输入:左上角和右下角坐标
输出:留下的boxes的索引
import numpy as np
import cv2
import matplotlib.pyplot as plt
import random
def py_cpu_nms(dets, thresh):
"""Pure Python NMS baseline."""
x1 = dets[:, 0]
y1 = dets[:, 1]
x2 = dets[:, 2]
y2 = dets[:, 3]
scores = dets[:, 4]
areas = (x2 - x1 + 1) * (y2 - y1 + 1)
#从大到小排列,取index
order = scores.argsort()[::-1] #逆序排序
#keep为最后保留的边框
keep = []
while order.size > 0:
#order[0]是当前分数最大的窗口,之前没有被过滤掉,肯定是要保留的
i = order[0]
keep.append(i)
#计算窗口i与其他所以窗口的交叠部分的面积,矩阵计算
xx1 = np.maximum(x1[i], x1[order[1:]])
yy1 = np.maximum(y1[i], y1[order[1:]])
xx2 = np.minimum(x2[i], x2[order[1:]])
yy2 = np.minimum(y2[i], y2[order[1:]])
w = np.maximum(0.0, xx2 - xx1 + 1)
h = np.maximum(0.0, yy2 - yy1 + 1)
inter = w * h
#交/并得到iou值
ovr = inter / (areas[i] + areas[order[1:]] - inter)
#ind为所有与窗口i的iou值小于threshold值的窗口的index,其他窗口此次都被窗口i吸收
inds = np.where(ovr <= thresh)[0]
#下一次计算前要把窗口i去除,所有i对应的在order里的位置是0,所以剩下的加1
order = order[inds + 1]
return keep
boxes = np.array([[3,6,9,11,0.9],[6,3,8,7,0.6],[3,7,10,12,0.7],[1,4,13,7,0.2]])
y = py_cpu_nms(boxes, 0.3)
img = cv2.imread('model.jpg')
color =['red','blue','green','black']
fig, ax = plt.subplots(figsize=(12, 12))
ax.imshow(img, aspect='equal')
for box in boxes[y]:
ax.add_patch(
plt.Rectangle((box[0], box[1]),
box[2] - box[0],
box[3] - box[1], fill=False,
edgecolor=random.choice(color), linewidth=1)
)
plt.axis('off')
plt.show()
原始框:
经NMS后的框