Low-cost Depth Camera Research Articles

Shape descriptors to characterize the shoot of entire plant from multiple side views of a motorized depth sensor

A low-cost depth camera recently introduced is synchronized with a specially devised low-cost motorized turntable. This results in a low-cost motorized depth sensor, able to provide a large number of registered side views, which is exploited here for the quantitative characterization of the shoots of entire plants. A set of four new shape descriptors of the shoots, constructed from the depth images on multiple side views of the shoots of plants, is proposed. The four descriptors quantify effective volume, multiscale organization, spatial symmetries and lacunarity of the plants. The four descriptors are here defined, validated on synthetic scenes with known properties, and then applied on nine different-looking real plants to illustrate their abilities for quantitative characterization and comparison. The resulting motorized depth sensor and associated image processing open new perspectives to various plant science applications including plant growth and architecture monitoring, plant response to stresses or the assessment of aesthetic parameters for ornamental plants.

Full-Body Pose Tracking-The Top View Reprojection Approach.

Recent introduction of low-cost depth cameras triggered a number of interesting works, pushing forward the state-of-the-art in human body pose extraction and tracking. However, despite the remarkable progress, many of the contemporary methods cope inadequately with complex scenarios, involving multiple interacting users, under the presence of severe inter- and intra-occlusions. In this work, we present a model-based approach for markerless articulated full body pose extraction and tracking in RGB-D sequences. A cylinder-based model is employed to represent the human body. For each body part a set of hypotheses is generated and tracked over time by a Particle Filter. To evaluate each hypothesis, we employ a novel metric that considers the reprojected Top View of the corresponding body part. The latter, in conjunction with depth information, effectively copes with difficult and ambiguous cases, such as severe occlusions. For evaluation purposes, we conducted several series of experiments using data from a public human action database, as well as own-collected data involving varying number of interacting users. The performance of the proposed method has been further compared against that of the Microsoft's Kinect SDK and NiTE (TM) using ground truth information. The results obtained attest for the effectiveness of our approach.

Integral imaging display for natural scene based on KinectFusion

In this paper, we propose an integral imaging display system based on KinectFusion, using only a moving low-cost depth camera as the pickup device. The multi-frame depth data of the observed scene streamed from a Kinect sensor is fused into a single global surface model represented by the volumetric truncated signed distance function. Thus, the inherent noise associated with single frame depth data can be eliminated. The elemental image array for display is obtained by ray casting the volumetric truncated signed distance function. To match the pickup part and the display part, the relationship between the pickup voxel and the display voxel is deduced using the ray optics theory. Experimental results show the validity of the proposed method.

Assessment of a Microsoft Kinect-based 3D scanning system for taking body segment girth measurements: a comparison to ISAK and ISO standards

ABSTRACTUse of anthropometric data to infer sporting performance is increasing in popularity, particularly within elite sport programmes. Measurement typically follows standards set by the International Society for the Advancement of Kinanthropometry (ISAK). However, such techniques are time consuming, which reduces their practicality. Schranz et al. recently suggested 3D body scanners could replace current measurement techniques; however, current systems are costly. Recent interest in natural user interaction has led to a range of low-cost depth cameras capable of producing 3D body scans, from which anthropometrics can be calculated. A scanning system comprising 4 depth cameras was used to scan 4 cylinders, representative of the body segments. Girth measurements were calculated from the 3D scans and compared to gold standard measurements. Requirements of a Level 1 ISAK practitioner were met in all 4 cylinders, and ISO standards for scan-derived girth measurements were met in the 2 larger cylinders only. A fixed measurement bias was identified that could be corrected with a simple offset factor. Further work is required to determine comparable performance across a wider range of measurements performed upon living participants. Nevertheless, findings of the study suggest such a system offers many advantages over current techniques, having a range of potential applications.

Characterization of a multi-user indoor positioning system based on low cost depth vision (Kinect) for monitoring human activity in a smart home.

An increasing number of systems use indoor positioning for many scenarios such as asset tracking, health care, games, manufacturing, logistics, shopping, and security. Many technologies are available and the use of depth cameras is becoming more and more attractive as this kind of device becomes affordable and easy to handle. This paper contributes to the effort of creating an indoor positioning system based on low cost depth cameras (Kinect). A method is proposed to optimize the calibration of the depth cameras, to describe the multi-camera data fusion and to specify a global positioning projection to maintain the compatibility with outdoor positioning systems. The monitoring of the people trajectories at home is intended for the early detection of a shift in daily activities which highlights disabilities and loss of autonomy. This system is meant to improve homecare health management at home for a better end of life at a sustainable cost for the community.

A framework for gait-based recognition using Kinect

Gait analysis has gained new impetus over the past few years. This is mostly due to the launch of low cost depth cameras accompanied with real time pose estimation algorithms. In this work we focus on the problem of human gait recognition. In particular, we propose a modification of a framework originally designed for the task of action recognition and apply it to gait recognition. The new scheme allows us to achieve complex representations of gait sequences and thus express efficiently the dynamic characteristics of human walking sequences. The representational power of the suggested model is evaluated on a publicly available dataset where we achieved up to 93.29% identification rate, 3.1% EER on the verification task and 99.11% gender recognition rate.

Depth-based human fall detection via shape features and improved extreme learning machine.

Falls are one of the major causes leading to injury of elderly people. Using wearable devices for fall detection has a high cost and may cause inconvenience to the daily lives of the elderly. In this paper, we present an automated fall detection approach that requires only a low-cost depth camera. Our approach combines two computer vision techniques-shape-based fall characterization and a learning-based classifier to distinguish falls from other daily actions. Given a fall video clip, we extract curvature scale space (CSS) features of human silhouettes at each frame and represent the action by a bag of CSS words (BoCSS). Then, we utilize the extreme learning machine (ELM) classifier to identify the BoCSS representation of a fall from those of other actions. In order to eliminate the sensitivity of ELM to its hyperparameters, we present a variable-length particle swarm optimization algorithm to optimize the number of hidden neurons, corresponding input weights, and biases of ELM. Using a low-cost Kinect depth camera, we build an action dataset that consists of six types of actions (falling, bending, sitting, squatting, walking, and lying) from ten subjects. Experimenting with the dataset shows that our approach can achieve up to 91.15% sensitivity, 77.14% specificity, and 86.83% accuracy. On a public dataset, our approach performs comparably to state-of-the-art fall detection methods that need multiple cameras.

3D real human reconstruction via multiple low-cost depth cameras

In traditional human-centered games and virtual reality applications, a skeleton is commonly tracked using consumer-level cameras or professional motion capture devices to animate an avatar. In this paper, we propose a novel application that automatically reconstructs a real 3D moving human captured by multiple RGB-D cameras in the form of a polygonal mesh, and which may help users to actually enter a virtual world or even a collaborative immersive environment. Compared with 3D point clouds, a 3D polygonal mesh is commonly adopted to represent objects or characters in games and virtual reality applications. A vivid 3D human mesh can hugely promote the feeling of immersion when interacting with a computer. The proposed method includes three key steps for realizing dynamic 3D human reconstruction from RGB images and noisy depth data captured from a distance. First, we remove the static background to obtain a 3D partial view of the human from the depth data with the help of calibration parameters, and register two neighboring partial views. The whole 3D human is globally registered using all the partial views to obtain a relatively clean 3D human point cloud. A complete 3D mesh model is constructed from the point cloud using Delaunay triangulation and Poisson surface reconstruction. Finally, a series of experiments demonstrates the reconstruction quality of the 3D human meshes. Dynamic meshes with different poses are placed in a virtual environment, which can be used to provide personalized avatars for everyday users, and enhance the interactive experience in games and virtual reality environments.

Child body shape measurement using depth cameras and a statistical body shape model

We present a new method for rapidly measuring child body shapes from noisy, incomplete data captured from low-cost depth cameras. This method fits the data using a statistical body shape model (SBSM) to find a complete avatar in the realistic body shape space. The method also predicts a set of standard anthropometric data for a specific subject without measuring dimensions directly from the fitted model. Since the SBSM was developed using principal component (PC) analysis, we formulate an optimisation problem to fit the model in which the degrees of freedom are defined in PC-score space. The mean unsigned distance between the fitted-model based on depth-camera data and the high-resolution laser scan data was 9.4 mm with a standard deviation (SD) of 5.1 mm. For the torso, the mean distance was 2.9 mm (SD 1.4 mm). The correlations between standard anthropometric dimensions predicted by the SBSM and manually measured dimensions exceeded 0.9.

Depth-Color Fusion Strategy for 3-D Scene Modeling With Kinect

Low-cost depth cameras, such as Microsoft Kinect, have completely changed the world of human-computer interaction through controller-free gaming applications. Depth data provided by the Kinect sensor presents several noise-related problems that have to be tackled to improve the accuracy of the depth data, thus obtaining more reliable game control platforms and broadening its applicability. In this paper, we present a depth-color fusion strategy for 3-D modeling of indoor scenes with Kinect. Accurate depth and color models of the background elements are iteratively built, and used to detect moving objects in the scene. Kinect depth data is processed with an innovative adaptive joint-bilateral filter that efficiently combines depth and color by analyzing an edge-uncertainty map and the detected foreground regions. Results show that the proposed approach efficiently tackles main Kinect data problems: distance-dependent depth maps, spatial noise, and temporal random fluctuations are dramatically reduced; objects depth boundaries are refined, and nonmeasured depth pixels are interpolated. Moreover, a robust depth and color background model and accurate moving objects silhouette are generated.