Design of Compressive Imaging Masks for Human Activity Perception Based on Binary Convolutional Neural Network

Ma, Rui1; Liu, Guocheng1; Hao, Qi1; Wang, Cong2

10.1109/MFI.2017.8170438

2017

978-1-5090-6065-8

2017 IEEE INTERNATIONAL CONFERENCE ON MULTISENSOR FUSION AND INTEGRATION FOR INTELLIGENT SYSTEMS (MFI)

2017-November

260-265

16-18 Nov. 2017

10 Exco-ro, Buk-gu, Daegu, Korea, Republic of

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Many applications demand proper design and implementation of 0-1 binary compressive sensing (CS) measurement matrices. This paper presents a construction method for such binary CS measurement matrices by training a convolutional neural network (CNN) with 0-1 weights. The desired CS performance of resultant binary measurement matrices can be achieved by designing a proper CNN training procedure. For human activity recognition applications, such a sensing system is implemented with a small number of optical sensors and optical masks, which can achieve a high recognition capability with a far smaller amount of data than traditional cameras. In the experiments, the compressive sensory readings are classified using a basic K-Nearest Neighbor (KNN) algorithm to demonstrate the high sampling efficiency of hardware without compromising much the recognition performance.

Sensor arrays Kernel Convolution Image sensors Intelligent sensors Sparse matrices

第一 ; 通讯

英语

CPCI-S ; EI

China Postdoctoral Science Foundation[2017M612659]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic

WOS:000426937700040

20180904837539

Compressed sensing ; Convolution ; Intelligent systems ; Nearest neighbor search ; Neural networks

Information Theory and Signal Processing:716.1 ; Artificial Intelligence:723.4 ; Algebra:921.1 ; Optimization Techniques:921.5

Web of Science

1.Southern Univ Sci & Technol, Dept Comp Sci & Engn, Shenzhen 518055, Guangdong, Peoples R China
2.South China Univ Technol, Sch Automat Sci & Engn, Guangzhou 510641, Guangdong, Peoples R China

Ma, Rui,Liu, Guocheng,Hao, Qi,et al. Design of Compressive Imaging Masks for Human Activity Perception Based on Binary Convolutional Neural Network[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2017:260-265.