Review of Stereo Matching Algorithms Based on Deep Learning
العنوان: | Review of Stereo Matching Algorithms Based on Deep Learning |
---|---|
المؤلفون: | Zhou Kun, Xiangxi Meng, Bo Cheng |
المصدر: | Computational Intelligence and Neuroscience Computational Intelligence and Neuroscience, Vol 2020 (2020) |
سنة النشر: | 2019 |
مصطلحات موضوعية: | General Computer Science, Computer science, General Mathematics, Computer applications to medicine. Medical informatics, 0211 other engineering and technologies, R858-859.7, Stereo matching, Neurosciences. Biological psychiatry. Neuropsychiatry, 02 engineering and technology, Review Article, Field (computer science), Deep Learning, Image Interpretation, Computer-Assisted, 0202 electrical engineering, electronic engineering, information engineering, 021101 geological & geomatics engineering, business.industry, General Neuroscience, Deep learning, General Medicine, Stereopsis, Unsupervised learning, 020201 artificial intelligence & image processing, Artificial intelligence, business, Algorithm, Algorithms, RC321-571 |
الوصف: | Stereo vision is a flourishing field, attracting the attention of many researchers. Recently, leveraging on the development of deep learning, stereo matching algorithms have achieved remarkable performance far exceeding traditional approaches. This review presents an overview of different stereo matching algorithms based on deep learning. For convenience, we classified the algorithms into three categories: (1) non-end-to-end learning algorithms, (2) end-to-end learning algorithms, and (3) unsupervised learning algorithms. We have provided a comprehensive coverage of the remarkable approaches in each category and summarized the strengths, weaknesses, and major challenges, respectively. The speed, accuracy, and time consumption were adopted to compare the different algorithms. |
تدمد: | 1687-5273 |
الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::65bdd5319651adb874fbdc757b8d5cc8Test https://pubmed.ncbi.nlm.nih.gov/32273887Test |
حقوق: | OPEN |
رقم الانضمام: | edsair.doi.dedup.....65bdd5319651adb874fbdc757b8d5cc8 |
قاعدة البيانات: | OpenAIRE |
تدمد: | 16875273 |
---|