Robust head and hands tracking with occlusion handling for human machine interaction

Chen, Bor-Jeng; Huang, Cheng-Ming; Tseng, Ting-En; Fu, Li‐Chen

doi:10.1109/iros.2012.6386113

Cited by 9 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, our system achieves the near real-time efficiency (15~20 fps) with 640×480 image resolution and single thread implementation, which are applicable for HMI. [14] …”

Section: Discussionmentioning

confidence: 99%

Hands tracking with self-occlusion handling in cluttered environment

Chen

Huang

Liu

et al. 2013

2013 9th Asian Control Conference (ASCC)

Self Cite

View full text Add to dashboard Cite

This paper presents a two-hands tracking method with a monocular camera for human machine interaction (HMI). To clarify the face of the user and his/her hands, the face is also tracked in our method. The targets are tracked independently when they are far from each other; however, they are merged with dependent likelihood measurements in higher dimension while they are likely to interrupt each other. While one target is being tracked in the independent situation, other targets are masked to decrease the skin color disturbances on the tracked one. Multiple cues, including the combination of the locally discriminative color weighted image and the back-projection image of the reference color model, the motion history image and the gradient orientation feature, are employed to verify the hypotheses originated from the particle filter. On the other hand, when the targets are closing or even overlapping, the multiple importance sampling (MIS) particle filter generates the tracking hypotheses of the merged targets by the skin blob reasoning and the depth order estimation. These joint hypotheses are then evaluated by the visual cues of occluded face template, hand shape gradient orientation, motion continuity and forearm equation. The experimental results present the real-time efficiency and the robustness in comparison with the state-of-the-art human pose estimation method.

show abstract

“…Finally, our system achieves the near real-time efficiency (15~20 fps) with 640×480 image resolution and single thread implementation, which are applicable for HMI. [14] …”

Section: Discussionmentioning

confidence: 99%

Hands tracking with self-occlusion handling in cluttered environment

Chen

Huang

Liu

et al. 2013

2013 9th Asian Control Conference (ASCC)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Regardless of which of the two gesture recognition methods are used, research has shown that gesture commands offer distinct advantages over more traditional mouse and keyboard systems. The greatest advantage that all gesture systems have is that gestures are very natural for the human body to adapt to and use [41], [42]. This comes from the fact that the human body can intuitively keep track of its limbs kinaesthetically, which allows one to utilize the natural dexterity of one's body [37], [43].…”

Section: Figure 4 -Oculus Rift Gogglesmentioning

confidence: 99%

“…And secondly the cameras that are used to pick up the gestures can have major issues when it comes to finding/ determining the actual motion of the joints due to background interference, typically caused by inconsistent lighting, static background objects, and joint/ object orientation [41], [44]. These issues however have not stopped people from attempting to use motion gestures as a method for controlling aircraft.…”

Section: Figure 4 -Oculus Rift Gogglesmentioning

confidence: 99%

Enhancing the functional design of a multi-touch UAV ground control station

Haber¹

2023

Preprint

View full text Add to dashboard Cite

This thesis presents a reconfigurable Ground Control Station designed for Unmanned Aerial Vehicle use, which utilizes multi-touch gesture inputs as well as the ability for the operator to personalize where the instruments they interact with are located on screen. The Ground Control Station that is presented was designed and developed in Ryerson University’s Mixed-Reality Immersive Motion Simulation Laboratory utilizing commercial off the shelf programs supplied by Presagis. Presagis’ VAPS XT 4.1 beta was used to design and develop the actual Ground Control Station’s User Interface due to its ability to create high quality interfaces for aircraft that harness multi-touch gestures. While FlightSIM 14 was used to simulate a high fidelity aircraft being controlled by the Ground Control Station. The final interface was comprised of six key features and 12 different instrument panels that could be manipulated by the operator to control a simulated aircraft throughout a virtual environment.

show abstract

“…Ajallooeion [13] presented a method based on saliency map to rapidly find hand region. Cheng Bor-Jeng, et al [14] presented a face related method for hand finding. Viola and Jones' Haar feature detector detects face directly, and then compute the skin color similarity between face and hand.…”

Section: Introductionmentioning

confidence: 99%

Octree segmentation based calling gesture recognition for elderly care robot

Zhao

Naguib

Lee

2014

Proceedings of the 8th International Conference on Ubiquitous Information Management and Communication

View full text Add to dashboard Cite

This paper presents a method of calling gesture recognition by isolating the head and hand of a caller based on octree segmentation. The recognition of calling gestures is designed here mainly for elderly to call a service robot for their service request. A big challenge to solve is how to make the calling gesture recognition work in a complex environment with crowded people, cluttered and randomly moving objects, as well as illumination variations. The approach taken here is to segment out individual people from the 3D point cloud acquired by Microsoft Kinect or ASUS Xtion Pro and detect their heads and hands in certain geometric configurations. The segmentation is done fast by representing the 3D point cloud in octree cells and clustering those octree cells connected by the neighborhood relationship. The head and hand in a certain geometric configuration are identified from the candidate regions defined with a segmented object and by detecting the shape and color evidences. Color model in HSV color space also discussed to well define the skin color model. The proposed method has been implemented and tested on "HomeMate," a service robot developed for elderly care. The result of performance evaluation is given.

show abstract

Robust head and hands tracking with occlusion handling for human machine interaction

Cited by 9 publications

References 26 publications

Hands tracking with self-occlusion handling in cluttered environment

Hands tracking with self-occlusion handling in cluttered environment

Enhancing the functional design of a multi-touch UAV ground control station

Octree segmentation based calling gesture recognition for elderly care robot

Contact Info

Product

Resources

About