Towards joint attention for a domestic service robot - person awareness and gesture recognition using Time-of-Flight cameras

Droeschel, David; Stückler, Jörg; Holz, Dirk; Behnke, Sven

doi:10.1109/icra.2011.5980067

Cited by 30 publications

(11 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their results were obtained after testing the algorithm on a purposely built dataset of their own which included only the activities involving one individual. Droeschel et al presented a person awareness and gesture recognition approach for joint attention in a domestic environment [8]. They used time-of-flight cameras to classify between showing and pointing gestures and presented their results with high accuracy.…”

Section: Related Workmentioning

confidence: 99%

Tracking a Subset of Skeleton Joints: An Effective Approach towards Complex Human Activity Recognition

Anjum

Rosa

Bona

2017

Journal of Robotics

View full text Add to dashboard Cite

We present a robust algorithm for complex human activity recognition for natural human-robot interaction. The algorithm is based on tracking the position of selected joints in human skeleton. For any given activity, only a few skeleton joints are involved in performing the activity, so a subset of joints contributing the most towards the activity is selected. Our approach of tracking a subset of skeleton joints (instead of tracking the whole skeleton) is computationally efficient and provides better recognition accuracy. We have developed both manual and automatic approaches for the selection of these joints. The position of the selected joints is tracked for the duration of the activity and is used to construct feature vectors for each activity. Once the feature vectors have been constructed, we use a Support Vector Machines (SVM) multiclass classifier for training and testing the algorithm. The algorithm has been tested on a purposely built dataset of depth videos recorded using Kinect camera. The dataset consists of 250 videos of 10 different activities being performed by different users. Experimental results show classification accuracy of 83% when tracking all skeleton joints, 95% when using manual selection of subset joints, and 89% when using automatic selection of subset joints.

show abstract

Section: Related Workmentioning

confidence: 99%

Tracking a Subset of Skeleton Joints: An Effective Approach towards Complex Human Activity Recognition

Anjum

Rosa

Bona

2017

Journal of Robotics

View full text Add to dashboard Cite

show abstract

“…The combination of a depth sensor with a color camera has been exploited in several applications such as object recognition [48,108,2], person awareness, gesture recognition [31], simultaneous localization and mapping (SLAM) [10,64], robotized plant-growth measurement [1], etc. These methods mainly deal with the problem of noise in depth measurement, as examined in chapter 1, as well as with the low resolution of range data as compared to the color data.…”

Section: Related Workmentioning

confidence: 99%

Time-of-Flight Cameras

Hansard

Lee

Choi

et al. 2013

SpringerBriefs in Computer Science

167

View full text Add to dashboard Cite

This chapter introduces the principles and difficulties of time-of-flight depth measurement. The depth-images that are produced by time-of-flight cameras suffer from characteristic problems, which are divided into the following two classes. Firstly there are systematic errors, such as noise and ambiguity, which are directly related to the sensor. Secondly, there are non-systematic errors, such as scattering and motion blur, which are more strongly related to the scene-content. It is shown that these errors are often quite different from those observed in ordinary color images. The case of motion blur, which is particularly problematic, is examined in detail. A practical methodology for investigating the performance of depth-cameras is presented. Time-of-flight devices are compared to structured-light systems, and the problems posed by specular and translucent materials are investigated.

show abstract

“…For example, the robot can draw a user's attention to certain locations in the environment by simply pointing at it. Our robots can also perceive gestures such as pointing, showing of objects, or stop gestures [4]. The robots sense these gestures using the RGB-D camera.…”

Section: Gesture Recognition and Synthesismentioning

confidence: 99%

Towards Robust Mobility, Flexible Object Manipulation, and Intuitive Multimodal Interaction for Domestic Service Robots

Stückler

Droeschel

Gräve

et al. 2012

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper, we detail the contributions of our team NimbRo to the RoboCup @Home league in 2011. We explain design and rationale of our domestic service robot Cosero that we used for the first time in a competition in 2011. We demonstrated novel capabilities in the league such as real-time table-top segmentation, flexible grasp planning, and real-time tracking of objects. We also describe our approaches to humanrobot cooperative manipulation and 3D navigation. Finally, we report on the use of our approaches and the performance of our robots at RoboCup 2011.

show abstract

Towards joint attention for a domestic service robot - person awareness and gesture recognition using Time-of-Flight cameras

Cited by 30 publications

References 28 publications

Tracking a Subset of Skeleton Joints: An Effective Approach towards Complex Human Activity Recognition

Tracking a Subset of Skeleton Joints: An Effective Approach towards Complex Human Activity Recognition

Time-of-Flight Cameras

Towards Robust Mobility, Flexible Object Manipulation, and Intuitive Multimodal Interaction for Domestic Service Robots

Contact Info

Product

Resources

About