Stereo matching algorithm based on deep learning: A survey
The development of stereo matching algorithm is still one of the challenging problems, especially in ill-posed regions. Hence, this article presents a survey on the algorithm frameworks related to the stereo matching algorithm. Based on the early survey that had been conducted, two major frameworks...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-05-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157820304493 |
| _version_ | 1811307199464472576 |
|---|---|
| author | Mohd Saad Hamid NurulFajar Abd Manap Rostam Affendi Hamzah Ahmad Fauzan Kadmin |
| author_facet | Mohd Saad Hamid NurulFajar Abd Manap Rostam Affendi Hamzah Ahmad Fauzan Kadmin |
| author_sort | Mohd Saad Hamid |
| collection | DOAJ |
| description | The development of stereo matching algorithm is still one of the challenging problems, especially in ill-posed regions. Hence, this article presents a survey on the algorithm frameworks related to the stereo matching algorithm. Based on the early survey that had been conducted, two major frameworks available in current stereo matching algorithm development, they are traditional and artificial intelligence (AI) frameworks. Most of the traditional methods are very low accuracy compared to the AI-based approach. This can be observed in the standard benchmarking dataset, such as from the KITTI and the Middlebury, where AI methods rank at the top of the accuracy list. Additionally, the trend for solving computer vision problems uses AI or machine learning tools that become more apparent in recent years. Thus, this paper is focusing on the survey between the deep learning frameworks, which is one of the machine learning tools related to the convolutional neural network (CNN). Several mixed approaches between CNN based method and traditional handcraft method, as well as the end to end CNN method also discussed in this paper. |
| first_indexed | 2024-04-13T09:00:21Z |
| format | Article |
| id | doaj.art-cb1d8f198ea14790af353390fda20f0d |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-04-13T09:00:21Z |
| publishDate | 2022-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-cb1d8f198ea14790af353390fda20f0d2022-12-22T02:53:09ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782022-05-0134516631673Stereo matching algorithm based on deep learning: A surveyMohd Saad Hamid0NurulFajar Abd Manap1Rostam Affendi Hamzah2Ahmad Fauzan Kadmin3Fakulti Teknologi Kejuruteraan Elektrik & Elektronik, Universiti Teknikal Malaysia Melaka, 76100 Durian Tunggal, Melaka, MalaysiaFakulti Kejuruteraan Elektronik & Kejuruteraan Komputer, Universiti Teknikal Malaysia Melaka, 76100 Durian Tunggal, Melaka, MalaysiaFakulti Teknologi Kejuruteraan Elektrik & Elektronik, Universiti Teknikal Malaysia Melaka, 76100 Durian Tunggal, Melaka, Malaysia; Corresponding author.Fakulti Teknologi Kejuruteraan Elektrik & Elektronik, Universiti Teknikal Malaysia Melaka, 76100 Durian Tunggal, Melaka, MalaysiaThe development of stereo matching algorithm is still one of the challenging problems, especially in ill-posed regions. Hence, this article presents a survey on the algorithm frameworks related to the stereo matching algorithm. Based on the early survey that had been conducted, two major frameworks available in current stereo matching algorithm development, they are traditional and artificial intelligence (AI) frameworks. Most of the traditional methods are very low accuracy compared to the AI-based approach. This can be observed in the standard benchmarking dataset, such as from the KITTI and the Middlebury, where AI methods rank at the top of the accuracy list. Additionally, the trend for solving computer vision problems uses AI or machine learning tools that become more apparent in recent years. Thus, this paper is focusing on the survey between the deep learning frameworks, which is one of the machine learning tools related to the convolutional neural network (CNN). Several mixed approaches between CNN based method and traditional handcraft method, as well as the end to end CNN method also discussed in this paper.http://www.sciencedirect.com/science/article/pii/S1319157820304493Stereo matching algorithmDeep learningConvolutional neural networkArtificial intelligence |
| spellingShingle | Mohd Saad Hamid NurulFajar Abd Manap Rostam Affendi Hamzah Ahmad Fauzan Kadmin Stereo matching algorithm based on deep learning: A survey Journal of King Saud University: Computer and Information Sciences Stereo matching algorithm Deep learning Convolutional neural network Artificial intelligence |
| title | Stereo matching algorithm based on deep learning: A survey |
| title_full | Stereo matching algorithm based on deep learning: A survey |
| title_fullStr | Stereo matching algorithm based on deep learning: A survey |
| title_full_unstemmed | Stereo matching algorithm based on deep learning: A survey |
| title_short | Stereo matching algorithm based on deep learning: A survey |
| title_sort | stereo matching algorithm based on deep learning a survey |
| topic | Stereo matching algorithm Deep learning Convolutional neural network Artificial intelligence |
| url | http://www.sciencedirect.com/science/article/pii/S1319157820304493 |
| work_keys_str_mv | AT mohdsaadhamid stereomatchingalgorithmbasedondeeplearningasurvey AT nurulfajarabdmanap stereomatchingalgorithmbasedondeeplearningasurvey AT rostamaffendihamzah stereomatchingalgorithmbasedondeeplearningasurvey AT ahmadfauzankadmin stereomatchingalgorithmbasedondeeplearningasurvey |