Object Detection

版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/phoenix198425/article/details/79951924


Name Description y
Object Classification At most one object y=(c1c2c3)
Object Localization At most one object y=(pcbxbybwbhc1c2c3)
Landmark Detection At most one object y=(pcl1xl1yl64xl64y)
Object Detection Multiple objects

Sliding Windows Object Detection Algorithm

  1. Input: closely cropped images by sliding window
  2. Crop images with larger window


Complex computation

Convolutional Implement of Sliding Windows

Turn Full Connection (FC) into convolutional layer

Bounding Box Detection

Yolo (You only look once) Algorithm
IoU (Intersection over Union)

Non-max Supression (NMS)

Discard all boxes with low pc
While remaining boxes exists:
1. Pick the box with the largest pc , output that as a prediction
2. Discard remaining boxes with IoU 0.5 with the box output in previous step

Region Proposal

R-RNN: Segmentation Algorithm
Fast R-RNN
Faster R-RNN