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 occlusions. The localized hand position, together with the corresponding input depth value, is used to generate a normalized cropped image that is fed into a second CNN to regress relative 3D hand joint locations in real time. For added accuracy, robustness and temporal stability, we refine the pose estimates using a kinematic pose tracking energy. To train the CNNs, we introduce a new photorealistic dataset that uses a merged reality approach to capture and synthesize large amounts of annotated data of natural hand interaction in cluttered scenes. Through quantitative and qualitative evaluation, we show that our method is robust to self-occlusion and occlusions by objects, particularly in moving egocentric perspectives.
Brigham Young University（杨百翰大学）；Adobe Research（Adobe 研究院）
Hand segmentation and detection in truly unconstrained RGB-based settings is important for many applications. However, existing datasets are far from sufficient in terms of size and variety due to the infeasibility of manual annotation of large amounts of segmentation and detection data. As a result, current methods are limited by many underlying assumptions such as constrained environment, consistent skin color and lighting. In this work, we present Ego2Hands, a large-scale RGB-based egocentric hand segmentation/detection dataset that is semi-automatically annotated and a color-invariant comp…
Egocentric segmentation has attracted recent interest in the computer vision community due to their potential in Mixed Reality (MR) applications. While most previous works have been focused on segmenting egocentric human body parts (mainly hands), little attention has been given to egocentric objects. Due to the lack of datasets of pixel-wise annotations of egocentric objects, in this paper we contribute with a semantic-wise labeling of a subset of 2124 images from the RGB-D THU-READ Dataset. We also report benchmarking results using Thundernet, a real-time semantic segmentation network, that …
Hong Kong University of Science and Technology（香港科技大学）；Massachusetts Institute of Technology（麻省理工学院）
Although there has been significant progress in the past decade,tracking is still a very challenging computer vision task, due to problems such as occlusion and model drift.Recently, the increased popularity of depth sensors e.g. Microsoft Kinect has made it easy to obtain depth data at low cost.This may be a game changer for tracking, since depth information can be used to prevent model drift and handle occlusion.In this paper, we construct a benchmark dataset of 100 RGBD videos with high diversity, including deformable objects, various occlusion conditions and moving cameras. We propose a ve…
We introduce a new pipeline for hand localization and fingertip detection. For RGB images captured from an egocentric vision mobile camera, hand and fingertip detection remains a challenging problem due to factors like background complexity and hand shape variety. To address these issues accurately and robustly, we build a large scale dataset named Ego-Fingertip and propose a bi-level cascaded pipeline of convolutional neural networks, namely, Attention-based Hand Detector as well as Multi-point Fingertip Detector. The proposed method significantly tackles challenges and achieves satisfactoril…
Human gait is one of important biometric characteristics for human identification at a distance. In practice, occlusion usually occurs and seriously affects accuracy of gait recognition. However, there is no available database to support in-depth research of this problem, and state-of-arts gait recognition methods have not paid enough attention to it, thus this paper focuses on gait recognition under occlusion. We collect a new gait recognition database called OG RGB+D database, which breaks through the limitation of other gait databases and includes multimodal gait data of various occlusions …
New York University（纽约大学）；Tongji University（同济大学）；Tsinghua University（清华大学）
We are interested in anticipating as early as possible the target location of a person's object manipulation action in a 3D workspace from egocentric vision. It is important in fields like human-robot collaboration, but has not yet received enough attention from vision and learning communities. To stimulate more research on this challenging egocentric vision task, we propose a large multimodality dataset of more than 1 million frames of RGB-D and IMU streams, and provide evaluation metrics based on our high-quality 2D and 3D labels from semi-automatic annotation. Meanwhile, we design baseline …
We present JRDB, a novel egocentric dataset collected from our social mobile manipulator JackRabbot. The dataset includes 64 minutes of annotated multimodal sensor data including stereo cylindrical 360$^\circ$ RGB video at 15 fps, 3D point clouds from two Velodyne 16 Lidars, line 3D point clouds from two Sick Lidars, audio signal, RGB-D video at 30 fps, 360$^\circ$ spherical image from a fisheye camera and encoder values from the robot's wheels. Our dataset incorporates data from traditionally underrepresented scenes such as indoor environments and pedestrian areas, all from the ego-perspectiv…
We present a solution to egocentric 3D body pose estimation from monocular images captured from downward looking fish-eye cameras installed on the rim of a head mounted VR device. This unusual viewpoint leads to images with unique visual appearance, with severe self-occlusions and perspective distortions that result in drastic differences in resolution between lower and upper body. We propose an encoder-decoder architecture with a novel multi-branch decoder designed to account for the varying uncertainty in 2D predictions. The quantitative evaluation, on synthetic and real-world datasets, show…
ETH Zürich（苏黎世联邦理工学院）；Microsoft（微软）；Meta Reality Labs Research（Meta现实实验室）
Understanding social interactions from egocentric views is crucial for many applications, ranging from assistive robotics to AR/VR. Key to reasoning about interactions is to understand the body pose and motion of the interaction partner from the egocentric view. However, research in this area is severely hindered by the lack of datasets. Existing datasets are limited in terms of either size, capture/annotation modalities, ground-truth quality, or interaction diversity. We fill this gap by proposing EgoBody, a novel large-scale dataset for human pose, shape and motion estimation from egocentric…
Face versus Body Tracking for Human-Robot Interaction: An Egocentric Dataset
Furhat Robotics；University of Naples Federico II（那不勒斯费德里科二世大学）；Division of Speech, Music and Hearing, KTH Royal Institute of Technology（语音、音乐和听觉研究所，皇家理工学院）
University of Minnesota（明尼苏达大学）；Carnegie Mellon University（卡内基梅隆大学）
In this paper, we study a problem of egocentric scene understanding, i.e., predicting depths and surface normals from an egocentric image. Egocentric scene understanding poses unprecedented challenges: (1) due to large head movements, the images are taken from non-canonical viewpoints (i.e., tilted images) where existing models of geometry prediction do not apply; (2) dynamic foreground objects including hands constitute a large proportion of visual scenes. These challenges limit the performance of the existing models learned from large indoor datasets, such as ScanNet and NYUv2, which compris…
DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；Zhengzhou University（郑州大学）；University of Wollongong（伍伦贡大学）
In this paper, we propose a \textbf{Tr}ansformer-based RGB-D \textbf{e}gocentric \textbf{a}ction \textbf{r}ecognition framework, called Trear. It consists of two modules, inter-frame attention encoder and mutual-attentional fusion block. Instead of using optical flow or recurrent units, we adopt self-attention mechanism to model the temporal structure of the data from different modalities. Input frames are cropped randomly to mitigate the effect of the data redundancy. Features from each modality are interacted through the proposed fusion block and combined through a simple yet effective fusio…
Aragon Institute of Engineering Research (i3A), Universidad de Zaragoza（阿拉贡工程研究所（i3A），萨拉戈萨大学）；University of California, Irvine（加州大学欧文分校）
We focus on the task of everyday hand pose estimation from egocentric viewpoints. For this task, we show that depth sensors are particularly informative for extracting near-field interactions of the camera wearer with his/her environment. Despite the recent advances in full-body pose estimation using Kinect-like sensors, reliable monocular hand pose estimation in RGB-D images is still an unsolved problem. The problem is considerably exacerbated when analyzing hands performing daily activities from a first-person viewpoint, due to severe occlusions arising from object manipulations and a limite…
EgoTraj: Real-World Egocentric Human Trajectory Dataset for Multimodal Prediction
Department of Civil, Architectural, and Environmental Engineering, The University of Texas at Austin（土木、建筑与环境工程系，德克萨斯大学奥斯汀分校）；Meta Reality Labs（Meta现实实验室）；School of Architecture, The University of Texas at Austin（建筑学院，德克萨斯大学奥斯汀分校）
The University of Hong Kong（香港大学）；Microsoft Research Asia（微软亚洲研究院）；TransGP；Texas A&M University（德克萨斯农工大学）
Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit temporal information for robust estimation. Noticing the different temporal granularity of and the semantic correlation between hand pose estimation and action recognition, we build a network hierarchy with two cascaded transformer encoders, where the first one exploits the short-term temporal cue for hand pose estimation, and the latter aggregates per-frame po…
Cross-Modal Action Recognition in Egocentric Video Using Mamba: Integrating RGB and Hand Skeleton Streams via CLS Token Fusion Strategies
Univ. of Buenos Aires. Faculty of Exact and Natural Sciences. Dept. of Computer Science (DC)（布宜诺斯艾利斯大学。精确与自然科学学院。计算机科学系）；CONICET-Univ. of Buenos Aires. Institute of Computer Sciences (ICC)（布宜诺斯艾利斯大学CONICET联合体。计算机科学研究所）
We present a unified framework for understanding 3D hand and object interactions in raw image sequences from egocentric RGB cameras. Given a single RGB image, our model jointly estimates the 3D hand and object poses, models their interactions, and recognizes the object and action classes with a single feed-forward pass through a neural network. We propose a single architecture that does not rely on external detection algorithms but rather is trained end-to-end on single images. We further merge and propagate information in the temporal domain to infer interactions between hand and object traje…
Politecnico di Torino（都灵理工大学）；CINI Consortium（CINI联盟）；Politecnico di Milano（米兰理工大学）
Event cameras are novel bio-inspired sensors, which asynchronously capture pixel-level intensity changes in the form of "events". Due to their sensing mechanism, event cameras have little to no motion blur, a very high temporal resolution and require significantly less power and memory than traditional frame-based cameras. These characteristics make them a perfect fit to several real-world applications such as egocentric action recognition on wearable devices, where fast camera motion and limited power challenge traditional vision sensors. However, the ever-growing field of event-based vision …
Iowa State University（爱荷华州立大学）；United Technologies Research Center（联合技术研究中心）；Google Inc.（谷歌公司）
Occlusion edges in images which correspond to range discontinuity in the scene from the point of view of the observer are an important prerequisite for many vision and mobile robot tasks. Although they can be extracted from range data however extracting them from images and videos would be extremely beneficial. We trained a deep convolutional neural network (CNN) to identify occlusion edges in images and videos with both RGB-D and RGB inputs. The use of CNN avoids hand-crafting of features for automatically isolating occlusion edges and distinguishing them from appearance edges. Other than qua…
While much progress has been made in 6-DoF object pose estimation from a single RGB image, the current leading approaches heavily rely on real-annotation data. As such, they remain sensitive to severe occlusions, because covering all possible occlusions with annotated data is intractable. In this paper, we introduce an approach to robustly and accurately estimate the 6-DoF pose in challenging conditions and without using any real pose annotations. To this end, we leverage the intuition that the poses predicted by a network from an image and from its counterpart synthetically altered to mimic o…
