Open Access

REVIEW

Junchuan Yang^*
Journal of New Media, Vol.2, No.4, pp. 137-148, 2020, DOI:10.32604/jnm.2020.014278 - 23 December 2020
Abstract Person Re-identification (re-ID) is a hot research topic in the field of computer vision now, which can be regarded as a sub-problem of image retrieval. The goal of person re-ID is to give a monitoring pedestrian image and retrieve other images of the pedestrian across the device. At present, person re-ID is mainly divided into two categories. One is the traditional methods, which relies heavily on manual features. The other is to use deep learning technology to solve. Because traditional methods mainly rely on manual feature, they cannot adapt well to a complex environment with More >

View

2117

Download

1387

Open Access

ARTICLE

Aziguli Wulamu^1,2,*, Jingyue Sang³, Dezheng Zhang^1,2, Zuxian Shi^1,2
Journal of New Media, Vol.2, No.4, pp. 149-155, 2020, DOI:10.32604/jnm.2020.014115 - 23 December 2020
Abstract Cultivated land extraction is essential for sustainable development and agriculture. In this paper, the network we propose is based on the encoderdecoder structure, which extracts the semantic segmentation neural network of cultivated land from satellite images and uses it for agricultural automation solutions. The encoder consists of two part: the first is the modified Xception, it can used as the feature extraction network, and the second is the atrous convolution, it can used to expand the receptive field and the context information to extract richer feature information. The decoder part uses the conventional upsampling operation More >

View

1684

Download

1321

Open Access

ARTICLE

Jihai Yang¹, Zongtao Duan¹, Muyao Wang², Jabar Mahmood¹, Yuanyuan Xiao¹, Yun Yang^1,*
Journal of New Media, Vol.2, No.4, pp. 157-165, 2020, DOI:10.32604/jnm.2020.014309 - 23 December 2020
Abstract Modern autonomous vehicles are getting progressively popular and increasingly getting closer to the core of future development in transportation field. However, there is no reliable authentication mechanism for the unmanned vehicle communication system, this phenomenon draws attention about the security of autonomous vehicles of people in all aspects. Physical Unclonable Function (PUF) circuits is light-weight, and it can product unique and unpredictable digital signature utilizing the manufacturing variations occur in each die and these exact silicon features cannot be recreated theoretically. Considering security issues of communication between Electronic Control Units (ECUs) in vehicles, we propose… More >

View

2391

Download

1356

Open Access

ARTICLE

Duolu Mao^1,*, Kaiyong Li¹, Yaping Mao²
Journal of New Media, Vol.2, No.4, pp. 167-172, 2020, DOI:10.32604/jnm.2020.012816 - 23 December 2020
Abstract In order to improve the accuracy of wireless network positioning, the triangulation method of wireless network positioning technology is proposed, which is based on the linear least square fitting method. It makes the observed value and the fitting value very close, effectively solves the problem of significant contradiction between the fitting result and the observed value in the principle of least square method, and can realize the accurate measurement of geographic information by wireless network positioning technology. More >

View

1705

Download

1205