1 / 6

教你輕鬆寫 Hw2

教你輕鬆寫 Hw2. Find KEYPOINTS. (1) 經過 SIFT , keypoints 資訊存在 descriptor 裡 (2)Descriptor 存有 128 維度的資料 (2) 利用 object img 與 target img 的 descriptor 資訊去找建立 K-NN. How to RaNSAC. 對 object img 每個 keypoint 找到 K-NN Ex. 使用 3-NN. 可以看出,組合的方式有很多種 1->1 1->7 2->4 2->11 … 3->3 3->6 4->7 4->7.

nizana
Download Presentation

教你輕鬆寫 Hw2

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. 教你輕鬆寫Hw2

  2. Find KEYPOINTS (1)經過SIFT,keypoints資訊存在descriptor裡 (2)Descriptor存有128維度的資料 (2)利用object img與target img的descriptor資訊去找建立K-NN

  3. How to RaNSAC 對object img每個keypoint找到K-NN Ex. 使用3-NN 可以看出,組合的方式有很多種 1->1 1->7 2->4 2->11 … 3->3 3->6 4->7 4->7

  4. How to RaNSAC • 以下提供一種作法(非一定)(以4-NN為例): • (1)設定總共要跑幾個round: z,不同的round會挑不同4個objkeypoint • (2)在每個round有四個random number:n1,n2,n3,n4 • 分別代表四個objkeypoints的index • (3)分別存取四個objkeypoints的nearest neighbors(共4*4*4*4種可能) • (4)每次都要算Homography matrix,並計算inlier數

  5. Homography matrix (1)考慮找出的homography matrix的正確性(例如.inlier數量最多最正確) (2)將objimg的coordinate乘上該matrix (3)Warping到target img上面,並且框出邊框

  6. INPUT • 例如老虎,則input四張圖(c1~c4) • 找出最好的match • 使用最好的objimg畫出框來

More Related