Improving Census Transform by High-Pass with Haar Wavelet Transform and Edge Detection
One of the common methods for measuring distance is to use a camera and image processing algorithm, such as an eye and brain. Mechanical stereo vision uses two cameras to shoot the same object and analyzes the disparity of the stereo vision. One of the most robust methods to calculate disparity is t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/9/2537 |
| _version_ | 1797569256205844480 |
|---|---|
| author | Jiun-Jian Liaw Chuan-Pin Lu Yung-Fa Huang Yu-Hsien Liao Shih-Cian Huang |
| author_facet | Jiun-Jian Liaw Chuan-Pin Lu Yung-Fa Huang Yu-Hsien Liao Shih-Cian Huang |
| author_sort | Jiun-Jian Liaw |
| collection | DOAJ |
| description | One of the common methods for measuring distance is to use a camera and image processing algorithm, such as an eye and brain. Mechanical stereo vision uses two cameras to shoot the same object and analyzes the disparity of the stereo vision. One of the most robust methods to calculate disparity is the well-known census transform, which has the problem of conversion window selection. In this paper, three methods are proposed to improve the performance of the census transform. The first one uses a low-pass band of the wavelet to reduce the computation loading and a high-pass band of the wavelet to modify the disparity. The main idea of the second method is the adaptive size selection of the conversion window by edge information. The third proposed method is to apply the adaptive window size to the previous sparse census transform. In the experiments, two indexes, percentage of bad matching pixels (PoBMP) and root mean squared (RMS), are used to evaluate the performance with the known ground truth data. According to the results, the computation required can be reduced by the multiresolution feature of the wavelet transform. The accuracy is also improved with the modified disparity processing. Compared with previous methods, the number of operation points is reduced by the proposed adaptive window size method. |
| first_indexed | 2024-03-10T20:09:20Z |
| format | Article |
| id | doaj.art-403f57f76afc470785be8c113131edad |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:09:20Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-403f57f76afc470785be8c113131edad2023-11-19T23:03:25ZengMDPI AGSensors1424-82202020-04-01209253710.3390/s20092537Improving Census Transform by High-Pass with Haar Wavelet Transform and Edge DetectionJiun-Jian Liaw0Chuan-Pin Lu1Yung-Fa Huang2Yu-Hsien Liao3Shih-Cian Huang4Department of Information and Communication Engineering, Chaoyang University of Technology, Taichung 413310, TaiwanDepartment of Information Technology, Meiho University, Pingtung 912009, TaiwanDepartment of Information and Communication Engineering, Chaoyang University of Technology, Taichung 413310, TaiwanDepartment of Information and Communication Engineering, Chaoyang University of Technology, Taichung 413310, TaiwanDepartment of Information and Communication Engineering, Chaoyang University of Technology, Taichung 413310, TaiwanOne of the common methods for measuring distance is to use a camera and image processing algorithm, such as an eye and brain. Mechanical stereo vision uses two cameras to shoot the same object and analyzes the disparity of the stereo vision. One of the most robust methods to calculate disparity is the well-known census transform, which has the problem of conversion window selection. In this paper, three methods are proposed to improve the performance of the census transform. The first one uses a low-pass band of the wavelet to reduce the computation loading and a high-pass band of the wavelet to modify the disparity. The main idea of the second method is the adaptive size selection of the conversion window by edge information. The third proposed method is to apply the adaptive window size to the previous sparse census transform. In the experiments, two indexes, percentage of bad matching pixels (PoBMP) and root mean squared (RMS), are used to evaluate the performance with the known ground truth data. According to the results, the computation required can be reduced by the multiresolution feature of the wavelet transform. The accuracy is also improved with the modified disparity processing. Compared with previous methods, the number of operation points is reduced by the proposed adaptive window size method.https://www.mdpi.com/1424-8220/20/9/2537census transformsparse census transformdisparitystereo vision |
| spellingShingle | Jiun-Jian Liaw Chuan-Pin Lu Yung-Fa Huang Yu-Hsien Liao Shih-Cian Huang Improving Census Transform by High-Pass with Haar Wavelet Transform and Edge Detection Sensors census transform sparse census transform disparity stereo vision |
| title | Improving Census Transform by High-Pass with Haar Wavelet Transform and Edge Detection |
| title_full | Improving Census Transform by High-Pass with Haar Wavelet Transform and Edge Detection |
| title_fullStr | Improving Census Transform by High-Pass with Haar Wavelet Transform and Edge Detection |
| title_full_unstemmed | Improving Census Transform by High-Pass with Haar Wavelet Transform and Edge Detection |
| title_short | Improving Census Transform by High-Pass with Haar Wavelet Transform and Edge Detection |
| title_sort | improving census transform by high pass with haar wavelet transform and edge detection |
| topic | census transform sparse census transform disparity stereo vision |
| url | https://www.mdpi.com/1424-8220/20/9/2537 |
| work_keys_str_mv | AT jiunjianliaw improvingcensustransformbyhighpasswithhaarwavelettransformandedgedetection AT chuanpinlu improvingcensustransformbyhighpasswithhaarwavelettransformandedgedetection AT yungfahuang improvingcensustransformbyhighpasswithhaarwavelettransformandedgedetection AT yuhsienliao improvingcensustransformbyhighpasswithhaarwavelettransformandedgedetection AT shihcianhuang improvingcensustransformbyhighpasswithhaarwavelettransformandedgedetection |