Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Xiaolin Ma"'
Publikováno v:
IEEE Sensors Journal. 21:6487-6496
Micro-Doppler-based continuous human motion recognition (HMR) has gained considerable attention recently. However, existing methods mainly rely on individual recurrent neural network or sliding-window-based approaches, which makes them hard to effect
Publikováno v:
IEEE Sensors Journal. 21:5022-5034
The application of micro-Doppler-based continuous human motion recognition (HMR) is greatly hindered by non-target micro motion interference, due to the deformation of micro-Doppler signatures of target human motion caused by such interference. In th
Publikováno v:
2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC).
To solve the problems of missed text detection and inaccurate text region location in natural scene text detection, a multi-scale and multi-level feature fusion network with attention mechanism is proposed. This method uses the Mask RCNN as the basic
Autor:
Yuying Xiao, Xiaolin Ma
Publikováno v:
2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC).
The field of body action recognition is a research hotspot in computer vision. Due to the complex calculation process of traditional recognition algorithms and the limitations of the data set to be processed, action recognition algorithms based on de
Publikováno v:
2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC).
With the development of convolutional neural networks, Deep Learning (DL) has also made great breakthroughs in the field of image inpainting. Deep Learning-based models can repair large-area missing defaced images, but usually produce various unpleas
Publikováno v:
ICNCC
It is important to reduce the computation complexity while maintaining the accuracy of convolution neural networks. We deem it is possible to further reduce the network complexity while ensuring the accuracy. In this paper, we propose a novel feature
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b60299a5c3787e205fb033dc5e8a9179
Publikováno v:
2019 Chinese Control And Decision Conference (CCDC).
In the ORB-SLAM system for mobile robots, there are many problems such as large matching error, slow operation speed, low positioning accuracy and small map application scope. To solve these problems, this paper first adds the depth information based
Publikováno v:
2018 Chinese Control And Decision Conference (CCDC).
Aiming at solving the difficulty of feature selecting and the poor retrieval result in the image retrieval, we proposed an image retrieval algorithm which was based on multiple convolutional features of RPN and weighted cosine similarity. We used the
Publikováno v:
2018 10th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA).
Human activity categories can be mainly divided into two types: body motion (e.g. "dancing" and "jumping") and human-object interaction (e.g. "playing guitar" and "riding bike"). In this paper, we propose a model that uses this insight to combine spa
Publikováno v:
Applied Sciences; Volume 6; Issue 11; Pages: 329
Applied Sciences, Vol 6, Iss 11, p 329 (2016)
Applied Sciences, Vol 6, Iss 11, p 329 (2016)
In this paper, we explore the properties of the Channel State Information (CSI) of WiFi signals and present a device-free indoor activity recognition system. Our proposed system uses only one ubiquitous router access point and a laptop as a detection