Object Detection 目标检测 学习笔记

Object Detection

Object Detection

Four steps for Computer Vision Tasks :

Classification , Classification + Localization , Object Detection , Instance Segmentation

one-stage

two-stage

bbox : Bounding box 包含物体的最小矩形 （ x , y , w , h ）

​ x , y 默认为左上角，可自定义

​ w , h 宽和高

IoU : Intersection over Union ---- Intersection / Union

NMS : Non-Maximum Suppression 非极大值抑制（ search for local maximum ）

sliding windows :

Classification && Localization

R-CNN ( Region Based CNNs )

1. Input images

2. Extract region proposals ( ~2k ) 提取 Selective Search Algorithm

3. compute CNN features

4. classify regions ( SVM )

Selective Search Algorithm ( Based on Greedy Principle )

combine smaller segmented regions to generate region proposal 分割区域

input : an image

output : generate region proposals

advantage over random proposal generation 产生 :

process :

1. generate initial sub-segmentation of input image.

2. Combine the most similar two ( What would happen if two is changed into other number ? ) bounding boxes into larger ones recursively 递归地 , until there is only one image left .

   color similarity , texture similarity , region size , etc.

3. Use these larger boxes to generate region proposals for object detection.

CNN

model ----- AlexNet model
stride of 4 四步 :
max pooling :
input : ( 227 , 227 , 3 )
softmax layer 层 :
SVM ( Support Vector Machine ) :
bounding box regressor 回归量 :