Please enable JavaScript.
Coggle requires JavaScript to display documents.
Object Detection (Region Proposal (R-CNN (Propose Regions. Classify…
Object Detection
Region Proposal
-
Fast R-CNN
Propose Regions. Use convolution implementation of sliding windows to classify all the proposed regions at once.
-
-
Non-max Suppresion
- Discard all boxes with Probability <= 0.6
- Pick Box with largest Probability
- Discard any remaining box with IoU >= 0.5 with the box output from previous step
-
-
Anchor Boxes
- Used to handle Overlapping objects
- Each Object in training image is assigned to grid cell that contains object's midpoint and anchor box for the grid cell with highest IoU
YOLO
- Divide image in a n x n grid
- Output a vector [pc,bx,by,bw,bh,c1,c2...cn] for each grid