Using Segmented 3D Point Clouds for Accurate Likelihood Approximation in Human Pose Tracking

Lehment, Nicolas H.; Kaiser, M. Shamim; Rigoll, Gerhard

doi:10.1007/s11263-012-0557-0

Cited by 10 publications

(5 citation statements)

References 17 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Human point cloud segmentation is typically challenging and difficult to achieve correct approximations, especially when there is self-occlusion and no color or texture signals. Lehment et al's suggested segmentation model [16] attempted to address this issue by extracting tiny regions of high saliency, such as the hands or arms, and ensuring that the information contained in these regions is not overshadowed by larger, less salient parts, such as the chest. The use of a deep recurrent hierarchical network can also provide more flexibility by minimizing or eliminating posture detection issues caused by a limited visibility human torso in the frame, also known as the frame occlusion problem, which occurs when only a portion of the body is visible [17].…”

Section: Related Workmentioning

confidence: 99%

Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images

Ryselis

Blažauskas

Damaševičius

et al. 2022

Sensors

View full text Add to dashboard Cite

The identification of human activities from videos is important for many applications. For such a task, three-dimensional (3D) depth images or image sequences (videos) can be used, which represent the positioning information of the objects in a 3D scene obtained from depth sensors. This paper presents a framework to create foreground–background masks from depth images for human body segmentation. The framework can be used to speed up the manual depth image annotation process with no semantics known beforehand and can apply segmentation using a performant algorithm while the user only adjusts the parameters, or corrects the automatic segmentation results, or gives it hints by drawing a boundary of the desired object. The approach has been tested using two different datasets with a human in a real-world closed environment. The solution has provided promising results in terms of reducing the manual segmentation time from the perspective of the processing time as well as the human input time.

show abstract

Section: Related Workmentioning

confidence: 99%

Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images

Ryselis

Blažauskas

Damaševičius

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Fouhey et al presented an estimation algorithm for the depth fading in Kinect depth image [7]. For human gesture recognition, Yan et al used Kinect to precisely recognize hand gestures, especially the gestures of fingers [8].Lehment et al proposed a pose tracking algorithm based on segmented 3D point clouds [9].…”

Section: Introductionmentioning

confidence: 99%

Pixel-line based clustering for the 3D point cloud generated by Kinect depth map

Qiu¹,

Zheng²

2013

2013 IEEE International Conference on Information and Automation (ICIA)

View full text Add to dashboard Cite

A novel pixel-line based clustering algorithm for Kinect depth image data is proposed in this paper. The algorithm first clusters the three-dimensional points belonging to the same pixel row. Then the single row clusters coming from adjacent rows are compared and matched to fulfill the three-dimensional cluster growth. Experiments are carried out with both office scene and greenhouse scene. The clustering results show that the algorithm is good at highlighting small objects but is sensitive to uneven surfaces.Index Terms -clustering, pixel-line based, 3D point cloud, Kinect, depth image.

show abstract

“…Ugolotti and Cagnoni (2013) parametrically describes a deformable body model with 42 parameters: 29 degrees-of-freedom to describe articulated skeletal joints, 7 parameters to specify limb lengths/thicknesses; and 6 parameters describing the relative pose of the model. A similar idea is explored by Lehment et al (2013) who searches a 22-DOF human pose space using an observation likelihood function approximation whereby point-cloud measurements from a Kinect sensor are compared to the expected point-cloud of a pose hypothesis. Both of these works use parallel processing to search the large pose space in real-time.…”

Section: Quality Control Is a Domain In Which 'mentioning

confidence: 99%

“…The most likely hypothesis is determined using a Bayesian filter that infers evidence towards hypotheses through the summation of likelihood weights based on measurements. Similarly Lehment et al (2013) determines the parametric pose of a human by comparing measurements against the expected measurements for 800 pose hypotheses. The most likely pose is determined using an approximation of the conditional measurement probability under each pose hypothesis.…”

Section: Maximum-sum-of-evidence Pose Estimationmentioning

confidence: 99%

“…The encoder resolution of the sensor-head is 0. computation time is reduced by approximately 400 times when using precomputed ranges. The MSoE estimator lends itself to parallel computation (Lehment et al (2013), Ugolotti and Cagnoni (2013)). Hypothesis support is independent and can be calculated concurrently on multiple threads.…”

Section: Feasibility Of Real-time Evidence-based Pose Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Determining and verifying object pose from LiDAR measurements to support the perception needs of an autonomous excavator

Phillips¹

View full text Add to dashboard Cite

This thesis is a study of how light detection and ranging, also known as LiDAR, can be used to meet perception requirements for field robot applications.LiDAR works by having an emitter produce a pulse of light along a known spatial direction. The distance or range to the world along that direction is determined by measuring the time it takes for reflections of the emitted light to be received at a collector. When this is done over multiple spatial directions, a cloud of points is produced that represent a sampling of the world. LiDAR is a mature technology and commercially available sensors are capable of producing point-clouds comprising up to 65,000 points over 360 degree fields of view, that are updated every 50 ms.This thesis is about how an autonomous machine can interpret meaning from these point-clouds in situations where the environment is complex and dynamic, where there is interaction with other agents leading to occlusion and where there is significant dust in the atmosphere.These conditions are systemic to open-cut mining environments, the domain where this thesis draws its motivation. In particular, the thesis uses as its primary example, the perception requirements for automation of a class of large mining excavators known as electric mining shovels. The work is specifically concerned with the problems of using point-clouds from machine mounted sensors to inform and verify knowledge of object position and orientation in the surrounds of these machines, for instance, the trucks being loaded.LiDAR is affected by dust and some see this a fatal flaw for mining robotics. The work starts with an exploration of the behaviour of a commercial LiDAR sensor in the presence of dust and finds that measurements are systematic and predictable. LiDAR sensors are found to exhibit four behaviours and it is shown how these behaviours can be understood from physics-based arguments. Several conclusions emerge, most notably where LiDAR measures dust, it does so to the leading edge of a dust-cloud rather than, say, as a random point within the cloud. This provides powerful insights into how better to use measurements from LiDAR when dust is present, and in particular suggests that dust can be treated like other forms of occlusion.A problem that must be solved to use LiDAR for machine perception is to establish from where each sensor views the world. This is sometimes called sensor registration and it amounts to finding where a sensor is positioned and how it is orientated. This is typically done by placing markers at known locations and computing the sensor registration from where they appear in the sensor data. For mining robot applications, the use of standard marker or artificial-feature-based approaches is infeasible. The thesis develops a method for sensor registration that overcomes this concern by utilizing the geometric structure of the terrain surrounding the autonomous vehicle platform. The method determines the i information content of registration parameters in measurements of the terrain, and update...

show abstract

Using Segmented 3D Point Clouds for Accurate Likelihood Approximation in Human Pose Tracking

Cited by 10 publications

References 17 publications

Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images

Computer-Aided Depth Video Stream Masking Framework for Human Body Segmentation in Depth Sensor Images

Pixel-line based clustering for the 3D point cloud generated by Kinect depth map

Determining and verifying object pose from LiDAR measurements to support the perception needs of an autonomous excavator

Contact Info

Product

Resources

About