2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1 (CVPR'06)
DOI: 10.1109/cvpr.2006.28
| View full text |Cite
|
Sign up to set email alerts
|
Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

1
20
1
1

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 30 publications
(23 citation statements)
references
References 20 publications
(37 reference statements)
1
20
1
1
Order By: Relevance
“…Có thể hiểu chất liệu của một đối tượng chính là thành phần bao phủ bên ngoài của đối tượng đó, là thành phần không thể thiếu được của mỗi đối tượng. Một số nhóm nghiên cứu theo hướng chất liệu như E. H. Adelson [11], L. B. Sharan [12], K. M. Henry [13]. Bản thân nhóm tác giả cũng đã có một số nghiên cứu về chất liệu như phát hiện chất liệu dựa vào đặc trưng bất biến địa phương [18], phát hiện chất liệu dựa vào hình học Fractal [19].…”
Section: Giới Thiệuunclassified
“…These edges were combined using an active contour method to identify a single glass region. This method was later extended by McHenry and Ponce [9] with a region-based approach along with the edge information to classify regions as transparent or not. They proposed two measures called the discrepancy measure and the affinity measure.…”
Section: Related Workmentioning
confidence: 99%
“…The situation is different for transparent objects. These features are characteristic of transparency and so they are used to segment unknown transparent objects from a single RGB image by McHenry et al [17], McHenry and Ponce [16]. This problem is also addressed by Kompella and Sturm [13] in a robotic context of transparent obstacles detection.…”
Section: Related Workmentioning
confidence: 99%
“…However, a more robust segmentation algorithm is required to use it in practice for this task. For example, the segmentation should be improved with using both the invalid depth cue proposed in this paper and complementary algorithms proposed by McHenry et al [17], McHenry and Ponce [16]. C. Grasping Fig.…”
Section: B Recognitionmentioning
confidence: 99%
“…A drawback of this approach is that it ignores potentially rich information in the interior of the object caused by the refraction of the background behind it. Others have eschewed analytic models and instead proposed methods based on learning from an examplar set [7,19,18,10,16,13]. Additional key distinctions between approaches include whether the sensor used is passive (e.g., CCD/CMOS camera) or active (e.g., timeof-flight sensor [12]) and whether a single view or multiple views are considered.…”
Section: Related Workmentioning
confidence: 99%