An adaptive cost aggregation method based on bilateral filter and canny edge detector with segmented area for stereo matching

Wei Jong Yang, Zi Shiung Tsai, Pau-Choo Chung, Yao Teng Cheng

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

Abstract

In traditional stereo matching, global approach is more accurate but time consuming, also have high accuracy in occlusion area. On the contrary, local approach is usually fast but have bad performance, and easily influenced by noise. This paper proposed a novel method to compute disparity between two images. It is based on local approach, but our new cost function aggregated the cost in global way. This aggregation is processed by a weight map which created by the bilateral filter. Every pixel transfers its own cost information to all pixels on the same object, but this information would be restricted by the weight map. After finishing preliminary depth map, we use L-R check to find occlusion and mismatch pixels to refined our depth map. These refinement mechanics fix occlusion areas by the smallest disparity nearby. At last, we use bilateral filter clean up whole depth map. All of above computing process can be parallelized on GPU or cloud sever. Although this algorithm is designed for lowlevel machine, it still exerts high performance in high-level hardware.

Original languageEnglish
Title of host publicationInternational Workshop on Advanced Image Technology, IWAIT 2019
EditorsQian Kemao, Yung-Lyul Lee, Kazuya Hayase, Phooi Yee Lau, Wen-Nung Lie, Lu Yu, Sanun Srisuk
PublisherSPIE
ISBN (Electronic)9781510627734
DOIs
Publication statusPublished - 2019 Jan 1
EventInternational Workshop on Advanced Image Technology 2019, IWAIT 2019 - Singapore, Singapore
Duration: 2019 Jan 62019 Jan 9

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11049
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceInternational Workshop on Advanced Image Technology 2019, IWAIT 2019
CountrySingapore
CitySingapore
Period19-01-0619-01-09

Fingerprint

Bilateral Filter
Stereo Matching
Depth Map
Occlusion
Aggregation
Agglomeration
Pixel
Detector
occlusion
Detectors
costs
filters
detectors
Costs
Pixels
pixels
Mechanics
Cost Function
High Accuracy
Refinement

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Yang, W. J., Tsai, Z. S., Chung, P-C., & Cheng, Y. T. (2019). An adaptive cost aggregation method based on bilateral filter and canny edge detector with segmented area for stereo matching. In Q. Kemao, Y-L. Lee, K. Hayase, P. Y. Lau, W-N. Lie, L. Yu, & S. Srisuk (Eds.), International Workshop on Advanced Image Technology, IWAIT 2019 [110491J] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11049). SPIE. https://doi.org/10.1117/12.2521396
Yang, Wei Jong ; Tsai, Zi Shiung ; Chung, Pau-Choo ; Cheng, Yao Teng. / An adaptive cost aggregation method based on bilateral filter and canny edge detector with segmented area for stereo matching. International Workshop on Advanced Image Technology, IWAIT 2019. editor / Qian Kemao ; Yung-Lyul Lee ; Kazuya Hayase ; Phooi Yee Lau ; Wen-Nung Lie ; Lu Yu ; Sanun Srisuk. SPIE, 2019. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{8e0c5433acbe4d0bab3e6a4916436a45,
title = "An adaptive cost aggregation method based on bilateral filter and canny edge detector with segmented area for stereo matching",
abstract = "In traditional stereo matching, global approach is more accurate but time consuming, also have high accuracy in occlusion area. On the contrary, local approach is usually fast but have bad performance, and easily influenced by noise. This paper proposed a novel method to compute disparity between two images. It is based on local approach, but our new cost function aggregated the cost in global way. This aggregation is processed by a weight map which created by the bilateral filter. Every pixel transfers its own cost information to all pixels on the same object, but this information would be restricted by the weight map. After finishing preliminary depth map, we use L-R check to find occlusion and mismatch pixels to refined our depth map. These refinement mechanics fix occlusion areas by the smallest disparity nearby. At last, we use bilateral filter clean up whole depth map. All of above computing process can be parallelized on GPU or cloud sever. Although this algorithm is designed for lowlevel machine, it still exerts high performance in high-level hardware.",
author = "Yang, {Wei Jong} and Tsai, {Zi Shiung} and Pau-Choo Chung and Cheng, {Yao Teng}",
year = "2019",
month = "1",
day = "1",
doi = "10.1117/12.2521396",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Qian Kemao and Yung-Lyul Lee and Kazuya Hayase and Lau, {Phooi Yee} and Wen-Nung Lie and Lu Yu and Sanun Srisuk",
booktitle = "International Workshop on Advanced Image Technology, IWAIT 2019",
address = "United States",

}

Yang, WJ, Tsai, ZS, Chung, P-C & Cheng, YT 2019, An adaptive cost aggregation method based on bilateral filter and canny edge detector with segmented area for stereo matching. in Q Kemao, Y-L Lee, K Hayase, PY Lau, W-N Lie, L Yu & S Srisuk (eds), International Workshop on Advanced Image Technology, IWAIT 2019., 110491J, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11049, SPIE, International Workshop on Advanced Image Technology 2019, IWAIT 2019, Singapore, Singapore, 19-01-06. https://doi.org/10.1117/12.2521396

An adaptive cost aggregation method based on bilateral filter and canny edge detector with segmented area for stereo matching. / Yang, Wei Jong; Tsai, Zi Shiung; Chung, Pau-Choo; Cheng, Yao Teng.

International Workshop on Advanced Image Technology, IWAIT 2019. ed. / Qian Kemao; Yung-Lyul Lee; Kazuya Hayase; Phooi Yee Lau; Wen-Nung Lie; Lu Yu; Sanun Srisuk. SPIE, 2019. 110491J (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11049).

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

TY - GEN

T1 - An adaptive cost aggregation method based on bilateral filter and canny edge detector with segmented area for stereo matching

AU - Yang, Wei Jong

AU - Tsai, Zi Shiung

AU - Chung, Pau-Choo

AU - Cheng, Yao Teng

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In traditional stereo matching, global approach is more accurate but time consuming, also have high accuracy in occlusion area. On the contrary, local approach is usually fast but have bad performance, and easily influenced by noise. This paper proposed a novel method to compute disparity between two images. It is based on local approach, but our new cost function aggregated the cost in global way. This aggregation is processed by a weight map which created by the bilateral filter. Every pixel transfers its own cost information to all pixels on the same object, but this information would be restricted by the weight map. After finishing preliminary depth map, we use L-R check to find occlusion and mismatch pixels to refined our depth map. These refinement mechanics fix occlusion areas by the smallest disparity nearby. At last, we use bilateral filter clean up whole depth map. All of above computing process can be parallelized on GPU or cloud sever. Although this algorithm is designed for lowlevel machine, it still exerts high performance in high-level hardware.

AB - In traditional stereo matching, global approach is more accurate but time consuming, also have high accuracy in occlusion area. On the contrary, local approach is usually fast but have bad performance, and easily influenced by noise. This paper proposed a novel method to compute disparity between two images. It is based on local approach, but our new cost function aggregated the cost in global way. This aggregation is processed by a weight map which created by the bilateral filter. Every pixel transfers its own cost information to all pixels on the same object, but this information would be restricted by the weight map. After finishing preliminary depth map, we use L-R check to find occlusion and mismatch pixels to refined our depth map. These refinement mechanics fix occlusion areas by the smallest disparity nearby. At last, we use bilateral filter clean up whole depth map. All of above computing process can be parallelized on GPU or cloud sever. Although this algorithm is designed for lowlevel machine, it still exerts high performance in high-level hardware.

UR - http://www.scopus.com/inward/record.url?scp=85063919831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063919831&partnerID=8YFLogxK

U2 - 10.1117/12.2521396

DO - 10.1117/12.2521396

M3 - Conference contribution

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - International Workshop on Advanced Image Technology, IWAIT 2019

A2 - Kemao, Qian

A2 - Lee, Yung-Lyul

A2 - Hayase, Kazuya

A2 - Lau, Phooi Yee

A2 - Lie, Wen-Nung

A2 - Yu, Lu

A2 - Srisuk, Sanun

PB - SPIE

ER -

Yang WJ, Tsai ZS, Chung P-C, Cheng YT. An adaptive cost aggregation method based on bilateral filter and canny edge detector with segmented area for stereo matching. In Kemao Q, Lee Y-L, Hayase K, Lau PY, Lie W-N, Yu L, Srisuk S, editors, International Workshop on Advanced Image Technology, IWAIT 2019. SPIE. 2019. 110491J. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2521396