Knowledge Commons of Institute of Automation,CAS
Modeling Stereopsis via Markov Random Field | |
Ming, Yansheng; Hu, Zhanyi | |
发表期刊 | NEURAL COMPUTATION |
2010-08-01 | |
卷号 | 22期号:8页码:2161-2191 |
文章类型 | Article |
摘要 | Markov random field (MRF) and belief propagation have given birth to stereo vision algorithms with top performance. This article explores their biological plausibility. First, an MRF model guided by physiological and psychophysical facts was designed. Typically an MRF-based stereo vision algorithm employs a likelihood function that reflects the local similarity of two regions and a potential function that models the continuity constraint. In our model, the likelihood function is constructed on the basis of the disparity energy model because complex cells are considered as front-end disparity encoders in the visual pathway. Our likelihood function is also relevant to several psychological findings. The potential function in our model is constrained by the psychological finding that the strength of the cooperative interaction minimizing relative disparity decreases as the separation between stimuli increases. Our model is tested on three kinds of stereo images. In simulations on images with repetitive patterns, we demonstrate that our model could account for the human depth percepts that were previously explained by the second-order mechanism. In simulations on random dot stereograms and natural scene images, we demonstrate that false matches introduced by the disparity energy model can be reliably removed using our model. A comparison with the coarse-to-fine model shows that our model is able to compute the absolute disparity of small objects with larger relative disparity. We also relate our model to several physiological findings. The hypothesized neurons of the model are selective for absolute disparity and have facilitative extra receptive field. There are plenty of such neurons in the visual cortex. In conclusion, we think that stereopsis can be implemented by neural networks resembling MRF. |
WOS标题词 | Science & Technology ; Technology ; Life Sciences & Biomedicine |
关键词[WOS] | BINOCULAR DEPTH-PERCEPTION ; VISUAL-CORTEX ; BELIEF PROPAGATION ; DISPARITY ; NEURONS ; COMPUTATION ; MECHANISM ; MACAQUE ; V1 ; DISCRIMINATION |
收录类别 | SCI |
语种 | 英语 |
WOS研究方向 | Computer Science ; Neurosciences & Neurology |
WOS类目 | Computer Science, Artificial Intelligence ; Neurosciences |
WOS记录号 | WOS:000279109600009 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/2960 |
专题 | 多模态人工智能系统全国重点实验室_机器人视觉 |
作者单位 | Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Ming, Yansheng,Hu, Zhanyi. Modeling Stereopsis via Markov Random Field[J]. NEURAL COMPUTATION,2010,22(8):2161-2191. |
APA | Ming, Yansheng,&Hu, Zhanyi.(2010).Modeling Stereopsis via Markov Random Field.NEURAL COMPUTATION,22(8),2161-2191. |
MLA | Ming, Yansheng,et al."Modeling Stereopsis via Markov Random Field".NEURAL COMPUTATION 22.8(2010):2161-2191. |
条目包含的文件 | 条目无相关文件。 |
个性服务 |
推荐该条目 |
保存到收藏夹 |
查看访问统计 |
导出为Endnote文件 |
谷歌学术 |
谷歌学术中相似的文章 |
[Ming, Yansheng]的文章 |
[Hu, Zhanyi]的文章 |
百度学术 |
百度学术中相似的文章 |
[Ming, Yansheng]的文章 |
[Hu, Zhanyi]的文章 |
必应学术 |
必应学术中相似的文章 |
[Ming, Yansheng]的文章 |
[Hu, Zhanyi]的文章 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论