NMS(Non-Maximum Suppression)非极大值抑制
非极大值抑制
概述
在目标检测领域，我们经常用到非极大值抑制（NMS），NMS就是在局部范围内抑制不是极大值的目标，只保留极大值。
原理
在检测任务重，我们会得到一批具有置信度S的bbox列表B，首先根据置信度S对bbox进行排序，选择置信度最高的框M，从B中移除M并加入到最终结果D中，将剩余的框与B分别作交并比运算，IOU大于阈值Nt（通常设为0.3~0.5）的框从B中移除，一轮结束，再重新对B中的框按照置信度排序，选择下一个框加入D，并移除一些框，重复这个过程，直到B为空。
Python代码
def nms(dets, thresh):
x1 = dets[:, 0]
y1 = dets[:, 1]
x2 = dets[:, 2]
y2 = dets[:, 3]
scores = dets[:, 4]
areas = (x2 - x1 + 1) * (y2 - y1 + 1)
order = scores.argsort()[::-1]
keep = []
while order.size > 0:
i = order[0]
keep.append(i)
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
ovr = inter / (areas[i] + areas[order[1:]] - inter)
inds = np.where(ovr <= thresh)[0]
order = order[inds + 1]
return keepSoft-NMS
NMS的方法在遇到两个ground truth的目标框IOU很高时，会将具有较低置信度的框去掉(置信度改成0),soft-nms的提出就是为了解决这一问题，该方法对于非极大值的框置信度不置0，而是置为IOU的函数，置信度降低但不至于被删除。
IOU的函数有两种选择项：
（1）method=1时，线性函数
（1）method=2时，高斯函数
代码
def cpu_soft_nms(boxes,sigma=0.5, Nt=0.1, threshold=0.001, method=0):
N = boxes.shape[0]
for i in range(N):
maxscore = boxes[i, 4]
maxpos = i
tx1 = boxes[i, 0]
ty1 = boxes[i, 1]
tx2 = boxes[i, 2]
ty2 = boxes[i, 3]
ts = boxes[i, 4]
pos = i + 1
# get max box
while pos < N:
if maxscore < boxes[pos, 4]:
maxscore = boxes[pos, 4]
maxpos = pos
pos = pos + 1
# add max box as a detection
boxes[i, 0] = boxes[maxpos, 0]
boxes[i, 1] = boxes[maxpos, 1]
boxes[i, 2] = boxes[maxpos, 2]
boxes[i, 3] = boxes[maxpos, 3]
boxes[i, 4] = boxes[maxpos, 4]
# swap ith box with position of max box
boxes[maxpos, 0] = tx1
boxes[maxpos, 1] = ty1
boxes[maxpos, 2] = tx2
boxes[maxpos, 3] = ty2
boxes[maxpos, 4] = ts
tx1 = boxes[i, 0]
ty1 = boxes[i, 1]
tx2 = boxes[i, 2]
ty2 = boxes[i, 3]
ts = boxes[i, 4]
pos = i + 1
# NMS iterations, note that N changes if detection boxes fall below threshold
while pos < N:
x1 = boxes[pos, 0]
y1 = boxes[pos, 1]
x2 = boxes[pos, 2]
y2 = boxes[pos, 3]
s = boxes[pos, 4]
area = (x2 - x1 + 1) * (y2 - y1 + 1)
iw = (min(tx2, x2) - max(tx1, x1) + 1)
if iw > 0:
ih = (min(ty2, y2) - max(ty1, y1) + 1)
if ih > 0:
ua = float((tx2 - tx1 + 1) * (ty2 - ty1 + 1) + area - iw * ih)
ov = iw * ih / ua # iou between max box and detection box
if method == 1: # linear
if ov > Nt:
weight = 1 - ov
else:
weight = 1
elif method == 2: # gaussian
weight = np.exp(-(ov * ov) / sigma)
else: # original NMS
if ov > Nt:
weight = 0
else:
weight = 1
boxes[pos, 4] = weight * boxes[pos, 4]
# if box score falls below threshold, discard the box by swapping with last box
# update N
if boxes[pos, 4] < threshold:
boxes[pos, 0] = boxes[N - 1, 0]
boxes[pos, 1] = boxes[N - 1, 1]
boxes[pos, 2] = boxes[N - 1, 2]
boxes[pos, 3] = boxes[N - 1, 3]
boxes[pos, 4] = boxes[N - 1, 4]
N = N - 1
pos = pos - 1
pos = pos + 1
keep = [i for i in range(N)]
return keep参考
参考博客 https://blog.csdn.net/Quincuntial/article/details/78815187 代码，可进行实验观察
参考 https://www.cnblogs.com/makefile/p/nms.html