Wireless Image Retrieval at the Edge

被引:139
作者
Jankowski, Mikolaj [1 ]
Gunduz, Deniz [1 ]
Mikolajczyk, Krystian [1 ]
机构
[1] Imperial Coll London, Dept Elect & Elect Engn, London SW7 2BU, England
基金
英国工程与自然科学研究理事会; 欧洲研究理事会;
关键词
Image edge detection; Servers; Task analysis; Wireless communication; Performance evaluation; Image coding; Feature extraction; Deep learning; Internet of Things; image retrieval; joint source-channel coding; person re-identification; NETWORK;
D O I
10.1109/JSAC.2020.3036955
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
We study the image retrieval problem at the wireless edge, where an edge device captures an image, which is then used to retrieve similar images from an edge server. These can be images of the same person or a vehicle taken from other cameras at different times and locations. Our goal is to maximize the accuracy of the retrieval task under power and bandwidth constraints over the wireless link. Due to the stringent delay constraint of the underlying application, sending the whole image at a sufficient quality is not possible. We propose two alternative schemes based on digital and analog communications, respectively. In the digital approach, we first propose a deep neural network (DNN) aided retrieval-oriented image compression scheme, whose output bit sequence is transmitted over the channel using conventional channel codes. In the analog joint source and channel coding (JSCC) approach, the feature vectors are directly mapped into channel symbols. We evaluate both schemes on image based re-identification (re-ID) tasks under different channel conditions, including both static and fading channels. We show that the JSCC scheme significantly increases the end-to-end accuracy, speeds up the encoding process, and provides graceful degradation with channel conditions. The proposed architecture is evaluated through extensive simulations on different datasets and channel conditions, as well as through ablation studies.
引用
收藏
页码:89 / 100
页数:12
相关论文
共 43 条
[1]  
Abad MSH, 2020, INT CONF ACOUST SPEE, P8866, DOI [10.1109/ICASSP40776.2020.9054634, 10.1109/icassp40776.2020.9054634]
[2]   Federated Learning Over Wireless Fading Channels [J].
Amiri, Mohammad Mohammadi ;
Gunduz, Deniz .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2020, 19 (05) :3546-3557
[3]  
Amiri MM, 2019, IEEE INT SYMP INFO, P1432, DOI [10.1109/ISIT.2019.8849334, 10.1109/tsp.2020.2981904]
[4]  
[Anonymous], 2017, ARXIV170307737CS
[5]   Deep Joint Source-Channel Coding for Wireless Image Transmission [J].
Bourtsoulatze, Eirina ;
Kurka, David Burth ;
Gunduz, Deniz .
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2019, 5 (03) :567-579
[6]   Multi-Level Factorisation Net for Person Re-Identification [J].
Chang, Xiaobin ;
Hospedales, Timothy M. ;
Xiang, Tao .
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :2109-2118
[7]   ABD-Net: Attentive but Diverse Person Re-Identification [J].
Chen, Tianlong ;
Ding, Shaojin ;
Xie, Jingyi ;
Yuan, Ye ;
Chen, Wuyang ;
Yang, Yang ;
Ren, Zhou ;
Wang, Zhangyang .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :8350-8360
[8]  
Davis G. M., 1999, P SPIE, V2847, P376
[9]  
Eshratifar AE, 2019, INT SYM QUAL ELECT, P14, DOI [10.1109/ISQED.2019.8697647, 10.1109/isqed.2019.8697647]
[10]  
Farsad N, 2018, 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), P2326, DOI 10.1109/ICASSP.2018.8461983