111 lines
4.0 KiB
Python
111 lines
4.0 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 mixCthc_postprocess(preds, _mask_cv,pars=None):
|
|||
|
|
'''考虑船上人过滤'''
|
|||
|
|
'''输入：危化品的结果（类别+坐标）、原图、mask图像
|
|||
|
|
过程：获得mask的轮廓，判断危化品是否在轮廓内。
|
|||
|
|
在，则保留且绘制；不在，舍弃。
|
|||
|
|
返回：最终绘制的结果图、最终危化品（坐标、类别、置信度），
|
|||
|
|
'''
|
|||
|
|
'''1、最大分隔路面作为判断依据'''
|
|||
|
|
# 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。
|
|||
|
|
# speedroad = _mask_cv.copy()
|
|||
|
|
# speedroad = _mask_cv[speedroad==1]
|
|||
|
|
# _mask_cv[0] = _mask_cv[1]
|
|||
|
|
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()
|
|||
|
|
print('+' * 10, '_mask_cv shape信息', _mask_cv.shape)
|
|||
|
|
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()
|
|||
|
|
|
|||
|
|
# print('+'*10,'路面分隔信息',len(contour_info))
|
|||
|
|
'''新增模块：：如果路面为空，则返回原图、无危化品等。'''
|
|||
|
|
if contour_info == []:
|
|||
|
|
# final_img=_img_cv
|
|||
|
|
final_Cthc_filterroad = []
|
|||
|
|
timeInfos = 0
|
|||
|
|
|
|||
|
|
return final_Cthc_filterroad, timeInfos
|
|||
|
|
else:
|
|||
|
|
# print(contour_info[0])
|
|||
|
|
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Cthc取出，car取出。'''
|
|||
|
|
init_Cthc = []
|
|||
|
|
# init_car = []
|
|||
|
|
for i in range(len(preds)):
|
|||
|
|
if preds[i][5] == 0:
|
|||
|
|
init_Cthc.append(preds[i])
|
|||
|
|
# elif preds[i][5] == 3:
|
|||
|
|
# init_car.append(preds[i])
|
|||
|
|
# person
|
|||
|
|
|
|||
|
|
# points = max_contour.reshape((-1, 1, 2))
|
|||
|
|
# cv2.polylines(image, [points], isClosed=True, color=(0, 255, 0), thickness=2)
|
|||
|
|
|
|||
|
|
'''3、preds中Cthc，通过1中路面过滤'''
|
|||
|
|
init_Cthc_filterroad = init_Cthc
|
|||
|
|
final_Cthc_filterroad = []
|
|||
|
|
for i in range(len(init_Cthc_filterroad)):
|
|||
|
|
center_x, center_y = center_coordinate(init_Cthc_filterroad[i])
|
|||
|
|
# print('#'*20,'line176:',len(max_contour),np.array(max_contour).shape,(center_x, center_y))
|
|||
|
|
# 返回 1、-1 或 0，分别对应点在多边形内部、外部或边界上的情况
|
|||
|
|
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_Cthc_filterroad.append(init_Cthc_filterroad[i])
|
|||
|
|
else:
|
|||
|
|
pass
|
|||
|
|
t9 = time.time()
|
|||
|
|
|
|||
|
|
timeInfos = ' findMaxroad:%.1f releJudge:%.1f' % (ms(t6, t4), ms(t9, t6))
|
|||
|
|
|
|||
|
|
return final_Cthc_filterroad, timeInfos # 返回最终绘制的结果图、危化品（坐标、类别、置信度）
|
|||
|
|
|
|||
|
|
|