RGB-D Video Sequences Research Articles

Deep learning-based approaches for human motion decoding in smart walkers for rehabilitation

Gait disabilities are among the most frequent impairments worldwide. Their treatment increasingly relies on rehabilitation therapies, in which smart walkers are being introduced to empower the user’s recovery state and autonomy, while reducing the clinicians effort. For that, these should be able to decode human motion and needs, as early as possible. Current walkers decode motion intention using information gathered from wearable or embedded sensors, namely inertial units, force sensors, hall sensors, and lasers, whose main limitations imply an expensive solution or hinder the perception of human movement. Smart walkers commonly lack an advanced and seamless human–robot interaction, which intuitively and promptly understands human motions. A contactless approach is proposed in this work, addressing human motion decoding as an early action recognition/detection problematic, using RGB-D cameras. We studied different deep learning-based algorithms, organised in three different approaches, to process lower body RGB-D video sequences, recorded from an embedded camera of a smart walker, and classify them into 4 classes (stop, walk, turn right/left). A custom dataset involving 15 healthy participants walking with the walker device was acquired and prepared, resulting in 28800 balanced RGB-D frames, to train and evaluate the deep learning networks. The best results were attained by a convolutional neural network with a channel-wise attention mechanism, reaching accuracy values of 99.61% and above 93%, for offline early detection/recognition and trial simulations, respectively. Following the hypothesis that human lower body features encode prominent information, fostering a more robust prediction towards real-time applications, the algorithm focus was also quantitatively evaluated using Dice metric, leading to values slightly higher than 30%. Promising results were attained for early action detection as a human motion decoding strategy, with enhancements in the focus of the proposed architectures.

Detailed Surface Geometry and Albedo Recovery from RGB-D Video under Natural Illumination.

This article presents a novel approach for depth map enhancement from an RGB-D video sequence. The basic idea is to exploit the photometric information in the color sequence to resolve the inherent ambiguity of shape from shading problem. Instead of making any assumption about surface albedo or controlled object motion and lighting, we use the lighting variations introduced by casual object movement. We are effectively calculating photometric stereo from a moving object under natural illuminations. One of the key technical challenges is to establish correspondences over the entire image set. We, therefore, develop a lighting insensitive robust pixel matching technique that out-performs optical flow method in presence of lighting variations. An adaptive reference frame selection procedure is introduced to get more robust to imperfect lambertian reflections. In addition, we present an expectation-maximization framework to recover the surface normal and albedo simultaneously, without any regularization term. We have validated our method on both synthetic and real datasets to show its superior performance on both surface details recovery and intrinsic decomposition.

Continuous perception for deformable objects understanding

We present a robot vision approach to deformable object classification, with direct application to autonomous service robots. Our approach is based on the assumption that continuous perception provides robots with greater visual competence for deformable objects interpretation and classification. Our approach classifies the category of clothing items by continuously perceiving the dynamic interactions of the garment’s material and shape as it is being picked up. For this, we extract continuously visual features of a RGB-D video sequence and we fuse features by means of the Locality Constrained Group Sparse Representation (LGSR) algorithm. To evaluate the performance of our approach, we created a fully annotated database featuring 150 garment videos in random configurations. Experiments demonstrate that by continuously observing an object deform, our approach achieves a classification score of 66.7%, outperforming state-of-the-art approaches by a ∼27.3% increase.

Social Activity Recognition on Continuous RGB-D Video Sequences

Modern service robots are provided with one or more sensors, often including RGB-D cameras, to perceive objects and humans in the environment. This paper proposes a new system for the recognition of human social activities from a continuous stream of RGB-D data. Many of the works until now have succeeded in recognising activities from clipped videos in datasets, but for robotic applications it is important to be able to move to more realistic scenarios in which such activities are not manually selected. For this reason, it is useful to detect the time intervals when humans are performing social activities, the recognition of which can contribute to trigger human-robot interactions or to detect situations of potential danger. The main contributions of this research work include a novel system for the recognition of social activities from continuous RGB-D data, combining temporal segmentation and classification, as well as a model for learning the proximity-based priors of the social activities. A new public dataset with RGB-D videos of social and individual activities is also provided and used for evaluating the proposed solutions. The results show the good performance of the system in recognising social activities from continuous RGB-D data.

The RBO dataset of articulated objects and interactions

We present a dataset with models of 14 articulated objects commonly found in human environments and with RGB-D video sequences and wrenches recorded of human interactions with them. The 358 interaction sequences total 67 minutes of human manipulation under varying experimental conditions (type of interaction, lighting, perspective, and background). Each interaction with an object is annotated with the ground-truth poses of its rigid parts and the kinematic state obtained by a motion-capture system. For a subset of 78 sequences (25 minutes), we also measured the interaction wrenches. The object models contain textured three-dimensional triangle meshes of each link and their motion constraints. We provide Python scripts to download and visualize the data. The data are available at https://turbo.github.io/articulated-objects/ and hosted at https://zenodo.org/record/1036660/.

Depth Super-Resolution on RGB-D Video Sequences with Large Displacement 3D Motion.

To enhance the resolution and accuracy of depth data, some video-based depth super-resolution methods have been proposed which utilizes its neighboring depth images in the temporal domain. They often consist of two main stages: motion compensation of temporally neighboring depth images and fusion of compensated depth images. However, large displacement 3D motion often leads to compensation error, and the compensation error is further introduced into the fusion. A video-based depth super-resolution method with novel motion compensation and fusion approaches is proposed in this paper. We claim that, 3D Nearest Neighboring Field (NNF) is a better choice than using positions with true motion displacement for depth enhancements. To handle large displacement 3D motion, the compensation stage utilized 3D NNF instead of true motion used in previous methods. Next, the fusion approach is modeled as a regression problem to predict the super-resolution result efficiently for each depth image by using its compensated depth images. A new deep convolutional neural network architecture is designed for fusion, which is able to employ a large amount of video data for learning the complicated regression function. We comprehensively evaluate our method on various RGB-D video sequences to show its superior performance.

Real-time human segmentation from RGB-D video sequence based on adaptive geodesic distance computation

In this paper, we propose a method for extracting humans in the foreground of video frames using color and depth information. To ensure real-time performance and to increase accuracy, we classify a video frame into two parts by degree of noise: head region with high noise level, and non-head region with low noise level. Then, we apply a high-computational geodesic matting algorithm to the noisy head region that includes hair, and a low-computational hole filling with smoothing method to other regions. Additionally, we modify the traditional color-based geodesic segmentation algorithm to consider additional depth information. Then, we apply temporal/spatial smoothing to the blended foreground mask in order to enhance the coherence between video frames. Experimental results show that the proposed method outperforms a previous approach by accuracy and performance.

Locating 3D Object Proposals: A Depth-Based Online Approach

2D object proposals, quickly detected regions in an image that likely contain an object of interest, are an effective approach for improving the computational efficiency and accuracy of object detection in color images. In this work, we propose a novel online method that generates 3D object proposals in a RGB-D video sequence. Our main observation is that depth images provide important information about the geometry of the scene. Diverging from the traditional goal of 2D object proposals to provide a high recall (lots of 2D bounding boxes near potential objects), we aim for precise 3D proposals. We leverage on depth information per frame and multi-view scene information to obtain accurate 3D object proposals. Using efficient but robust registration enables us to combine multiple frames of a scene in near real time and generate 3D bounding boxes for potential 3D regions of interest. Using standard metrics, such as Precision-Recall curves and F-measure, we show that the proposed approach is significantly more accurate than the current state-of-the-art techniques. Our online approach can be integrated into SLAM based video processing for quick 3D object localization. Our method takes less than a second in MATLAB on the UW-RGBD scene dataset on a single thread CPU and thus, has potential to be used in low-power chips in Unmanned Aerial Vehicles (UAVs), quadcopters, and drones.

Point Light Source Position Estimation From RGB-D Images by Learning Surface Attributes.

Light source position (LSP) estimation is a difficult yet an important problem in computer vision. A common approach for estimating the LSP assumes Lambert's law. However, in real-world scenes, Lambert's law does not hold for all different types of surfaces. Instead of assuming all that surfaces follow Lambert's law, our approach classifies image surface segments based on their photometric and geometric surface attributes (i.e. glossy, matte, curved, and so on) and assigns weights to image surface segments based on their suitability for LSP estimation. In addition, we propose the use of the estimated camera pose to globally constrain LSP for RGB-D video sequences. Experiments on Boom and a newly collected RGB-D video data sets show that the state-of-the-art methods are outperformed by the proposed method. The results demonstrate that weighting image surface segments based on their attributes outperform the state-of-the-art methods in which the image surface segments are considered to equally contribute. In particular, by using the proposed surface weighting, the angular error for LSP estimation is reduced from 12.6° to 8.2° and 24.6° to 4.8° for Boom and RGB-D video data sets, respectively. Moreover, using the camera pose to globally constrain LSP provides higher accuracy (4.8°) compared with using single frames (8.5°).

Dense RGB-D Map-Based Human Tracking and Activity Recognition using Skin Joints Features and Self-Organizing Map

This paper addresses the issues of 3D human activity detection, tracking and recognition from RGB-D video sequences using a feature structured framework. During human tracking and activity recognition, initially, dense depth images are captured using depth camera. In order to track human silhouettes, we considered spatial/temporal continuity, constraints of human motion information and compute centroids of each activity based on chain coding mechanism and centroids point extraction. In body skin joints features, we estimate human body skin color to identify human body parts (i.e., head, hands, and feet) likely to extract joint points information. These joints points are further processed as feature extraction process including distance position features and centroid distance features. Lastly, self-organized maps are used to recognize different activities. Experimental results demonstrate that the proposed method is reliable and efficient in recognizing human poses at different realistic scenes. The proposed system should be applicable to different consumer application systems such as healthcare system, video surveillance system and indoor monitoring systems which track and recognize different activities of multiple users.