150 lines
6.7 KiB
Python
150 lines
6.7 KiB
Python
import math
|
||
|
||
import numpy as np
|
||
import torch
|
||
import time
|
||
|
||
|
||
def dmpr_yolo( yolo_det, dmpr_det,pars):
|
||
#if len(yolo_det)==0 or len(dmpr_det)==0:
|
||
|
||
#print('line11:\n',yolo_det, dmpr_det,pars)
|
||
time1=time.time()
|
||
if len(yolo_det)==0:
|
||
return yolo_det,' No yolo detections'
|
||
|
||
img_shape = (pars['imgSize'][1],pars['imgSize'][0])
|
||
cls = pars['carCls']; scaleRatio = pars['scaleRatio']
|
||
illParkCls = pars['illCls'];border = pars['border']
|
||
|
||
yolo_det = np.array(yolo_det)
|
||
yolo_det_0 = yolo_det.copy()
|
||
|
||
|
||
|
||
|
||
#print('-'*10,'line17：',yolo_det_0)
|
||
|
||
# 过滤在图像边界的box(防止出现类似一小半车辆的情况)
|
||
|
||
x_c = (yolo_det[:, 0] + yolo_det[:, 2]) / 2
|
||
y_c = (yolo_det[:, 1] + yolo_det[:, 3]) / 2
|
||
tmp = (x_c >= border) & (x_c <= (img_shape[1] - border)) & (y_c >= border) & (y_c <= (img_shape[0] - border))
|
||
yolo_det = yolo_det[tmp]
|
||
|
||
|
||
# 创建yolo_det_clone内容为x1, y1, x2, y2, conf, cls, unlabel (unlabel代表该类是否需要忽略，0：不忽略 其他：忽略)
|
||
yolo_det_clone = yolo_det.copy()
|
||
tmp_0_tensor = np.zeros([len(yolo_det), 1])
|
||
yolo_det_clone = np.concatenate([yolo_det_clone, tmp_0_tensor], axis=1)
|
||
|
||
# cls为需要计算的类别
|
||
yolo_det = yolo_det[yolo_det[:, -1] == cls]
|
||
|
||
# new_yolo_det为膨胀后数据，内容为x1, y1, x2, y2, flag (flag代表膨胀后车位内是否包含角点 且 与角点方向差值小于90度, 其值为第一个满足条件的角点索引)
|
||
new_yolo_det = np.zeros([len(yolo_det), 7])
|
||
|
||
# yolo框膨胀，长的边两边各膨胀0.4倍总长，短的边两边各膨胀0.2倍总长
|
||
x_length = yolo_det[:, 2] - yolo_det[:, 0] #x2-x1
|
||
y_length = yolo_det[:, 3] - yolo_det[:, 1] #y2-y1
|
||
|
||
# x, y哪个方向差值大哪个方向膨胀的多
|
||
x_dilate_coefficient = ((x_length > y_length) + 1)*scaleRatio
|
||
y_dilate_coefficient = ((~(x_length > y_length)) + 1)*scaleRatio
|
||
|
||
# 原始框中心点x_c, y_c
|
||
new_yolo_det[:, 5] = (yolo_det[:, 0] + yolo_det[:, 2]) / 2
|
||
new_yolo_det[:, 6] = (yolo_det[:, 1] + yolo_det[:, 3]) / 2
|
||
|
||
# 膨胀
|
||
new_yolo_det[:, 0] = np.round(yolo_det[:, 0] - x_dilate_coefficient * x_length).clip(0, img_shape[1]) #x1 膨胀
|
||
new_yolo_det[:, 1] = np.round(yolo_det[:, 1] - y_dilate_coefficient * y_length).clip(0, img_shape[0]) #y1 膨胀
|
||
new_yolo_det[:, 2] = np.round(yolo_det[:, 2] + x_dilate_coefficient * x_length).clip(0, img_shape[1]) #x2 膨胀
|
||
new_yolo_det[:, 3] = np.round(yolo_det[:, 3] + y_dilate_coefficient * y_length).clip(0, img_shape[0]) #y2 膨胀
|
||
|
||
m, n = new_yolo_det.size, dmpr_det.size
|
||
|
||
if not m or not n:
|
||
#print('##line47 original yolo_det_clone:',yolo_det_clone)
|
||
yolo_det_clone[np.logical_and( yolo_det_clone[:,-1]==0,yolo_det_clone[:,-2]==cls),-2] = illParkCls
|
||
|
||
#yolo_det_clone[yolo_det_clone[:, -1] == 0 & yolo_det_clone[:, -2==cls] , -2] = illParkCls
|
||
return yolo_det_clone[:,0:6], ' no cars or T/L corners'
|
||
|
||
new_yolo = new_yolo_det[:, np.newaxis, :].repeat(dmpr_det.shape[0], 1) # 扩展为 (m , n, 5)
|
||
dmpr_det = dmpr_det[np.newaxis, ...].repeat(new_yolo_det.shape[0], 0)
|
||
yolo_dmpr = np.concatenate((new_yolo, dmpr_det), axis=2) # (m, n, 10)
|
||
|
||
x_p, y_p = yolo_dmpr[..., 8], yolo_dmpr[..., 9]
|
||
x1, y1, x2, y2 = yolo_dmpr[..., 0], yolo_dmpr[..., 1], yolo_dmpr[..., 2], yolo_dmpr[..., 3]
|
||
x_c, y_c = yolo_dmpr[..., 5], yolo_dmpr[..., 6]
|
||
|
||
direction1 = np.arctan2(y_c - y_p, x_c - x_p) / math.pi * 180
|
||
direction2 = yolo_dmpr[..., 10] / math.pi * 180
|
||
direction3 = direction2 + 90 # L形角点另外一个方向
|
||
direction3[direction3 > 180] -= 360
|
||
ang_diff = direction1 - direction2
|
||
ang_diff2 = direction1 - direction3
|
||
|
||
# 判断膨胀后yolo框包含角点关系 && 包含角点的时候计算水平框中心点与角点的角度关系
|
||
# direction ∈ （-180， 180） 若角差大于180，需算补角
|
||
# T形角点比较一个方向，L形角点比较两个方向
|
||
mask = (x_p >= x1) & (x_p <= x2) & (y_p >= y1) & (y_p <= y2) & \
|
||
(((yolo_dmpr[..., 11] <= 0.5) & # T形角点情况
|
||
(((ang_diff >= -90) & (ang_diff <= 90)) | ((ang_diff > 180) & ((360 - ang_diff) <= 90)) |
|
||
(((ang_diff) < -180) & ((360 + ang_diff) <= 90)))) |
|
||
((yolo_dmpr[..., 11] > 0.5) & # L形角点情况
|
||
(((ang_diff >= -90) & (ang_diff <= 90)) | ((ang_diff > 180) & ((360 - ang_diff) <= 90)) |
|
||
(((ang_diff) < -180) & ((360 + ang_diff) <= 90))) &
|
||
(((ang_diff2 >= -90) & (ang_diff2 <= 90)) | ((ang_diff2 > 180) & ((360 - ang_diff2) <= 90)) |
|
||
(((ang_diff2) < -180) & ((360 + ang_diff2) <= 90)))))
|
||
|
||
res = np.sum(mask, axis=1)
|
||
|
||
yolo_det_clone[yolo_det_clone[:, -2] == cls, -1] = res
|
||
#print('##line69 original yolo_det_clone:',yolo_det_clone)
|
||
#yolo_det_clone[yolo_det_clone[:, -1] == 0, -2] = illParkCls
|
||
|
||
#print('-'*20,'--line78',yolo_det_clone)
|
||
yolo_det_clone[ np.logical_and( yolo_det_clone[:,-1]==0,yolo_det_clone[:,-2]==cls) ,-2 ] = illParkCls
|
||
#print('-'*20,'--line80:',yolo_det_clone)
|
||
yolo_det_clone = yolo_det_clone[:,0:6]
|
||
time2=time.time()
|
||
|
||
return np.array(yolo_det_clone), 'dmpr_yolo:%.1f'%( (time2-time1)*1000 )
|
||
def stdc_yolo(stdc_det, yolo_det,pars):
|
||
|
||
is_car = yolo_det[:, -1] == pars['carCls'] # 获取最后一列，判断是否等于0
|
||
car = yolo_det[is_car] # 筛选出最后一列等于0的行
|
||
no_car = yolo_det[~is_car] # 筛选出最后一列不等于0的行
|
||
|
||
im = np.uint8(stdc_det)
|
||
x_c = ((car[:, 0] + car[:, 2]) // 2).astype(int)
|
||
y_c = ((car[:, 1] + car[:, 3]) // 2).astype(int)
|
||
car_filted = car[im[y_c, x_c] == 0]
|
||
#yolo_filted = yolo_det
|
||
|
||
yolo_filted = np.concatenate((car_filted, no_car), axis=0)
|
||
return yolo_filted
|
||
|
||
def dmpr_yolo_stdc(predsList,pars):
|
||
if len(predsList)==2:
|
||
yolo_det, dmpr_det = predsList[0:2]
|
||
else:
|
||
yolo_det, dmpr_det,stdc_det = predsList[0:3]
|
||
if len(yolo_det)==0:
|
||
return yolo_det,' No yolo detections'
|
||
if isinstance(yolo_det,list):
|
||
yolo_det = np.array(yolo_det)
|
||
if len(predsList)>2:
|
||
yolo_det = stdc_yolo(stdc_det, yolo_det,pars)
|
||
|
||
rets = dmpr_yolo(yolo_det, dmpr_det,pars)
|
||
for i,ret in enumerate(rets[0]):
|
||
#print(ret,'\n ',rets,pars['classReindex'])
|
||
ret[5] = pars['classReindex'][ret[5]]
|
||
#rets[i][5] = pars['classReindex'][ret[5]]
|
||
|
||
|
||
return rets
|