Commodity RGB-D sensors capture color images along with dense pixel-wise depth information in real-time. Typical RGB-D sensors are provided with a factory calibration and exhibit erratic depth readings due to coarse calibration values, ageing and thermal influence effects. This limits their applicability in computer vision and robotics. We propose a novel method to accurately calibrate depth considering spatial and thermal influences jointly. Our work is based on Gaussian Process Regression in a four dimensional Cartesian and thermal domain. We propose to leverage modern GPUs for dense depth map correction in real-time. For reproducibility we make our dataset and source code publicly available.
UBATrack: Spatio-Temporal State Space Model for General Multi-Modal Tracking
Key Laboratory of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University（教育区块链与智能技术重点实验室，教育部，广西师范大学）；Guangxi Key Laboratory of Multi-Source Information Mining and Security, Guangxi Normal University（广西多源信息挖掘与安全重点实验室，广西师范大学）；University Engineering Research Center of Educational Intelligent Technology, Guangxi Normal University（教育智能技术大学工程研究中心，广西师范大学）；Guangxi Key Laboratory of Machine Vision and Intelligent Control, Wuzhou University（广西机器视觉与智能控制重点实验室，梧州大学）
This paper proposes a novel polarization sensor structure and network architecture to obtain a high-quality RGB image and polarization information. Conventional polarization sensors can simultaneously acquire RGB images and polarization information, but the polarizers on the sensor degrade the quality of the RGB images. There is a trade-off between the quality of the RGB image and polarization information as fewer polarization pixels reduce the degradation of the RGB image but decrease the resolution of polarization information. Therefore, we propose an approach that resolves the trade-off by …
Oxford e-Research Centre（牛津电子研究中心）；University Of Oxford（牛津大学）
That the Microsoft Kinect, an RGB-D sensor, transformed the gaming and end consumer sector has been anticipated by the developers. That it also impacted in rigorous computer vision research has probably been a surprise to the whole community. Shortly before the commercial deployment of its successor, Kinect One, the research literature fills with resumees and state-of-the art papers to summarize the development over the past 3 years. This particular report describes significant research projects which have built on sensoring setups that include two or more RGB-D sensors in one scene.
Dynamic Subframe Splitting and Spatio-Temporal Motion Entangled Sparse Attention for RGB-E Tracking
School of Artificial Intelligence and Computer Science, Jiangnan University（江南大学人工智能与计算机学院）；Centre for Vision, Speech and Signal Processing, University of Surrey（萨里大学视觉、语音与信号处理中心）
University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）
This article describes novel approaches to quickly estimate planar surfaces from RGBD sensor data. The approach manipulates the standard algebraic fitting equations into a form that allows many of the needed regression variables to be computed directly from the camera calibration information. As such, much of the computational burden required by a standard algebraic surface fit can be pre-computed. This provides a significant time and resource savings, especially when many surface fits are being performed which is often the case when RGBD point-cloud data is being analyzed for normal estimatio…
OSRAM GmbH（欧司朗有限公司）；Istituto Italiano di Tecnologia (IIT)（意大利技术研究院）；University of Verona (UNIVR)（维罗纳大学）
Lighting design and modelling or industrial applications like luminaire planning and commissioning rely heavily on time consuming manual measurements or on physically coherent computational simulations. Regarding the latter,standard approaches are based on CAD modeling simulations and offline rendering, with long processing times and therefore inflexible workflows. Thus, in this paper we pro-pose a computer vision based system to measure lighting with just a single RGBD camera. The proposed method uses both depth data and images from the sensor to provide a dense measure of light intensity in …
A novel approach towards depth map super-resolution using multi-view uncalibrated photometric stereo is presented. Practically, an LED light source is attached to a commodity RGB-D sensor and is used to capture objects from multiple viewpoints with unknown motion. This non-static camera-to-object setup is described with a nonconvex variational approach such that no calibration on lighting or camera motion is required due to the formulation of an end-to-end joint optimization problem. Solving the proposed variational model results in high resolution depth, reflectance and camera pose estimates,…
The ability to estimate 3D human body pose and movement, also known as human pose estimation (HPE), enables many applications for home-based health monitoring, such as remote rehabilitation training. Several possible solutions have emerged using sensors ranging from RGB cameras, depth sensors, millimeter-Wave (mmWave) radars, and wearable inertial sensors. Despite previous efforts on datasets and benchmarks for HPE, few dataset exploits multiple modalities and focuses on home-based health monitoring. To bridge the gap, we present mRI, a multi-modal 3D human pose estimation dataset with mmWave,…
Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor
Department of Precision Instrument, Tsinghua University（清华大学精密仪器系）；Pen-Tung Sah Institute of Micro-Nano Science and Technology, Xiamen University（厦门大学萨本栋微米纳米科学技术研究院）；Communication University of China（中国传媒大学）；Primevision Technology（普视科技）
Crowd counting research has made significant advancements in real-world applications, but it remains a formidable challenge in cross-modal settings. Most existing methods rely solely on the optical features of RGB images, ignoring the feasibility of other modalities such as thermal and depth images. The inherently significant differences between the different modalities and the diversity of design choices for model architectures make cross-modal crowd counting more challenging. In this paper, we propose Cross-modal Spatio-Channel Attention (CSCA) blocks, which can be easily integrated into any…
This paper proposes a new optical camouflage system that uses RGB-D cameras, for acquiring point cloud of background scene, and tracking observers eyes. This system enables a user to conceal an object located behind a display that surrounded by 3D objects. If we considered here the tracked point of observer s eyes is a light source, the system will work on estimating shadow shape of the display device that falls on the objects in background. The system uses the 3d observer s eyes and the locations of display corners to predict their shadow points which have nearest neighbors in the constructed…
Light-weight time-of-flight (ToF) depth sensors are small, cheap, low-energy and have been massively deployed on mobile devices for the purposes like autofocus, obstacle detection, etc. However, due to their specific measurements (depth distribution in a region instead of the depth value at a certain pixel) and extremely low resolution, they are insufficient for applications requiring high-fidelity depth such as 3D reconstruction. In this paper, we propose DELTAR, a novel method to empower light-weight ToF sensors with the capability of measuring high resolution and accurate depth by cooperati…
University of Luxembourg（卢森堡大学）；Université de Bourgogne（勃艮第大学）；IEE S.A.（IEE公司）
Complete and textured 3D reconstruction of dynamic scenes has been facilitated by mapped RGB and depth information acquired by RGB-D cameras based multi-view systems. One of the most critical steps in such multi-view systems is to determine the relative poses of all cameras via a process known as extrinsic calibration. In this work, we propose a sensor fusion framework based on a weighted bi-objective optimization for refinement of extrinsic calibration tailored for RGB-D multi-view systems. The weighted bi-objective cost function, which makes use of 2D information from RGB images and 3D infor…
University of Chinese Academy of Sciences（中国科学院大学）
The dynamics of human skeletons have significant information for the task of action recognition. The similarity between trajectories of corresponding joints is an indicating feature of the same action, while this similarity may subject to some distortions that can be modeled as the combination of spatial and temporal affine transformations. In this work, we propose a novel feature called spatio-temporal dual affine differential invariant (STDADI). Furthermore, in order to improve the generalization ability of neural networks, a channel augmentation method is proposed. On the large scale action…
University of Bristol（布里斯托大学）；University of Cambridge（剑桥大学）
We describe a new method for comparing frame appearance in a frame-to-model 3-D mapping and tracking system using an low dynamic range (LDR) RGB-D camera which is robust to brightness changes caused by auto exposure. It is based on a normalised radiance measure which is invariant to exposure changes and not only robustifies the tracking under changing lighting conditions, but also enables the following exposure compensation perform accurately to allow online building of high dynamic range (HDR) maps. The latter facilitates the frame-to-model tracking to minimise drift as well as better capturi…
Ankara University（安卡拉大学）；Hacettepe University（哈塞特佩大学）
Sign language recognition using computational models is a challenging problem that requires simultaneous spatio-temporal modeling of the multiple sources, i.e. faces, hands, body, etc. In this paper, we propose an isolated sign language recognition model based on a model trained using Motion History Images (MHI) that are generated from RGB video frames. RGB-MHI images represent spatio-temporal summary of each sign video effectively in a single RGB image. We propose two different approaches using this RGB-MHI model. In the first approach, we use the RGB-MHI model as a motion-based spatial atten…
MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Bonn（波恩大学）
Hand motion capture has been an active research topic in recent years, following the success of full-body pose tracking. Despite similarities, hand tracking proves to be more challenging, characterized by a higher dimensionality, severe occlusions and self-similarity between fingers. For this reason, most approaches rely on strong assumptions, like hands in isolation or expensive multi-camera systems, that limit the practical use. In this work, we propose a framework for hand tracking that can capture the motion of two interacting hands using only a single, inexpensive RGB-D camera. Our approa…
Université Laval（拉瓦尔大学）；Thales Digital Solutions（泰雷兹数字解决方案）；Inria（法国国家信息与自动化研究所）
Augmented reality devices require multiple sensors to perform various tasks such as localization and tracking. Currently, popular cameras are mostly frame-based (e.g. RGB and Depth) which impose a high data bandwidth and power usage. With the necessity for low power and more responsive augmented reality systems, using solely frame-based sensors imposes limits to the various algorithms that needs high frequency data from the environement. As such, event-based sensors have become increasingly popular due to their low power, bandwidth and latency, as well as their very high frequency data acquisi…
Over the past ten years we have seen a democratization of range sensing technology. While previously range sensors have been highly expensive and only accessible to a few domain experts, such sensors are nowadays ubiquitous and can even be found in the latest generation of mobile devices, e.g., current smartphones. This democratization of range sensing technology was started with the release of the Microsoft Kinect, and since then many different commodity range sensors followed its lead, such as the Primesense Carmine, Asus Xtion Pro, and the Structure Sensor from Occipital. The availability o…
This paper presents a robust and efficient semi-dense visual odometry solution for RGB-D cameras. The core of our method is a 2D-3D ICP pipeline which estimates the pose of the sensor by registering the projection of a 3D semi-dense map of the reference frame with the 2D semi-dense region extracted in the current frame. The processing is speeded up by efficiently implemented approximate nearest neighbour fields under the Euclidean distance criterion, which permits the use of compact Gauss-Newton updates in the optimization. The registration is formulated as a maximum a posterior problem to dea…
Tsinghua University（清华大学）；Google（谷歌）；Chinese Academy of Sciences（中国科学院）
Human volumetric capture is a long-standing topic in computer vision and computer graphics. Although high-quality results can be achieved using sophisticated off-line systems, real-time human volumetric capture of complex scenarios, especially using light-weight setups, remains challenging. In this paper, we propose a human volumetric capture method that combines temporal volumetric fusion and deep implicit functions. To achieve high-quality and temporal-continuous reconstruction, we propose dynamic sliding fusion to fuse neighboring depth observations together with topology consistency. Moreo…
In past few years we have observed an increase in the usage of RGBD sensors in mobile devices. These sensors provide a good estimate of the depth map for the camera frame, which can be used in numerous augmented reality applications. This paper presents a new visual inertial odometry (VIO) system, which uses measurements from a RGBD sensor and an inertial measurement unit (IMU) sensor for estimating the motion state of the mobile device. The resulting system is called the depth-aided VIO (DVIO) system. In this system we add the depth measurement as part of the nonlinear optimization process. S…
Université Laval（拉瓦尔大学）；University of St Andrews（圣安德鲁斯大学）
Determining the direction in which a person is looking is an important problem in a wide range of HCI applications. In this paper we describe a highly accurate algorithm that performs gaze estimation using an affordable and widely available device such as Kinect. The method we propose starts by performing accurate head pose estimation achieved by fitting a person specific morphable model of the face to depth data. The ordinarily competing requirements of high accuracy and high speed are met concurrently by formulating the fitting objective function as a combination of terms which excel either …
University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）；Air Force Research Laboratory（空军研究实验室）
This article describes a technique to augment a typical RGBD sensor by integrating depth estimates obtained via Structure-from-Motion (SfM) with sensor depth measurements. Limitations in the RGBD depth sensing technology prevent capturing depth measurements in four important contexts: (1) distant surfaces (>5m), (2) dark surfaces, (3) brightly lit indoor scenes and (4) sunlit outdoor scenes. SfM technology computes depth via multi-view reconstruction from the RGB image sequence alone. As such, SfM depth estimates do not suffer the same limitations and may be computed in all four of the previou…
Driver inattention assessment has become a very active field in intelligent transportation systems. Based on active sensor Kinect and computer vision tools, we have built an efficient module for detecting driver distraction and recognizing the type of distraction. Based on color and depth map data from the Kinect, our system is composed of four sub-modules. We call them eye behavior (detecting gaze and blinking), arm position (is the right arm up, down, right of forward), head orientation, and facial expressions. Each module produces relevant information for assessing driver inattention. They …
This paper presents a new approach to accurately track a moving vehicle with a multiview setup of red-green-blue depth (RGBD) cameras. We first propose a correction method to eliminate a shift, which occurs in depth sensors when they become worn. This issue could not be otherwise corrected with the ordinary calibration procedure. Next, we present a sensor-wise filtering system to correct for an unknown vehicle motion. A data fusion algorithm is then used to optimally merge the sensor-wise estimated trajectories. We implement most parts of our solution in the graphic processor. Hence, the whole…
SenseTime Research（商汤科技研究院）；SenseBrain；Shanghai AI Laboratory（上海人工智能实验室）
Developing and integrating advanced image sensors with novel algorithms in camera systems is prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lack of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). To bridge the gap, we introduce the first MIPI challenge including five tracks focusing on novel image sensors and imaging algorithms. In this paper, RGB+ToF Depth Completion, one of the five …
Instituto Maimónides de Investigación en Biomedicina (IMIBIC)（迈蒙尼德生物医学研究所）；Córdoba University（科尔多瓦大学）；Health Time；Clínica las Nieves（拉斯涅韦斯诊所）
BACKGROUND AND OBJECTIVE: Patient positioning is a crucial step in radiation therapy, for which non-invasive methods have been developed based on surface reconstruction using optical 3D imaging. However, most solutions need expensive specialized hardware and a careful calibration procedure that must be repeated over time.This paper proposes a fast and cheap patient positioning method based on inexpensive consumer level RGB-D sensors. METHODS: The proposed method relies on a 3D reconstruction approach that fuses, in real-time, artificial and natural visual landmarks recorded from a hand-held RG…
Univ Lyon, INSA-Lyon, CNRS, LIRIS（里昂大学，里昂国立应用科学学院，法国国家科学研究中心，里昂信息科学与技术实验室）；Laboratoire d’Informatique de l’Université de Tours (EA 6300), INSA Centre Val de Loire（图尔大学信息学实验室，卢瓦尔河谷国立应用科学学院）
We address human action recognition from multi-modal video data involving articulated pose and RGB frames and propose a two-stream approach. The pose stream is processed with a convolutional model taking as input a 3D tensor holding data from a sub-sequence. A specific joint ordering, which respects the topology of the human body, ensures that different convolutional layers correspond to meaningful levels of abstraction. The raw RGB stream is handled by a spatio-temporal soft-attention mechanism conditioned on features from the pose network. An LSTM network receives input from a set of image l…
High-accuracy per-pixel depth is vital for computational photography, so smartphones now have multimodal camera systems with time-of-flight (ToF) depth sensors and multiple color cameras. However, producing accurate high-resolution depth is still challenging due to the low resolution and limited active illumination power of ToF sensors. Fusing RGB stereo and ToF information is a promising direction to overcome these issues, but a key problem remains: to provide high-quality 2D RGB images, the main color sensor's lens is optically stabilized, resulting in an unknown pose for the floating lens t…
University of Bonn（波恩大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Although commercial and open-source software exist to reconstruct a static object from a sequence recorded with an RGB-D sensor, there is a lack of tools that build rigged models of articulated objects that deform realistically and can be used for tracking or animation. In this work, we fill this gap and propose a method that creates a fully rigged model of an articulated object from depth data of a single sensor. To this end, we combine deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow. The fully rigged model then consi…
SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）
Recently, it is increasingly popular to equip mobile RGB cameras with Time-of-Flight (ToF) sensors for active depth sensing. However, for off-the-shelf ToF sensors, one must tackle two problems in order to obtain high-quality depth with respect to the RGB camera, namely 1) online calibration and alignment; and 2) complicated error correction for ToF depth sensing. In this work, we propose a framework for jointly alignment and refinement via deep learning. First, a cross-modal optical flow between the RGB image and the ToF amplitude image is estimated for alignment. The aligned depth is then re…
Max-Planck-Institute for Informatics（马克斯·普朗克信息学研究所）；Universidad Rey Juan Carlos（胡安卡洛斯国王大学）
We present an approach for real-time, robust and accurate hand pose estimation from moving egocentric RGB-D cameras in cluttered real environments. Existing methods typically fail for hand-object interactions in cluttered scenes imaged from egocentric viewpoints, common for virtual or augmented reality applications. Our approach uses two subsequently applied Convolutional Neural Networks (CNNs) to localize the hand and regress 3D joint locations. Hand localization is achieved by using a CNN to estimate the 2D position of the hand center in the input, even in the presence of clutter and occlusi…
Institute for Computer Science and Control (SZTAKI), Eötvös Loránd Research Network (ELKH)（厄特沃什·洛兰研究网络（ELKH）计算机科学与控制研究所（SZTAKI））；Budapest University of Technology and Economics（布达佩斯技术与经济大学）
The frame rates of most 3D LIDAR sensors used in intelligent vehicles are substantially lower than current cameras installed in the same vehicle. This research suggests using a mono camera to virtually enhance the frame rate of LIDARs, allowing the more frequent monitoring of dynamic objects in the surroundings that move quickly. As a first step, dynamic object candidates are identified and tracked in the camera frames. Following that, the LIDAR measurement points of these items are found by clustering in the frustums of 2D bounding boxes. Projecting these to the camera and tracking them to th…
De Montfort University（德蒙福特大学）；University of Lincoln（林肯大学）
In this paper, we propose mushrooms detection, localization and 3D pose estimation algorithm using RGB-D data acquired from a low-cost consumer RGB-D sensor. We use the RGB and depth information for different purposes. From RGB color, we first extract initial contour locations of the mushrooms and then provide both the initial contour locations and the original image to active contour for mushrooms segmentation. These segmented mushrooms are then used as input to a circular Hough transform for each mushroom detection including its center and radius. Once each mushroom's center position in the …
Dynamic objects have a significant impact on the robot's perception of the environment which degrades the performance of essential tasks such as localization and mapping. In this work, we address this problem by synthesizing plausible color, texture and geometry in regions occluded by dynamic objects. We propose the novel geometry-aware DynaFill architecture that follows a coarse-to-fine topology and incorporates our gated recurrent feedback mechanism to adaptively fuse information from previous timesteps. We optimize our architecture using adversarial training to synthesize fine realistic tex…
Depth sensing is crucial for 3D reconstruction and scene understanding. Active depth sensors provide dense metric measurements, but often suffer from limitations such as restricted operating ranges, low spatial resolution, sensor interference, and high power consumption. In this paper, we propose a deep learning (DL) method to estimate per-pixel depth and its uncertainty continuously from a monocular video stream, with the goal of effectively turning an RGB camera into an RGB-D camera. Unlike prior DL-based methods, we estimate a depth probability distribution for each pixel rather than a sing…
