227 lines
9.1 KiB
Python
227 lines
9.1 KiB
Python
|
import numpy as np
|
|||
|
|
import time,cv2
|
|||
|
|
def ms(t1,t0):
|
|||
|
|
return (t1-t0)*1000.0
|
|||
|
|
def center_coordinate(boundbxs):
|
|||
|
|
'''
|
|||
|
|
输入：两个对角坐标xyxy
|
|||
|
|
输出：矩形框重点坐标xy
|
|||
|
|
'''
|
|||
|
|
boundbxs_x1=boundbxs[0]
|
|||
|
|
boundbxs_y1=boundbxs[1]
|
|||
|
|
boundbxs_x2=boundbxs[2]
|
|||
|
|
boundbxs_y2=boundbxs[3]
|
|||
|
|
center_x=0.5*(boundbxs_x1+boundbxs_x2)
|
|||
|
|
center_y=0.5*(boundbxs_y1+boundbxs_y2)
|
|||
|
|
return center_x,center_y
|
|||
|
|
|
|||
|
|
def fourcorner_coordinate(boundbxs):
|
|||
|
|
'''
|
|||
|
|
输入：两个对角坐标xyxy
|
|||
|
|
输出：矩形框四个角点坐标，以contours顺序。
|
|||
|
|
'''
|
|||
|
|
boundbxs_x1=boundbxs[0]
|
|||
|
|
boundbxs_y1=boundbxs[1]
|
|||
|
|
boundbxs_x2=boundbxs[2]
|
|||
|
|
boundbxs_y2=boundbxs[3]
|
|||
|
|
wid=boundbxs_x2-boundbxs_x1
|
|||
|
|
hei=boundbxs_y2-boundbxs_y1
|
|||
|
|
boundbxs_x3=boundbxs_x1+wid
|
|||
|
|
boundbxs_y3=boundbxs_y1
|
|||
|
|
boundbxs_x4=boundbxs_x1
|
|||
|
|
boundbxs_y4 = boundbxs_y1+hei
|
|||
|
|
contours_rec=[[boundbxs_x1,boundbxs_y1],[boundbxs_x3,boundbxs_y3],[boundbxs_x2,boundbxs_y2],[boundbxs_x4,boundbxs_y4]]
|
|||
|
|
return contours_rec
|
|||
|
|
|
|||
|
|
def remove_simivalue(list1,list2):
|
|||
|
|
'''
|
|||
|
|
将list1中属于list2的元素都删除。
|
|||
|
|
输入：两个嵌套列表
|
|||
|
|
返回：嵌套列表
|
|||
|
|
'''
|
|||
|
|
list33=list1.copy()
|
|||
|
|
for i in range(len(list1)):
|
|||
|
|
for j in range(len(list2)):
|
|||
|
|
if list2[j] == list1[i]:
|
|||
|
|
# list33.pop(list1[i])
|
|||
|
|
list33.remove(list1[i])
|
|||
|
|
return list33
|
|||
|
|
|
|||
|
|
def remove_sameeleme_inalist(list3):
|
|||
|
|
'''
|
|||
|
|
将list3中重复嵌套列表元素删除。
|
|||
|
|
输入：嵌套列表
|
|||
|
|
返回：嵌套列表
|
|||
|
|
'''
|
|||
|
|
list3=list3
|
|||
|
|
list4=[]
|
|||
|
|
list4.append(list3[0])
|
|||
|
|
for dict in list3:
|
|||
|
|
k=0
|
|||
|
|
for item in list4:
|
|||
|
|
if dict!=item:
|
|||
|
|
k=k+1
|
|||
|
|
else:
|
|||
|
|
break
|
|||
|
|
if k==len(list4):
|
|||
|
|
list4.append(dict)
|
|||
|
|
return list4
|
|||
|
|
|
|||
|
|
def order_points(pts):
|
|||
|
|
''' sort rectangle points by clockwise '''
|
|||
|
|
sort_x = pts[np.argsort(pts[:, 0]), :]
|
|||
|
|
|
|||
|
|
Left = sort_x[:2, :]
|
|||
|
|
Right = sort_x[2:, :]
|
|||
|
|
# Left sort
|
|||
|
|
Left = Left[np.argsort(Left[:, 1])[::-1], :]
|
|||
|
|
# Right sort
|
|||
|
|
Right = Right[np.argsort(Right[:, 1]), :]
|
|||
|
|
return np.concatenate((Left, Right), axis=0)
|
|||
|
|
|
|||
|
|
def mixDrowing_water_postprocess(preds,_mask_cv,pars ):
|
|||
|
|
'''考虑船上人过滤'''
|
|||
|
|
'''输入：落水人员的结果（类别+坐标）、原图、mask图像
|
|||
|
|
过程：获得mask的轮廓，判断人员是否在轮廓内。
|
|||
|
|
在，则保留且绘制；不在，舍弃。
|
|||
|
|
返回：最终绘制的结果图、最终落水人员（坐标、类别、置信度），
|
|||
|
|
'''
|
|||
|
|
'''1、最大分割水域作为判断依据'''
|
|||
|
|
#zoom_factor=4 #缩小因子设置为4，考虑到numpy中分别遍历xy进行缩放耗时大。
|
|||
|
|
original_height = _mask_cv.shape[0]
|
|||
|
|
original_width=_mask_cv.shape[1]
|
|||
|
|
|
|||
|
|
zoom_factor = original_width/480.0
|
|||
|
|
|
|||
|
|
zoom_height=int(original_height/zoom_factor)
|
|||
|
|
zoom_width=int(original_width/zoom_factor)
|
|||
|
|
|
|||
|
|
_mask_cv = cv2.resize(_mask_cv, (zoom_width,zoom_height)) #缩小原图,宽在前，高在后
|
|||
|
|
t4 = time.time()
|
|||
|
|
img_gray = cv2.cvtColor(_mask_cv, cv2.COLOR_BGR2GRAY) if len(_mask_cv.shape)==3 else _mask_cv #
|
|||
|
|
t5 = time.time()
|
|||
|
|
contours, thresh = cv2.threshold(img_gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
|
|||
|
|
|
|||
|
|
# 寻找轮廓(多边界)
|
|||
|
|
contours, hierarchy = cv2.findContours(thresh, cv2.RETR_LIST, 2)
|
|||
|
|
contour_info = []
|
|||
|
|
for c in contours:
|
|||
|
|
contour_info.append((
|
|||
|
|
c,
|
|||
|
|
cv2.isContourConvex(c),
|
|||
|
|
cv2.contourArea(c),
|
|||
|
|
))
|
|||
|
|
contour_info = sorted(contour_info, key=lambda c: c[2], reverse=True)
|
|||
|
|
t6 = time.time()
|
|||
|
|
|
|||
|
|
'''新增模块：：如果水域为空，则返回原图、无落水人员等。'''
|
|||
|
|
if contour_info==[]:
|
|||
|
|
# final_img=_img_cv
|
|||
|
|
final_head_person_filterwater=[]
|
|||
|
|
timeInfos=0
|
|||
|
|
# return final_img, final_head_person_filterwater
|
|||
|
|
return final_head_person_filterwater,timeInfos
|
|||
|
|
else:
|
|||
|
|
max_contour = contour_info[0]
|
|||
|
|
max_contour=max_contour[0]*zoom_factor# contours恢复原图尺寸
|
|||
|
|
max_contour = max_contour.astype(np.int32)
|
|||
|
|
#print(max_contour)
|
|||
|
|
t7 = time.time()
|
|||
|
|
|
|||
|
|
|
|||
|
|
'''2.1、preds中head+person取出，boat取出。'''
|
|||
|
|
init_head_person=[]
|
|||
|
|
init_boat = []
|
|||
|
|
for i in range(len(preds)):
|
|||
|
|
if preds[i][5]==0 or preds[i][5]==1:
|
|||
|
|
init_head_person.append(preds[i])
|
|||
|
|
else:
|
|||
|
|
init_boat.append(preds[i])
|
|||
|
|
t8 = time.time()
|
|||
|
|
|
|||
|
|
'''新增模块：2.2、preds中head+person取出，过滤掉head与person中指向同一人的部分，保留同一人的person标签。'''
|
|||
|
|
init_head=[]
|
|||
|
|
init_person=[]
|
|||
|
|
#head与person标签分开
|
|||
|
|
for i in range(len(init_head_person)):
|
|||
|
|
if init_head_person[i][5]==0:
|
|||
|
|
init_head.append(init_head_person[i])
|
|||
|
|
else:
|
|||
|
|
init_person.append(init_head_person[i])
|
|||
|
|
# person的框形成contours
|
|||
|
|
person_contour=[]
|
|||
|
|
for i in range(len(init_person)):
|
|||
|
|
boundbxs_temp=[init_person[i][0],init_person[i][1],init_person[i][2],init_person[i][3]]
|
|||
|
|
contour_temp_person=fourcorner_coordinate(boundbxs_temp) #得到person预测框的顺序contour
|
|||
|
|
contour_temp_person=np.array(contour_temp_person)
|
|||
|
|
contour_temp_person=np.float32(contour_temp_person)
|
|||
|
|
person_contour.append(np.array(contour_temp_person))
|
|||
|
|
# head是否在person的contours内，在说明是同一人，过滤掉。
|
|||
|
|
list_head=[]
|
|||
|
|
for i in range(len(init_head)):
|
|||
|
|
for j in range(len(person_contour)):
|
|||
|
|
center_x, center_y=center_coordinate(init_head[i])
|
|||
|
|
flag = cv2.pointPolygonTest(person_contour[j], (center_x, center_y), False) #若为False，会找点是否在内，外，或轮廓上(相应返回+1, -1, 0)。
|
|||
|
|
if flag==1:
|
|||
|
|
pass
|
|||
|
|
else:
|
|||
|
|
list_head.append(init_head[i])
|
|||
|
|
# person和最终head合并起来
|
|||
|
|
init_head_person_temp=init_person+list_head
|
|||
|
|
|
|||
|
|
'''3、preds中head+person，通过1中水域过滤'''
|
|||
|
|
init_head_person_filterwater=init_head_person_temp
|
|||
|
|
final_head_person_filterwater=[]
|
|||
|
|
for i in range(len(init_head_person_filterwater)):
|
|||
|
|
center_x, center_y=center_coordinate(init_head_person_filterwater[i])
|
|||
|
|
#print('#'*20,'line176:',len(max_contour),np.array(max_contour).shape,(center_x, center_y))
|
|||
|
|
flag = cv2.pointPolygonTest(max_contour, (int(center_x), int(center_y)), False) #若为False，会找点是否在内，外，或轮廓上(相应返回+1, -1, 0)。
|
|||
|
|
if flag==1:
|
|||
|
|
final_head_person_filterwater.append(init_head_person_filterwater[i])
|
|||
|
|
else:
|
|||
|
|
pass
|
|||
|
|
t9 = time.time()
|
|||
|
|
|
|||
|
|
'''4、水域过滤后的head+person，再通过船舶范围过滤'''
|
|||
|
|
init_head_person_filterboat=final_head_person_filterwater
|
|||
|
|
# final_head_person_filterboat=[]
|
|||
|
|
#获取船舶范围
|
|||
|
|
boat_contour=[]
|
|||
|
|
|
|||
|
|
for i in range(len(init_boat)):
|
|||
|
|
boundbxs1=[init_boat[i][0],init_boat[i][1],init_boat[i][2],init_boat[i][3]]
|
|||
|
|
contour_temp=fourcorner_coordinate(boundbxs1) #得到boat预测框的顺序contour
|
|||
|
|
contour_temp_=np.array(contour_temp)
|
|||
|
|
contour_temp_=np.float32(contour_temp_)
|
|||
|
|
boat_contour.append(np.array(contour_temp_))
|
|||
|
|
t10 = time.time()
|
|||
|
|
# 遍历船舶范围，取出在船舶范围内的head和person（可能有重复元素）
|
|||
|
|
list_headperson_inboat=[]
|
|||
|
|
for i in range(len(init_head_person_filterboat)):
|
|||
|
|
for j in range(len(boat_contour)):
|
|||
|
|
center_x, center_y=center_coordinate(init_head_person_filterboat[i])
|
|||
|
|
# yyyyyyyy=boat_contour[j]
|
|||
|
|
flag = cv2.pointPolygonTest(boat_contour[j], (center_x, center_y), False) #若为False，会找点是否在内，外，或轮廓上(相应返回+1, -1, 0)。
|
|||
|
|
if flag==1:
|
|||
|
|
list_headperson_inboat.append(init_head_person_filterboat[i])
|
|||
|
|
else:
|
|||
|
|
pass
|
|||
|
|
# print('list_headperson_inboat',list_headperson_inboat)
|
|||
|
|
if len(list_headperson_inboat)==0:
|
|||
|
|
pass
|
|||
|
|
else:
|
|||
|
|
list_headperson_inboat=remove_sameeleme_inalist(list_headperson_inboat) #将重复嵌套列表元素删除
|
|||
|
|
# 过滤船舶范围内的head和person
|
|||
|
|
final_head_person_filterboat=remove_simivalue(init_head_person_filterboat,list_headperson_inboat)
|
|||
|
|
final_output_luoshui=final_head_person_filterboat
|
|||
|
|
t11 = time.time()
|
|||
|
|
|
|||
|
|
#timeInfos=('存图:%s, 过滤标签:%s ,遍历船舶范围:%s,水域过滤后的head+person:%s,水域过滤:%s,head+person、boat取出:%s，新增如果水域为空:%s，找contours:%s，图像改变:%s'
|
|||
|
|
# %((t11-t10) * 1000,(t10-t9) * 1000,(t9-t8) * 1000,(t8-t7) * 1000,(t7-t6) * 1000,(t6-t5) * 1000,(t5-t4) * 1000 ) )
|
|||
|
|
timeInfos=' findMaxWater:%.1f releJudge:%.1f'%( ms(t6,t4) ,ms(t11,t6) )
|
|||
|
|
return final_output_luoshui,timeInfos #返回最终绘制的结果图、最终落水人员（坐标、类别、置信度）
|
|||
|
|
def mixDrowing_water_postprocess_N(predList,pars ):
|
|||
|
|
preds,_mask_cv = predList[0:2]
|
|||
|
|
return mixDrowing_water_postprocess(preds,_mask_cv,pars )
|
|||
|
|
|