Deep Joint Source-channel Coding for Wireless Image Transmission
We propose a novel joint source and channel coding (JSCC) scheme for wireless image transmission that departs from the conventional use of explicit source and channel codes for compression and error correction, and directly maps the image pixel values to the complex-valued channel input signal. Our...
Gespeichert in:
| Veröffentlicht in: | Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) S. 4774 - 4778 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Tagungsbericht |
| Sprache: | Englisch |
| Veröffentlicht: |
IEEE
01.05.2019
|
| Schlagworte: | |
| ISSN: | 2379-190X |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | We propose a novel joint source and channel coding (JSCC) scheme for wireless image transmission that departs from the conventional use of explicit source and channel codes for compression and error correction, and directly maps the image pixel values to the complex-valued channel input signal. Our encoder-decoder pair form an autoencoder with a non-trainable layer in the middle, which represents the noisy communication channel. Our results show that the proposed deep JSCC scheme outperforms separation-based digital transmission at low signal-to-noise ratio (SNR) and low channel bandwidth regimes in the presence of additive white Gaussian noise (AWGN). More strikingly, deep JSCC does not suffer from the "cliff effect" as the channel SNR varies with respect to the SNR value assumed during training. In the case of a slow Rayleigh fading channel, deep JSCC can learn to communicate without explicit pilot signals or channel estimation, and significantly outperforms separation-based digital communication at all SNR and channel bandwidth values. |
|---|---|
| AbstractList | We propose a novel joint source and channel coding (JSCC) scheme for wireless image transmission that departs from the conventional use of explicit source and channel codes for compression and error correction, and directly maps the image pixel values to the complex-valued channel input signal. Our encoder-decoder pair form an autoencoder with a non-trainable layer in the middle, which represents the noisy communication channel. Our results show that the proposed deep JSCC scheme outperforms separation-based digital transmission at low signal-to-noise ratio (SNR) and low channel bandwidth regimes in the presence of additive white Gaussian noise (AWGN). More strikingly, deep JSCC does not suffer from the "cliff effect" as the channel SNR varies with respect to the SNR value assumed during training. In the case of a slow Rayleigh fading channel, deep JSCC can learn to communicate without explicit pilot signals or channel estimation, and significantly outperforms separation-based digital communication at all SNR and channel bandwidth values. |
| Author | Bourtsoulatze, Eirina Gunduz, Deniz Kurka, David Burth |
| Author_xml | – sequence: 1 givenname: Eirina surname: Bourtsoulatze fullname: Bourtsoulatze, Eirina organization: Electronic and Electrical Engineering, University College London, London, UK – sequence: 2 givenname: David Burth surname: Kurka fullname: Kurka, David Burth organization: Electrical and Electronic Engineering, Imperial College London, London, UK – sequence: 3 givenname: Deniz surname: Gunduz fullname: Gunduz, Deniz organization: Electrical and Electronic Engineering, Imperial College London, London, UK |
| BookMark | eNotj0FOwzAQAA0Cibb0Bb34AwneeBvbN1CgUFQJpBTBrXLidTFKnCouB34PEj3NbTQzZRdxiMTYAkQOIMzNurqr69e8EGByXWqJpTxjc6M0oDJGgwQ4Z5NCKpOBER9XbJrSlxBCK9QTdntPdODPQ4hHXg_fY0tZ-2ljpI5Xgwtxz_0w8vcwUkcp8XVv98S3o42pDymFIV6zS2-7RPMTZ-xt9bCtnrLNy-Nf2iYLoJbHDLHwgIhe-kYjSFEYEK0kQtc6LLRGQl-YRqJ1qvFWNNahLBstyHu3bOSMLf69gYh2hzH0dvzZnYblL0t1TEE |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/ICASSP.2019.8683463 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library (IEL) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISBN | 9781479981311 1479981311 |
| EISSN | 2379-190X |
| EndPage | 4778 |
| ExternalDocumentID | 8683463 |
| Genre | orig-research |
| GroupedDBID | 23M 29P 6IE 6IF 6IH 6IK 6IL 6IM 6IN AAJGR AAWTH ABLEC ACGFS ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP IPLJI M43 OCL RIE RIL RIO RNS |
| ID | FETCH-LOGICAL-i175t-442f1444f3fb841302910c3ee4dcd42884e4f29b34ad7bfa0bad436b80effd5b3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 48 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000482554005002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Sep 10 07:40:31 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i175t-442f1444f3fb841302910c3ee4dcd42884e4f29b34ad7bfa0bad436b80effd5b3 |
| PageCount | 5 |
| ParticipantIDs | ieee_primary_8683463 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-May |
| PublicationDateYYYYMMDD | 2019-05-01 |
| PublicationDate_xml | – month: 05 year: 2019 text: 2019-May |
| PublicationDecade | 2010 |
| PublicationTitle | Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) |
| PublicationTitleAbbrev | ICASSP |
| PublicationYear | 2019 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0008748 |
| Score | 2.4686606 |
| Snippet | We propose a novel joint source and channel coding (JSCC) scheme for wireless image transmission that departs from the conventional use of explicit source and... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 4774 |
| SubjectTerms | Bandwidth Channel estimation Deep neural networks Fading channels Image coding Image communication Image reconstruction joint source-channel coding Signal to noise ratio Speech processing Training Wireless communication wireless image transmission |
| Title | Deep Joint Source-channel Coding for Wireless Image Transmission |
| URI | https://ieeexplore.ieee.org/document/8683463 |
| WOSCitedRecordID | wos000482554005002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB7a4kEvPlrxTQ4ejd3dZHezN6VarEgpVKW3skkmUGh3S936-02ypSp48RYShsAkmS-ZfDMDcO0-y5iJAxpnJqE8VJwKpZCqOMqzXBkReFbl-0s6HIrJJBs14GYbC4OInnyGt67p__J1qdbOVdYViWA8YU1opmlSx2ptra5IudhkFQqDrDvo3Y_HI0fdsnuhFvtVP8XDR3__fxMfQOc7Do-MtghzCA0sjmDvRwrBNtw9IC7JczkrKjL2jnjqYnkLnJNe6aSIvZUSx3GdW5tGBgtrP4gHKLvAzlPWgbf-42vviW6qItCZhfqKch4Z-wrihhkpHARFFvEVQ-RaafuYEBy5iTLJeK5TafJA5pqzRIoAjdGxZMfQKsoCT4CY1KWjY0kcauSBFbCjxkTSnctQx3gKbaeL6bJOfDHdqOHs7-5z2HXqrtmAF9CqVmu8hB31Wc0-Vld-tb4A_mSWVA |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwED_mFNQXPzbx2zz4aFzbpG36pkzHpnMMNmVvo00uUJjtmJ1_v0k7poIvvoWEI-SS3C-5_O4CcG0fy5j2HepHOqDclZwKKZFK34ujWGrhlKzKt344GIjJJBrW4GYdC4OIJfkMb22xfMtXuVxaV1lLBILxgG3Aps-551TRWmu7K0IuVnmFXCdq9dr3o9HQkrfMaqgEf_2gUgJIZ-9_Xe9D8zsSjwzXGHMANcwOYfdHEsEG3D0gzslTnmYFGZWueGqjeTOckXZupYg5lxLLcp0Zq0Z678aCkBKizBRbX1kTXjuP43aXrv5FoKkB-4KasWtzD-Ka6URYEPIM5kuGyJVU5johOHLtRQnjsQoTHTtJrDgLEuGg1spP2BHUszzDYyA6tAnpWOC7CrljBEyr1l5id6arfDyBhtXFdF6lvpiu1HD6d_UVbHfHL_1pvzd4PoMdq_qKG3gO9WKxxAvYkp9F-rG4LGfuCwDdmZs |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+of+the+...+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%281998%29&rft.atitle=Deep+Joint+Source-channel+Coding+for+Wireless+Image+Transmission&rft.au=Bourtsoulatze%2C+Eirina&rft.au=Kurka%2C+David+Burth&rft.au=Gunduz%2C+Deniz&rft.date=2019-05-01&rft.pub=IEEE&rft.eissn=2379-190X&rft.spage=4774&rft.epage=4778&rft_id=info:doi/10.1109%2FICASSP.2019.8683463&rft.externalDocID=8683463 |