degug trafficV7

AI.py

@@ -116,9 +116,9 @@ def AI_process(im0s,model,segmodel,names,label_arraylist,rainbows,objectPar={ 'h
         postPar['mask']=seg_pred;postPar['det']=deepcopy(det_coords)
         postPar['label_info']=label_info
         tlist = list(postPar.keys()); tlist.sort()
-        
         if len(det_coords)> 0:
             list8, image,time_infos = trafficPostProcessingV2(postPar) 
+            print('##list8:',list8)
             Accident_results = np.array(list8,dtype=object)  
             acc_det=[]
             for bpoints in list8:

segutils/trafficUtils.py

@@ -707,6 +707,8 @@ def trafficPostProcessingV2(traffic_dict, debug=False):
     list3 = []  # # 存储vehicle最小外接矩形的最短边
     list4 = []  # list4存储车辆的box参数
     list5 = []  # 存储vehicle的宽高
+    list14 = []
+    list15 = []
     for cnt in contours:  # 道路
         rect = cv2.minAreaRect(cnt)
         if rect[1][0] * rect[1][1] > traffic_dict['speedRoadArea']:  # 过滤掉面积小于阈值的speedRoad
@@ -730,13 +732,13 @@ def trafficPostProcessingV2(traffic_dict, debug=False):
             list1.append(rect[1])  # 将道路的宽高存储在list1中
             list2.append(list1)
         list1 = []
-    if len(list2) == 0:
-        print("分割出的speedRoad区域的面积小于设定值，请调整设定值！")
+    # if len(list2) == 0:
+    #     print("分割出的speedRoad区域的面积小于设定值，请调整设定值！")
     # print("line213", list2)
-    list14 = []
-    list15 = []
+
     count = 0
     for i in range(0, len(traffic_dict['vehicleCoordinate']), 2):
+        list16 = []  # 5.6
         mask = np.zeros(image_vehicle.shape[:2], dtype="uint8")
 
         x0 = int(traffic_dict['vehicleCoordinate'][i][0] * traffic_dict['ZoomFactor']['x'])
@@ -755,8 +757,52 @@ def trafficPostProcessingV2(traffic_dict, debug=False):
         contours2, hierarchy2 = cv2.findContours(img2, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
 
         if len(contours2) != 0:
-            list10.append(contours2)
-            list14.append(traffic_dict['det'][count])
+            if len(contours2) > 1:  # 这里我通过比较同一检测框内各个contours对应的最小外接矩形的面积，来剔除那些存在干扰的contours，最终只保留一个contours
+                for j in range(len(contours2)):
+                    contours_j = contours2[j]
+                    rect = cv2.minAreaRect(contours_j)
+                    list16.append(rect[1][0] * rect[1][1])
+                if max(list16) >= traffic_dict['vehicleArea']:
+                    maxAreaIndex = list16.index(max(list16))
+                    maxAreacontours = contours2[maxAreaIndex]
+                    if len(maxAreacontours) >= 6:
+                        list10.append(maxAreacontours)
+                        list14.append(traffic_dict['det'][count])
+                    else:
+                        traffic_dict['det'][int(i / 2)].append(5)
+                        traffic_dict['det'][int(i / 2)].append(0.5)
+                        traffic_dict['det'][int(i / 2)].append(15)
+                        traffic_dict['det'][int(i / 2)].append(0.01)
+                        traffic_dict['det'][int(i / 2)].append(3)
+                        list15.append(traffic_dict['det'][int(i / 2)])
+                else:
+                    traffic_dict['det'][int(i / 2)].append(5)
+                    traffic_dict['det'][int(i / 2)].append(0.5)
+                    traffic_dict['det'][int(i / 2)].append(15)
+                    traffic_dict['det'][int(i / 2)].append(0.01)
+                    traffic_dict['det'][int(i / 2)].append(3)
+                    list15.append(traffic_dict['det'][int(i / 2)])
+            elif len(contours2) == 1:
+                contours_j = contours2[0]
+                rect = cv2.minAreaRect(contours_j)
+                if rect[1][0] * rect[1][1] >= traffic_dict['vehicleArea']:
+                    if len(contours_j) >= 6:
+                        list10.append(contours_j)
+                        list14.append(traffic_dict['det'][count])
+                    else:
+                        traffic_dict['det'][int(i / 2)].append(5)
+                        traffic_dict['det'][int(i / 2)].append(0.5)
+                        traffic_dict['det'][int(i / 2)].append(15)
+                        traffic_dict['det'][int(i / 2)].append(0.01)
+                        traffic_dict['det'][int(i / 2)].append(3)
+                        list15.append(traffic_dict['det'][int(i / 2)])
+                else:
+                    traffic_dict['det'][int(i / 2)].append(5)
+                    traffic_dict['det'][int(i / 2)].append(0.5)
+                    traffic_dict['det'][int(i / 2)].append(15)
+                    traffic_dict['det'][int(i / 2)].append(0.01)
+                    traffic_dict['det'][int(i / 2)].append(3)
+                    list15.append(traffic_dict['det'][int(i / 2)])
         else:
             traffic_dict['det'][int(i/2)].append(5)
             traffic_dict['det'][int(i/2)].append(0.5)
@@ -766,42 +812,22 @@ def trafficPostProcessingV2(traffic_dict, debug=False):
             list15.append(traffic_dict['det'][int(i/2)])
         count += 1
     traffic_dict['det'] = list14
-    # list12 = []
 
     if len(list10) != 0:
-        for i in range(len(list10)):  # 选取落在检测框范围内的分割区域，存在一个问题，就是其他vehicle的一小部分分割区域可能也落在了检测框中，这时会产生多个contours，
-            list12 = []
-            if len(list10[i]) > 1:  # 这里我通过比较同一检测框内各个contours对应的最小外接矩形的面积，来剔除那些存在干扰的contours，最终只保留一个contours
-                for j in range(len(list10[i])):
-                    contours_j = list10[i][j]
-                    rect = cv2.minAreaRect(contours_j)
-                    list12.append(rect)
-                list13 = [list12[g][1][0] * list12[g][1][1] for g in range(len(list12))]
-                maxAreaIndex = list13.index(max(list13))
-                rect = list12[maxAreaIndex]
-                box = cv2.boxPoints(rect).astype(np.int32)
-                maxAreacontours = list10[i][maxAreaIndex]
-                ellipse = cv2.fitEllipse(maxAreacontours)  # （中心点坐标(x，y)，(短轴长度，长轴长度)，短轴与水平线的夹角）
-                if ellipse[2] >= 0 and ellipse[2] < 90:
-                    vehicleAngle = 90 + ellipse[2]
-                elif ellipse[2] >= 90 and ellipse[2] < 180:
-                    vehicleAngle = ellipse[2] - 90
-                elif ellipse[2] == 180:
-                    vehicleAngle = 90
-            elif len(list10[i]) == 1:
-                rect = cv2.minAreaRect(np.array(list10[i][0]))
-                box = cv2.boxPoints(rect).astype(np.int32)
-                maxAreacontours = list10[i][0]
-                ellipse = cv2.fitEllipse(maxAreacontours)
-                if ellipse[2] >= 0 and ellipse[2] < 90:
-                    vehicleAngle = 90 + ellipse[2]
-                elif ellipse[2] >= 90 and ellipse[2] < 180:
-                    vehicleAngle = ellipse[2] - 90
-                elif ellipse[2] == 180:
-                    vehicleAngle = 90
+        for i in range(len(list10)):  # 选取落在检测框范围内的分割区域，存在一个问题，就是其他vehicle的一小部分分割区域可能也落在了检测框中，这时会产生多个contours.
+            ellipse = cv2.fitEllipse(list10[i])
+            if ellipse[2] >= 0 and ellipse[2] < 90:
+                vehicleAngle = 90 + ellipse[2]
+            elif ellipse[2] >= 90 and ellipse[2] < 180:
+                vehicleAngle = ellipse[2] - 90
+            elif ellipse[2] == 180:
+                vehicleAngle = 90
+            rect = cv2.minAreaRect(list10[i])
+            box = cv2.boxPoints(rect).astype(np.int32)
             list3.append(min(rect[1]))
             list4.append(box)
             list5.append(rect[1])
+
             for j in range(len(list2)):
                 if (rect[0][0] > list2[j][0] and rect[0][0] < list2[j][1]) and (rect[0][1] > list2[j][2] and rect[0][1] < list2[j][3]):  # 判断车辆矩形框的中心点坐标是否在道路矩形框Xmin,Xmax,Ymin和Ymax的范围内；
                     box = cv2.boxPoints(rect).astype(np.int32)  # 将Box2D结构作为输入并返回4个角点。
@@ -890,11 +916,13 @@ def trafficPostProcessingV2(traffic_dict, debug=False):
             list23.append(list15[i])
         # print("line372", list23)  # 目标对象, [[cls, x0, y0, x1, y1, score, 角度, 长宽比, 最小距离, max([角度得分, 长宽比得分, 最小距离得分]), 类别], ...]
     else:
-        print("分割模型未检测到vehicle！")
-        list23 = traffic_dict['det']
+        # print("分割模型未检测到vehicle！")
+        list23 = list15
+        print("line418", list23)
 
     t6 = time.time()
     time_infos = 'postTime:%.2f (分割时间：%.2f, findContours:%.2f  ruleJudge:%.2f)' % (
     get_ms(t6, t3), get_ms(t4, t3), get_ms(t5, t4), get_ms(t6, t5))
     return list23, image, time_infos
 
+