Transcript Table

Note: Lines that are metadata or do not contain timestamps are greyed out and do not have active links.

Results of Search: 176,291 lines — Showing 17221 - 17240.
Course Level Date Clip# Line Interlocutor Content
Oral Assessments Graduate 2019-08-16 4 87 S01 ∆like that∆
Oral Assessments Graduate 2019-08-16 4 88 S01 uh there are some corners you can (.) easily recognize
Oral Assessments Graduate 2019-08-16 4 89 S01 like here→
Oral Assessments Graduate 2019-08-16 4 90 UNK (0.8)
Oral Assessments Graduate 2019-08-16 4 91 S01 this one→ this one→ and a lot more to (0.7) show that
Oral Assessments Graduate 2019-08-16 4 92 S01 u:h ∆for computer vision∆→ u:h since its (.) computer aided
Oral Assessments Graduate 2019-08-16 4 93 S01 the picture is only recognized by the (.) computer↘
Oral Assessments Graduate 2019-08-16 4 94 S01 u:h if we see it like (.) e- oh ∆we know that∆ this is a corner
Oral Assessments Graduate 2019-08-16 4 95 S01 or something this is a feature point
Oral Assessments Graduate 2019-08-16 4 96 T01 sorry i just have a ques⌈tion so
Oral Assessments Graduate 2019-08-16 4 97 S01 ⌊yep
Oral Assessments Graduate 2019-08-16 4 98 T01 why would we ∇want to∇ detect corners
Oral Assessments Graduate 2019-08-16 4 99 S01 uh coz ∇they are the∇ most distinct features you have↘
Oral Assessments Graduate 2019-08-16 4 100 UNK (0.6)
Oral Assessments Graduate 2019-08-16 4 101 S01 inside the picture↘
Oral Assessments Graduate 2019-08-16 4 102 T01 so:: what does it help us do↘≈
Oral Assessments Graduate 2019-08-16 4 103 S01 +≈ u:h think if we can (.) uh
Oral Assessments Graduate 2019-08-16 4 104 S01 combine two images together→
Oral Assessments Graduate 2019-08-16 4 105 S01 if we have one picture and (0.8) the object's here→
Oral Assessments Graduate 2019-08-16 4 106 S01 and another one→ (0.5) the object's here↘