Action recognition using time of flight cameras

Oprisescu, Serban; Burlacu, Constantin; Buzuloiu, Vasile

doi:10.1109/iccomm.2010.5509074

Cited by 8 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the aim to increase user comfort and acceptance rate, marker-less and non-wearable solutions for posture recognition have become an active research field by exploiting essentially computer vision systems. Recently, Time-Of-Flight (TOF) sensors have increasingly investigated [2] as active vision solutions able to overcome typical drawbacks affecting the more traditional passive vision ones such as dependence from ambient conditions, computational expensiveness and privacy issues. The usage of cheaper (non-TOF) 3D sensors have been recently reported especially for fall detection applications [3].…”

Section: Introductionmentioning

confidence: 99%

A multi-feature scheme for posture recognition with 3D TOF sensor

2012

View full text Add to dashboard Cite

Fig. 1: System overview: a) TOF sensor; b) embedded PC; c) Wallmounted TOF device with sensor OS and world OW reference systems.Abstract-This paper presents a multi-feature approach for detection of key postures by using a MESA SR4000 time-offlight 3D sensor managed by a low-power embedded PC. Acquired data were pre-processed by using a well-established framework including self-calibration, segmentation and tracking functionalities. To accommodate different application scenarios, hierarchical coarse-to-fine features were extracted by exploiting two different descriptors: topological and volumetric. The topological descriptor encoded intrinsic topology of body postures in a skeleton-like representation based on geodesic distance. Instead, the volumetric descriptor used a cylindrical voxelization to describe postures in a histogram-based representation. Both synthetic and real datasets were used to evaluate performance. The complementary discrimination capabilities exhibited by the two descriptors allowed to achieve good results in four different application scenarios with a classification rate greater than 96.4%.

show abstract

Section: Introductionmentioning

confidence: 99%

A multi-feature scheme for posture recognition with 3D TOF sensor

2012

View full text Add to dashboard Cite

show abstract

“…Image segmentation is an essential operation in many applications, such as action recognition and tracking [1], [2], immersive videoconference [3], and biomedical imaging, just to name a few. However, original depth images always have large amount of data, the processing step may consume a lot of time, so simplifying the structure of discrete three dimensional data points and extracting advanced image feature are the basis of the identification and location of the three-dimensional object.…”

Section: Introductionmentioning

confidence: 99%

Kinect Depth Data Segmentation Based on Gauss Mixture Model Clustering

Liu

2013

AMR

View full text Add to dashboard Cite

Indoor scene understanding based on the depth image data is a cutting-edge issue in the field of three-dimensional computer vision. Taking the layout characteristics of the indoor scenes and more plane features in these scenes into account, this paper presents a depth image segmentation method based on Gauss Mixture Model clustering. First, transform the Kinect depth image data into point cloud which is in the form of discrete three-dimensional point data, and denoise and down-sample the point cloud data; second, calculate the point normal of all points in the entire point cloud, then cluster the entire normal using Gaussian Mixture Model, and finally implement the entire point clouds segmentation by RANSAC algorithm. Experimental results show that the divided regions have obvious boundaries and segmentation quality is above normal, and lay a good foundation for object recognition.

show abstract

“…passive camera systems) such as shadows presence, perspective ambiguity (monocular), camouflage effects, brightness fluctuations, few surface cues (untextured regions) and occlusion handling. In order to overcome the previously discussed drawbacks of traditional passive vision systems (both monocular and multi-view), the adoption of 3D active vision, mainly by TOF (Time-Of-Flight) range camera, is increasingly investigated [13,14,15,16]. The 3D TOF camera allows to measure the distance from the camera device of each point in captured scene, providing a sequence of range images (see Fig.…”

Section: Introduction and Related Workmentioning

confidence: 99%

Geodesic-based human posture analysis by using a single 3D TOF camera

Diraco

Leone

Siciliano

2011

2011 IEEE International Symposium on Industrial Electronics

View full text Add to dashboard Cite

In this paper an algorithmic framework for posture analysis using a single view 3D TOF camera is presented. The 3D human posture parameters are recovered automatically from range data without the usage of body markers. A topological approach is investigated in order to define descriptors suitable to estimate location of body parts and orientation of body articulations. Two Morse function are exploited, the first one provides an Euclidean distance mapping helpful to deal with body self-occlusions. The second Morse function is based on geodesic distance and provides an extended Discrete Reeb Graph description of the main body parts that are head, torso, arms and legs. Geodesic distance function exhibits the property of invariance under isometric transformations that typically occur when the human body changes its posture. The geodesic map of the body is obtained with a two steps procedure. Firstly, a Delaunay meshing is carried out starting from the depth map provided by the 3D TOF camera; secondly, geodesic distances are computed applying Dijkstra algorithm to previously computed mesh. Moreover, a re-meshing method is proposed in order to deal with self-occlusion problem which occurs in the depth data when a human body is partially occluded by other body segments. Experimental results on both synthetic and real data validate the effectiveness of the proposed approach to classifying four main postures: standing, lying, sitting and bending.

show abstract

Action recognition using time of flight cameras

Cited by 8 publications

References 10 publications

A multi-feature scheme for posture recognition with 3D TOF sensor

A multi-feature scheme for posture recognition with 3D TOF sensor

Kinect Depth Data Segmentation Based on Gauss Mixture Model Clustering

Geodesic-based human posture analysis by using a single 3D TOF camera

Contact Info

Product

Resources

About