-inertial odometry (VIO) without inertial measurement unit (IMU) intrinsic parameters (corresponding to gyroscope and accelerometer bias or white noise) or the extrinsic calibration between an IMU and camera. The network learns to integrate IMU measurements and generate hypothesis trajectories which are then corrected online according to the Jacobians o…
Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University（复旦大学脑启发智能科学与技术研究院）；Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence (Fudan University), Ministry of Education（教育部计算神经科学与脑启发智能重点实验室（复旦大学））；State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University（北京师范大学认知神经科学与学习国家重点实验室）；School of Systems Science, Beijing Normal University（北京师范大学系统科学学院）
We propose a neurobiologically inspired visual simultaneous localization and mapping (SLAM) system based on direction sparse method to real-time build cognitive maps of large-scale environments from a moving stereo camera. The core SLAM system mainly comprises a Bayesian attractor network, which utilizes neural responses of head direction (HD) cells in the hippocampus and grid cells in the medial entorhinal cortex (MEC) to represent the head direction and the position of the robot in the environment, respectively. Direct sparse method is employed to accurately and robustly estimate velocity in…
Event-based cameras are novel, efficient sensors inspired by the human vision system, generating an asynchronous, pixel-wise stream of data. Learning from such data is generally performed through heavy preprocessing and event integration into images. This requires buffering of possibly long sequences and can limit the response time of the inference system. In this work, we instead propose to directly use events from a DVS camera, a stream of intensity changes and their spatial coordinates. This sequence is used as the input for a novel \emph{asynchronous} RNN-like architecture, the Input-filte…
Conventional frame-based camera is not able to meet the demand of rapid reaction for real-time applications, while the emerging dynamic vision sensor (DVS) can realize high speed capturing for moving objects. However, to achieve visual texture reconstruction, DVS need extra information apart from the output spikes. This paper introduces a fovea-like sampling method inspired by the neuron signal processing in retina, which aims at visual texture reconstruction only taking advantage of the properties of spikes. In the proposed method, the pixels independently respond to the luminance changes wit…
ERetinex: Event Camera Meets Retinex Theory for Low-Light Image Enhancement
School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件学院）；College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人工智能与机器人研究所）；School of Software, Tsinghua University（清华大学软件学院）
This paper demonstrates for the first time that a biologically-plausible spiking neural network (SNN) equipped with Spike-Timing-Dependent Plasticity (STDP) can continuously learn to detect walking people on the fly using retina-inspired, event-based cameras. Our pipeline works as follows. First, a short sequence of event data ($<2$ minutes), capturing a walking human by a flying drone, is forwarded to a convolutional SNNSTDP system which also receives teacher spiking signals from a readout (forming a semi-supervised system). Then, STDP adaptation is stopped and the learned system is assessed …
Moving object detection is important in computer vision. Event-based cameras are bio-inspired cameras that work by mimicking the working of the human eye. These cameras have multiple advantages over conventional frame-based cameras, like reduced latency, HDR, reduced motion blur during high motion, low power consumption, etc. In spite of these advantages, event-based cameras are noise-sensitive and have low resolution. Moreover, the task of moving object detection in these cameras is difficult, as event-based sensors lack useful visual features like texture and color. In this paper, we investi…
University of Science and Technology of China（中国科学技术大学）；Huawei Technologies Co., Ltd.（华为技术有限公司）
Event cameras, such as dynamic vision sensors (DVS), are biologically inspired vision sensors that have advanced over conventional cameras in high dynamic range, low latency and low power consumption, showing great application potential in many fields. Event cameras are more sensitive to junction leakage current and photocurrent as they output differential signals, losing the smoothing function of the integral imaging process in the RGB camera. The logarithmic conversion further amplifies noise, especially in low-contrast conditions. Recently, researchers proposed a series of datasets and eval…
This paper proposes a robust localization system that employs deep learning for better scene representation, and enhances the accuracy of 6-DOF camera pose estimation. Inspired by the fact that global scene structure can be revealed by wide field-of-view, we leverage the large overlap of a fisheye camera between adjacent frames, and the powerful high-level feature representations of deep learning. Our main contribution is the novel network architecture that extracts both temporal and spatial information using a Recurrent Neural Network. Specifically, we propose a novel pose regularization term…
Universidade Federal do Espírito Santo（圣埃斯皮里图联邦大学）
We propose a bio-inspired foveated technique to detect cars in a long range camera view using a deep convolutional neural network (DCNN) for the IARA self-driving car. The DCNN receives as input (i) an image, which is captured by a camera installed on IARA's roof; and (ii) crops of the image, which are centered in the waypoints computed by IARA's path planner and whose sizes increase with the distance from IARA. We employ an overlap filter to discard detections of the same car in different crops of the same image based on the percentage of overlap of detections' bounding boxes. We evaluated th…
The Global Positioning System (GPS) has become a part of our daily life with the primary goal of providing geopositioning service. For an unmanned aerial system (UAS), geolocalization ability is an extremely important necessity which is achieved using Inertial Navigation System (INS) with the GPS at its heart. Without geopositioning service, UAS is unable to fly to its destination or come back home. Unfortunately, GPS signals can be jammed and suffer from a multipath problem in urban canyons. Our goal is to propose an alternative approach to geolocalize a UAS when GPS signal is degraded or den…
Zhejiang University（浙江大学）；Hunan University（湖南大学）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Shanghai SUPREMIND Technology Company Ltd.（上海思普睿明科技有限公司）
Australian National University（澳大利亚国立大学）；ETH Zurich（苏黎世联邦理工学院）；Monash University（莫纳什大学）
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), contain…
Renault（雷诺）；LEAT / CNRS UMR 7248（LEAT / 法国国家科学研究中心 UMR 7248）；University Côte d’Azur（蔚蓝海岸大学）
Convolutional neural networks (CNNs) are now the de facto solution for computer vision problems thanks to their impressive results and ease of learning. These networks are composed of layers of connected units called artificial neurons, loosely modeling the neurons in a biological brain. However, their implementation on conventional hardware (CPU/GPU) results in high power consumption, making their integration on embedded systems difficult. In a car for example, embedded algorithms have very high constraints in term of energy, latency and accuracy. To design more efficient computer vision algo…
Technische Universität Berlin（柏林工业大学）；Einstein Center Digital Future（爱因斯坦数字未来中心）；Science of Intelligence Excellence Cluster（智能科学卓越集群）
Event cameras are bio-inspired sensors that offer advantages over traditional cameras. They operate asynchronously, sampling the scene at microsecond resolution and producing a stream of brightness changes. This unconventional output has sparked novel computer vision methods to unlock the camera's potential. Here, the problem of event-based stereo 3D reconstruction for SLAM is considered. Most event-based stereo methods attempt to exploit the high temporal resolution of the camera and the simultaneity of events across cameras to establish matches and estimate depth. By contrast, this work inve…
