Toggle navigation
Home
About
About Journal
Historical Evolution
Indexed In
Awards
Reference Index
Editorial Board
Journal Online
Archive
Project Articles
Most Download Articles
Most Read Articles
Instruction
Contribution Column
Author Guidelines
Template
FAQ
Copyright Agreement
Expenses
Academic Integrity
Contact
Contact Us
Location Map
Subscription
Advertisement
中文
Journals
Publication Years
Keywords
Search within results
(((QIN Linlin[Author]) AND 1[Journal]) AND year[Order])
AND
OR
NOT
Title
Author
Institution
Keyword
Abstract
PACS
DOI
Please wait a minute...
For Selected:
Download Citations
EndNote
Ris
BibTeX
Toggle Thumbnails
Select
Human interaction recognition based on RGB and skeleton data fusion model
JI Xiaofei, QIN Linlin, WANG Yangyang
Journal of Computer Applications 2019, 39 (
11
): 3349-3354. DOI:
10.11772/j.issn.1001-9081.2019040633
Abstract
(
476
)
PDF
(993KB)(
345
)
Knowledge map
Save
In recent years, significant progress has been made in human interaction recognition based on RGB video sequences. Due to its lack of depth information, it cannot obtain accurate recognition results for complex interactions. The depth sensors (such as Microsoft Kinect) can effectively improve the tracking accuracy of the joint points of the whole body and obtain three-dimensional data that can accurately track the movement and changes of the human body. According to the respective characteristics of RGB and joint point data, a convolutional neural network structure model based on RGB and joint point data dual-stream information fusion was proposed. Firstly, the region of interest of the RGB video in the time domain was obtained by using the Vibe algorithm, and the key frames were extracted and mapped to the RGB space to obtain the spatial-temporal map representing the video information. The map was sent to the convolutional neural network to extract features. Then, a vector was constructed in each frame of the joint point sequence to extract the Cosine Distance (CD) and Normalized Magnitude (NM) features. The cosine distance and the characteristics of the joint nodes in each frame were connected in time order of the joint point sequence, and were fed into the convolutional neural network to learn more advanced temporal features. Finally, the softmax recognition probability matrixes of the two information sources were fused to obtain the final recognition result. The experimental results show that combining RGB video information with joint point information can effectively improve the recognition result of human interaction behavior, and achieves 92.55% and 80.09% recognition rate on the international public SBU Kinect interaction database and NTU RGB+D database respectively, verifying the effectiveness of the proposed model for the identification of interaction behaviour between two people.
Reference
|
Related Articles
|
Metrics
Select
File type detection algorithm based on principal component analysis and
K
nearest neighbors
YAN Mengdi, QIN Linlin, WU Gang
Journal of Computer Applications 2016, 36 (
11
): 3161-3164. DOI:
10.11772/j.issn.1001-9081.2016.11.3161
Abstract
(
587
)
PDF
(583KB)(
481
)
Knowledge map
Save
In order to solve the problem that using the file suffix and file feature to identify file type may cause a low recognition accuracy rate, a new content-based file-type detection algorithm was proposed, which was based on Principal Component Analysis (PCA) and
K
Nearest Neighbors (
K
NN). Firstly, PCA algorithm was used to reduce the dimension of the sample space. Then by clustering the training samples, each file type was represented by cluster centroids. In order to reduce the error caused by unbalanced training samples,
K
NN algorithm based on distance weighting was proposed. The experimental result shows that the improved algorithm, in the case of a large number of training samples, can reduce computational complexity, and can maintain a high recognition accuracy rate. This algorithm doesn't depend on the feature of each file, so it can be used more widely.
Reference
|
Related Articles
|
Metrics