深度学习学习日记_图像处理_NMS

了解：http://www.360doc.com/content/19/1107/16/67231541_871698395.shtml

1、为什么需要置信区间：误差范围（区间）在统计概率中就叫做置信区间；简单来说，置信区间就是误差范围。举例：假设一个同学考了两次才过英语四级，第一次53分，第二次63分。他两次考试的成绩可以不叫作进步，可以称为在某个正确值之间的测量误差范围之内。

2、置信区间和置信水平：在抽样调查中，样本能在多大程度上代表总体？其实这个问题的本质就是想知道数据统计的误差范围是多少，在统计中，其实很难根据一些样本去得到“真正”正确的值（样本得到的只能是估计值，不会是真值），但是可以给出一个区间，一个误差范围。

置信区间：误差范围[a,b]
置信水平 Y%：P(a<均值<b) = Y%

我们选择这个置信区间，目的是为了为了让“a和b之间包含总体平均值”这一结果具有特定的概率，这个概率就是置信水平

假设我设定的置信水平是95%，也就是说如果我做100次抽样，会有95个置信区间包含了总体平均值。

IoU: IoU 的全称为交并比（Intersection over Union）, IoU 计算的是 “预测的边框” 和 “真实的边框” 的交集和并集的比值即

(R∩G)/(R∪G)

计算IoU：包含两个部分

（1）交集的计算：

总之，可以把上述六种情况分为三种情况：相交、内含、不相交，计算方式如下：

#（1）将所有框的得分排序，选中最高分及其对应的框 
#（2）遍历其余的框，如果和当前最高分框的重叠面积(IOU)大于一定阈值，我们就将框删除。（为什么要删除，是因为超过设定阈值，认为两个框的里面的物体属于同一个类别，比如都属于狗这个类别。我们只需要留下一个类别的可能性框图即可。）
#（3）从未处理的框中继续选一个得分最高的，重复上述过程。


#!/usr/bin/env python
# _*_ coding: utf-8 _*_

import cv2
import numpy as np

"""
    Non-max Suppression Algorithm

    @param list  Object candidate bounding boxes
    @param list  Confidence score of bounding boxes
    @param float IoU threshold

    @return Rest boxes after nms operation
"""
def nms(bounding_boxes, confidence_score, threshold):
    # If no bounding boxes, return empty list
    if len(bounding_boxes) == 0:
        return [], []
    # Bounding boxes
    boxes = np.array(bounding_boxes)
    # coordinates of bounding boxes
    start_x = boxes[:, 0]
    start_y = boxes[:, 1]
    end_x = boxes[:, 2]
    end_y = boxes[:, 3]

    # Confidence scores of bounding boxes
    score = np.array(confidence_score)
    # Picked bounding boxes
    picked_boxes = []
    picked_score = []

    # Compute areas of bounding boxes
    areas = (end_x - start_x + 1) * (end_y - start_y + 1)
    
    # Sort by confidence score of bounding boxes
    order = np.argsort(score)

    # Iterate bounding boxes
    while order.size > 0:
        # The index of largest confidence score
        index = order[-1]

        # Pick the bounding box with largest confidence score
        picked_boxes.append(bounding_boxes[index])
        picked_score.append(confidence_score[index])

        # Compute ordinates of intersection-over-union(IOU)
        x1 = np.maximum(start_x[index], start_x[order[:-1]])
        x2 = np.minimum(end_x[index], end_x[order[:-1]])
        y1 = np.maximum(start_y[index], start_y[order[:-1]])
        y2 = np.minimum(end_y[index], end_y[order[:-1]])

        # Compute areas of intersection-over-union
        w = np.maximum(0.0, x2 - x1 + 1)
        h = np.maximum(0.0, y2 - y1 + 1)
        intersection = w * h

        # Compute the ratio between intersection and union
        ratio = intersection / (areas[index] + areas[order[:-1]] - intersection)

        left = np.where(ratio < threshold)
        order = order[left]

    return picked_boxes, picked_score


# Image name
image_name = 'A.jpg'

# Bounding boxes
bounding_boxes = [(187, 82, 337, 317), (150, 67, 305, 282), (246, 121, 368, 304)]
confidence_score = [0.9, 0.75, 0.8]

# Read image
image = cv2.imread(image_name)

# Copy image as original
org = image.copy()

# Draw parameters
font = cv2.FONT_HERSHEY_SIMPLEX
font_scale = 1
thickness = 2

# IoU threshold
threshold = 0.4

# Draw bounding boxes and confidence score
for (start_x, start_y, end_x, end_y), confidence in zip(bounding_boxes, confidence_score):
    (w, h), baseline = cv2.getTextSize(str(confidence), font, font_scale, thickness)
    cv2.rectangle(org, (start_x, start_y - (2 * baseline + 5)), (start_x + w, start_y), (0, 255, 255), -1)
    cv2.rectangle(org, (start_x, start_y), (end_x, end_y), (0, 255, 255), 2)
    cv2.putText(org, str(confidence), (start_x, start_y), font, font_scale, (0, 0, 0), thickness)

# Run non-max suppression algorithm
picked_boxes, picked_score = nms(bounding_boxes, confidence_score, threshold)

# Draw bounding boxes and confidence score after non-maximum supression
for (start_x, start_y, end_x, end_y), confidence in zip(picked_boxes, picked_score):
    (w, h), baseline = cv2.getTextSize(str(confidence), font, font_scale, thickness)
    cv2.rectangle(image, (start_x, start_y - (2 * baseline + 5)), (start_x + w, start_y), (0, 255, 255), -1)
    cv2.rectangle(image, (start_x, start_y), (end_x, end_y), (0, 255, 255), 2)
    cv2.putText(image, str(confidence), (start_x, start_y), font, font_scale, (0, 0, 0), thickness)

# Show image
cv2.imshow('Original', org)
cv2.imshow('NMS', image)
cv2.waitKey(0)