Efficient Human-Robot Interaction using Deep Learning with Mask R-CNN: Detection, Recognition, Tracking and Segmentation
Journal Title: Progress in Human Computer Interaction - Year 2018, Vol 1, Issue 2
Abstract
We address social human-robot interaction problem by proposing an integration of deep neural network with mechanical robotic system to make it robust for human-robot interactive activities. Mask R-CNN, a neural network for object detection, can effectively help localize human faces which can be manipulated to instruct movement of the robot head. Our approach is not only suitable for detection and segmentation tasks but able to integrate as well with the mechanism of parallel mini-manipulator representing the 3D dimensions, in position and orientation of workspace. It can also solve the object segmentation problem which appears to be one of the most challenging issues in computer vision nowadays.
Authors and Affiliations
Than Le, Dang Huynh
Keywords
Related Articles
- EP ID EP679116
- DOI -
- Views 258
- Downloads 0
Fusion of Cognitive Neuroscience and Human-Computer Interaction: A New Trend in Human-Computer Interaction Research
This paper, by means of literature and element analysis, discusses relevant literature in different fields such as cognitive neuroscience, human-computer interaction and brain-computer interface. Firstly, the development...
Lab VIEW Program Design of Public Traffic Station Broadcasting System
The development of traffi c information for us, is a sign of the development of civilized society. This topic uses the advanced technology idea to provide a transportation information automation solution. This paper intr...
Interactive Design of Mobile Phone Interface
This topic is divided into two parts: (1) mobile phone interactive design of the status quo survey, including the mobile phone market, the use of the crowd, the use of functions, keyboard and interface analysis. (2) Mobi...
Structural Design, Optimization and Analysis of Robotic Arm Via Finite Elements.
The study set out to determine the optimum architecture of a robotic arm link based on weight and payload and perform vibrational and stress analyses on the resultant shape. Findings showed the effectiveness of topology...
Face Image Set Recognition Based on Improved HOG-NMF and Convolutional Neural Networks
Objective Face recognition can be affected by unfavorable factors such as illumination, posture and expression, but the face image set is a collection of people’s various angles, different illuminations and even differen...