# Concepts

Name Description $y$$y$
Object Classification At most one object $y=\left(\begin{array}{c}{c}_{1}\\ {c}_{2}\\ {c}_{3}\end{array}\right)$$y = \begin{pmatrix} c_1 \\ c_2 \\ c_3 \end{pmatrix}$
Object Localization At most one object $y=\left(\begin{array}{c}{p}_{c}\\ {b}_{x}\\ {b}_{y}\\ {b}_{w}\\ {b}_{h}\\ {c}_{1}\\ {c}_{2}\\ {c}_{3}\end{array}\right)$$y = \begin{pmatrix} p_{c} \\ b_{x} \\ b_{y} \\ b_{w} \\ b_{h} \\ c_1 \\ c_2 \\ c_3 \end{pmatrix}$
Landmark Detection At most one object $y=\left(\begin{array}{c}{p}_{c}\\ {l}_{1x}\\ {l}_{1y}\\ ⋮\\ {l}_{64x}\\ {l}_{64y}\end{array}\right)$$y = \begin{pmatrix} p_{c} \\ l_{1x} \\ l_{1y} \\ \vdots \\ l_{64x} \\ l_{64y} \end{pmatrix}$
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 ${p}_{c}$$p_c$
While remaining boxes exists:
1. Pick the box with the largest ${p}_{c}$$p_c$ , output that as a prediction
2. Discard remaining boxes with IoU $\ge 0.5$$\ge 0.5$ with the box output in previous step

# Region Proposal

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