What is it about?
Human action recognition has been widely used in various fields of computer vision, pattern recognition and human-computer interaction and has attracted substantial attention. Combining deep learning and depth information, this paper proposed a new method of human action recognition based on improved Convolutional Neural Networks(CNNs).
Featured Image
Why is it important?
We use the depth motion maps (DMMs) to extract the depth sequence features and obtain three projected maps corresponding to front, side, and the top views. On this basis, an improved convolutional neural network is constructed to realize the recognition of human action, which uses three-dimensional input and two-dimensional process identification to speed up the computation and reduce the complexity of recognition process.The trained model on one depth video sequence dataset can be easily generalized to different datasets without changing network parameters.
Perspectives
We evaluate our approach on two public 3D action datasets: MSR Action3D Dataset and UT-Kinect Dataset, and one private CTP Action3D dataset that we built using Kinect to collect data. Experimental results show that the proposed methods of human action recognition achieve higher average recognition rate of 91.3% on MSR Action3D dataset, and 97.98% on UT-Kinect Dataset, and the average recognition rate is 93.8% on our CTP Action3D dataset.
Prof. Linqin CAI
Read the Original
This page is a summary of: Robust human action recognition based on depth motion maps and improved convolutional neural network, Journal of Electronic Imaging, April 2018, SPIE,
DOI: 10.1117/1.jei.27.5.051218.
You can read the full text:
Contributors
The following have contributed to this page
