Deep Joint Source-Channel Coding for Wireless Image Retrieval

Motivated by surveillance applications with wireless cameras or drones, we consider the problem of image retrieval over a wireless channel. Conventional systems apply lossy compression on query images to reduce the data that must be transmitted over a bandwidth and power limited wireless link. We fi...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 5070 - 5074
Main Authors: Jankowski, Mikolaj, Gunduz, Deniz, Mikolajczyk, Krystian
Format: Conference Proceeding
Language:English
Published: IEEE 01.05.2020
Subjects:
Bandwidth
deep learning
Image coding
Image retrieval
IoT
Joint source-channel coding
person re-identification
retrieval
Speech processing
Surveillance
Task analysis
Wireless communication
ISSN:2379-190X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Motivated by surveillance applications with wireless cameras or drones, we consider the problem of image retrieval over a wireless channel. Conventional systems apply lossy compression on query images to reduce the data that must be transmitted over a bandwidth and power limited wireless link. We first note that reconstructing the original image is not needed for retrieval tasks; hence, we introduce a deep neutral network (DNN) based compression scheme targeting the retrieval task. Then, we completely remove the compression step, and propose another DNN-based communication scheme that directly maps the feature vectors to channel inputs. This joint source-channel coding (JSCC) approach not only improves the end-to-end accuracy, but also simplifies and speeds up the encoding operation which is highly beneficial for power and latency constrained IoT applications.
ISSN:2379-190X
DOI:10.1109/ICASSP40776.2020.9054078