Event cameras are paradigm-shifting novel sensors that report asynchronous, per-pixel brightness changes called 'events' with unparalleled low latency. This makes them ideal for high speed, high dynamic range scenes where conventional cameras would fail. Recent work has demonstrated impressive results using Convolutional Neural Networks (CNNs) for video reconstruction and optic flow with events. We present strategies for improving training data for event based CNNs that result in 20-40% boost in performance of existing state-of-the-art (SOTA) video reconstruction networks retrained with our method, and up to 15% for optic flow networks. A challenge in evaluating event based video reconstruction is lack of quality ground truth images in existing datasets. To address this, we present a new High Quality Frames (HQF) dataset, containing events and ground truth frames from a DAVIS240C that are well-exposed and minimally motion-blurred. We evaluate our method on HQF + several existing major event camera datasets.
Ain Shams University（艾因夏姆斯大学）；Delft University of Technology（代尔夫特理工大学）
In this paper, an approach for reducing the drift in monocular visual odometry algorithms is proposed based on a feedforward neural network. A visual odometry algorithm computes the incremental motion of the vehicle between the successive camera frames, then integrates these increments to determine the pose of the vehicle. The proposed neural network reduces the errors in the pose estimation of the vehicle which results from the inaccuracies in features detection and matching, camera intrinsic parameters, and so on. These inaccuracies are propagated to the motion estimation of the vehicle caus…
A*star, Institute of High Performance Computing（新加坡科技研究局高性能计算研究所）；York University（约克大学）
Linear perspectivecues deriving from regularities of the built environment can be used to recalibrate both intrinsic and extrinsic camera parameters online, but these estimates can be unreliable due to irregularities in the scene, uncertainties in line segment estimation and background clutter. Here we address this challenge through four initiatives. First, we use the PanoContext panoramic image dataset [27] to curate a novel and realistic dataset of planar projections over a broad range of scenes, focal lengths and camera poses. Second, we use this novel dataset and the YorkUrbanDB [4] to sys…
State Key Lab of CAD&CG, Zhejiang University（浙江大学CAD&CG国家重点实验室）；Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
In this paper, we present RKD-SLAM, a robust keyframe-based dense SLAM approach for an RGB-D camera that can robustly handle fast motion and dense loop closure, and run without time limitation in a moderate size scene. It not only can be used to scan high-quality 3D models, but also can satisfy the demand of VR and AR applications. First, we combine color and depth information to construct a very fast keyframe-based tracking method on a CPU, which can work robustly in challenging cases (e.g.~fast camera motion and complex loops). For reducing accumulation error, we also introduce a very effici…
CLRNet: Targetless Extrinsic Calibration for Camera, Lidar and 4D Radar Using Deep Learning
Hungarian Research Network Institute for Computer Science and Control (HUN-REN SZTAKI)（匈牙利研究网络计算机科学与控制研究所）；Pázmány Péter Catholic University（帕兹曼·佩斯特天主教大学）；Intelligent Vehicles Group, TU Delft（智能车辆组，代尔夫特理工大学）；Perciv AI
Glass Surface Segmentation with an RGB-D Camera via Weighted Feature Fusion for Service Robots
Fujian Provincial Key Laboratory of Information Processing and Intelligent Control（福建省信息处理与智能控制重点实验室）；Minjiang University（闽江学院）；European University Cyprus（塞浦路斯欧洲大学）；Fujian Hantewin Intelligent Technology Co., Ltd.（福建省翰文智能科技有限公司）
Multi-human 3D pose estimation plays a key role in establishing a seamless connection between the real world and the virtual world. Recent efforts adopted a two-stage framework that first builds 2D pose estimations in multiple camera views from different perspectives and then synthesizes them into 3D poses. However, the focus has largely been on developing new computer vision algorithms on the offline video datasets without much consideration on the energy constraints in real-world systems with flexibly-deployed and battery-powered cameras. In this paper, we propose an energy-efficient edge-as…
CRAB: Camera-Radar Fusion for Reducing Depth Ambiguity in Backward Projection based View Transformation
Interdisciplinary Program in Artificial intelligence, Seoul National University（人工智能跨学科项目，首尔国立大学）；Cho Chun Shik Graduate School of Mobility, KAIST（移动性研究生院，韩国科学技术院）；dot Inc（42dot公司）；Electronics and Telecommunications Research Institute (ETRI)（电子电信研究院）；Department of Automobile and IT Convergence, Kookmin University（汽车与IT融合系，韩国釜山大学）
Multiview camera setups have proven useful in many computer vision applications for reducing ambiguities, mitigating occlusions, and increasing field-of-view coverage. However, the high computational cost associated with multiple views poses a significant challenge for end devices with limited computational resources. To address this issue, we propose a view selection approach that analyzes the target object or scenario from given views and selects the next best view for processing. Our approach features a reinforcement learning based camera selection module, MVSelect, that not only selects vi…
Universidad Politécnica de Madrid（马德里理工大学）；Universidad Complutense de Madrid（马德里康普顿斯大学）
In 3D reconstruction, the recovery of the calibration parameters of the cameras is paramount since it provides metric information about the observed scene, e.g., measures of angles and ratios of distances. Autocalibration enables the estimation of the camera parameters without using a calibration device, but by enforcing simple constraints on the camera parameters. In the absence of information about the internal camera parameters such as the focal length and the principal point, the knowledge of the camera pixel shape is usually the only available constraint. Given a projective reconstruction…
University of Zurich（苏黎世大学）；ETH Zurich（苏黎世联邦理工学院）；Einstein Center Digital Future（爱因斯坦数字未来中心）
Event cameras are bio-inspired sensors providing significant advantages over standard cameras such as low latency, high temporal resolution, and high dynamic range. We propose a novel structured-light system using an event camera to tackle the problem of accurate and high-speed depth sensing. Our setup consists of an event camera and a laser-point projector that uniformly illuminates the scene in a raster scanning pattern during 16 ms. Previous methods match events independently of each other, and so they deliver noisy depth estimates at high scanning speeds in the presence of signal latency a…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；Google（谷歌）
We leverage unsupervised learning of depth, egomotion, and camera intrinsics to improve the performance of single-image semantic segmentation, by enforcing 3D-geometric and temporal consistency of segmentation masks across video frames. The predicted depth, egomotion, and camera intrinsics are used to provide an additional supervision signal to the segmentation model, significantly enhancing its quality, or, alternatively, reducing the number of labels the segmentation model needs. Our experiments were performed on the ScanNet dataset.
Reducing Annotation Burden in Physical Activity Research Using Vision-Language Models
Department of Population Health, University of Oxford（牛津大学流行病学与健康统计学系）；University of Oxford（牛津大学）；School of Epidemiology and Health Statistics, Chengdu Medical College（成都医学院流行病学与健康统计学系）
Person re-identification is a key technology for analyzing video-based human behavior; however, its application is still challenging in practical situations due to the performance degradation for domains different from those in the training data. Here, we propose an environment-constrained adaptive network for reducing the domain gap. This network refines pseudo-labels estimated via a self-training scheme by imposing multi-camera constraints. The proposed method incorporates person-pair information without person identity labels obtained from the environment into the model training. In additio…
Today, video cameras are deployed in dense for monitoring physical places e.g., city, industrial, or agricultural sites. In the current systems, each camera node sends its feed to a cloud server individually. However, this approach suffers from several hurdles including higher computation cost, large bandwidth requirement for analyzing the enormous data, and privacy concerns. In dense deployment, video nodes typically demonstrate a significant spatio-temporal correlation. To overcome these obstacles in current approaches, this paper introduces CONVINCE, a new approach to look at the network ca…
ReWorld-Track: A Recursive Event World Model for Language-Guided Multi-Camera Tracking
Huazhong University of Science and Technology（华中科技大学）；Jiangxi University of Water Resources and Electric Power（江西水利电力大学）；Zhongnan University of Economics and Law（中南财经政法大学）
University Politehnica of Bucharest（布加勒斯特理工大学）；The University of Edinburgh（爱丁堡大学）
Recent advancements in energy-efficient hardware technology is driving the exponential growth we are experiencing in the Internet of Things (IoT) space, with more pervasive computations being performed near to data generation sources. A range of intelligent devices and applications performing local detection is emerging (activity recognition, fitness monitoring, etc.) bringing with them obvious advantages such as reducing detection latency for improved interaction with devices and safeguarding user data by not leaving the device. Video processing holds utility for many emerging applications an…
Prediction skills can be crucial for the success of tasks where robots have limited time to act or joints actuation power. In such a scenario, a vision system with a fixed, possibly too low, sampling rate could lead to the loss of informative points, slowing down prediction convergence and reducing the accuracy. In this paper, we propose to exploit the low latency, motion-driven sampling, and data compression properties of event cameras to overcome these issues. As a use-case, we use a Panda robotic arm to intercept a ball bouncing on a table. To predict the interception point, we adopt a Stat…
Parking management systems, and vacancy-indication services in particular, can play a valuable role in reducing traffic and energy waste in large cities. Visual detection methods represent a cost-effective option, since they can take advantage of hardware usually already available in many parking lots, namely cameras. However, visual detection methods can be fragile and not easily generalizable. In this paper, we present a robust detection algorithm based on deep convolutional neural networks. We implemented and tested our algorithm on a large baseline dataset, and also on a set of image feeds…
Zhejiang University（浙江大学）；Kunming Cotech Communication & Information Systems Co., Ltd（昆明科泰通信信息系统有限公司）
A lensless camera is an imaging system that uses a mask in place of a lens, making it thinner, lighter, and less expensive than a lensed camera. However, additional complex computation and time are required for image reconstruction. This work proposes a deep learning model named Raw3dNet that recognizes hand gestures directly on raw videos captured by a lensless camera without the need for image restoration. In addition to conserving computational resources, the reconstruction-free method provides privacy protection. Raw3dNet is a novel end-to-end deep neural network model for the recognition …
Event Cameras Meet SPADs for High-Speed, Low-Bandwidth Imaging
Robotics and Perception Group, University of Zurich, Switzerland（苏黎世大学机器人与感知组）；Camera Culture Group, MIT Media Lab, USA（MIT媒体实验室相机文化组）；EPFL, Lausanne, Switzerland（日内瓦联邦理工学院）
本文提出融合事件相机与SPAD传感器的框架，利用两者互补特性，实现低光高速成像，在100 kHz时间分辨率下较传统相机提升超过5 dB PSNR，并降低带宽成本。
Modern cameras have limited dynamic ranges and often produce images with saturated or dark regions using a single exposure. Although the problem could be addressed by taking multiple images with different exposures, exposure fusion methods need to deal with ghosting artifacts and detail loss caused by camera motion or moving objects. This paper proposes a deep network for exposure fusion. For reducing the potential ghosting problem, our network only takes two images, an underexposed image and an overexposed one. Our network integrates together homography estimation for compensating camera moti…
Center for Advanced Vehicular Systems (CAVS), Mississippi State University（密西西比州立大学高级车辆系统中心（CAVS））
Collision avoidance is a critical task in many applications, such as ADAS (advanced driver-assistance systems), industrial automation and robotics. In an industrial automation setting, certain areas should be off limits to an automated vehicle for protection of people and high-valued assets. These areas can be quarantined by mapping (e.g., GPS) or via beacons that delineate a no-entry area. We propose a delineation method where the industrial vehicle utilizes a LiDAR {(Light Detection and Ranging)} and a single color camera to detect passive beacons and model-predictive control to stop the veh…
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）
