Enhancement of depth map using texture and depth consistency

Ting An Chang, Jar-Ferr Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)


Presently, the procedure of we obtained depth map is based the stereo matching technique and stereo camera, but the depth map will be acquired based on the above method, the draft depth map is low resolution than texture image, it often produces regions with missing pixels. The missing pixel regions will not include any depth information for the depth image. This reason would lead the performance to degrade seriously in modern-day three-dimensional (3D) video applications. In this paper, we propose adaptive texture-similarity-based hole filling (ATSHF) and rotating counsel depth enhancement (RCDE). The proposed system, which is used for the enhancement of depth maps, is achieved by suppressing the noise, filling holes and sharpening object edges simultaneously. Results of experiments, presented for still images, show that proposed technique increases the quality of depth, especially around the object boundary. Beside, a comparison of the performance of the ATSHF and RCDE with those of customary depth enhancement methods shows that the proposed system is efficient.

Original languageEnglish
Title of host publicationProceedings of the 2016 IEEE Region 10 Conference, TENCON 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages4
ISBN (Electronic)9781509025961
Publication statusPublished - 2017 Feb 8
Event2016 IEEE Region 10 Conference, TENCON 2016 - Singapore, Singapore
Duration: 2016 Nov 222016 Nov 25

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON
ISSN (Print)2159-3442
ISSN (Electronic)2159-3450


Other2016 IEEE Region 10 Conference, TENCON 2016

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering


Dive into the research topics of 'Enhancement of depth map using texture and depth consistency'. Together they form a unique fingerprint.

Cite this