对视频的帧进行分割得到向量，举例说明
p = [1,1,0,0,1,1,0,0,0,1,2,2,2,3,3,3,4,4,5,5] y = [1,1,1,1,0,0,0,2,2,2,2,2,3,3,3,4,4,5,5,5]
其中，p为预测帧的分类，y为真实数据帧的分类。
计算p和y的IOU，也就是一维向量的IOU。首先明白IOU的概念，IOU的计算公式如下。
看如下简图，
很容易看出交集与并集的计算公式如下，
intersection = minimum(p_end, y_end) - maximum(p_start, y_start) union = maximum(p_end, y_end) - minimum(p_start[j], y_start)
因此，可以求出IOU.
完整代码如下。
import numpy as np
p = [1,1,0,0,1,1,0,0,0,1,2,2,2,3,3,3,4,4,5,5]
y = [1,1,1,1,0,0,0,2,2,2,2,2,3,3,3,4,4,5,5,5]
def get_labels_start_end_time(frame_wise_labels, bg_class=["background"]):
labels = []
starts = []
ends = []
last_label = frame_wise_labels[0]
if frame_wise_labels[0] not in bg_class:
labels.append(frame_wise_labels[0])
#如果标签第一帧不是"background"，labels[0]=第一帧的动作
starts.append(0)
#starts[0]=0
for i in range(len(frame_wise_labels)):
if frame_wise_labels[i] != last_label:
if frame_wise_labels[i] not in bg_class:
labels.append(frame_wise_labels[i])
starts.append(i)
if last_label not in bg_class:
ends.append(i)
last_label = frame_wise_labels[i]
#labels是动作标签
#starts是动作开始的位置
#end是动作结束的位置
if last_label not in bg_class:
ends.append(i + 1)
return labels, starts, ends
p_label, p_start,p_end = get_labels_start_end_time(p, bg_class=["background"])
y_label, y_start,y_end = get_labels_start_end_time(y, bg_class=["background"])
tp = 0
fp = 0
hits = np.zeros(len(y_label))
overlap = 0.1
for j in range(len(p_label)):
min_end_py = np.minimum(p_end[j], y_end)
max_start_py = np.maximum(p_start[j], y_start)
max_end_py = np.maximum(p_end[j], y_end)
min_start_py = np.minimum(p_start[j], y_start)
intersection = np.minimum(p_end[j], y_end) - np.maximum(p_start[j], y_start) # 交叉
union = np.maximum(p_end[j], y_end) - np.minimum(p_start[j], y_start)
IoU = (1.0 * intersection / union) * ([p_label[j] == y_label[x] for x in range(len(y_label))])
