新增車牌矯正功能

AlprTritonClient/EZLPR.py

@@ -8,6 +8,7 @@ sys.path.append(root_path)
 # from retina_utils.TrtRetinaGrayPlate import TrtRetinaPlate as TrtRetinaGrayPlate
 # from retina_utils.TrtRetinaGrayPlateSHM import TrtRetinaPlateSHM as TrtRetinaGrayPlateSHM
 
+from retina_utils.alignment import align
 from retina_utils.TrtRetinaColorPlate import TrtRetinaPlate as TrtRetinaColorPlate
 from retina_utils.TrtRetinaColorPlateSHM import TrtRetinaPlateSHM as TrtRetinaColorPlateSHM 
 
@@ -46,6 +47,7 @@ class TrtRetinaPlateThread(threading.Thread):
         self.conf_th = conf_th
         self.trt_plate = None   # to be created when run
         self.running = False
+        self.alignment = align
 
     def run(self):
         """Run until 'running' flag is set to False by main thread.
@@ -76,8 +78,14 @@ class TrtRetinaPlateThread(threading.Thread):
                 boxes = output[:,:4].astype(int)
                 confs = output[:,4]
                 lands = output[:,5:].astype(int)
-                loc = boxes[0]
-                crop_img = info.img[loc[1]:loc[3],loc[0]:loc[2]]
+                loc = boxes[0]         # 請考慮以後可能是 多個 batch ouptut
+                land = output[:,5:][0] # 請考慮以後可能是 多個 batch ouptut
+                if self.alignment is not None:
+                    crop_img = align(info.img,land,padding=5)
+                    if crop_img is None:
+                        crop_img = info.img[loc[1]:loc[3],loc[0]:loc[2]]
+                else:
+                    crop_img = info.img[loc[1]:loc[3],loc[0]:loc[2]]
                 # 過濾物件
                 plateInfo = PlateInfo(info.track_id, info.img ,crop_img)
                 self.plates_q.put(plateInfo)
@@ -204,4 +212,4 @@ class EZLPR(object):
             
     def __del__(self):
         self.trtRetinaPlateThread.stop()
-        self.trtCtcOcrThread.stop()
\ No newline at end of file
+        self.trtCtcOcrThread.stop()

AlprTritonClient/retina_utils/alignment.py

+import numpy as np
+import cv2
+def align(image,landmarks,padding):
+    # 取得車牌頂點座標
+    # 左上左下 右上右下
+    try:                        
+        #oring_landmarks=list(map(float, landmarks))
+        oring_landmarks = landmarks
+        left_top_landmark=oring_landmarks[:2]
+        left_bottom_landmark=oring_landmarks[2:4]
+        right_top_landmark=oring_landmarks[4:6]
+        right_bottom_landmark=oring_landmarks[6:8]
+        src_points = np.array([left_top_landmark, left_bottom_landmark,right_top_landmark, right_bottom_landmark], dtype = "float32")
+        transform_plate=four_point_transform(image,src_points,padding)
+        return transform_plate
+    except Exception as e:
+        return None
+    
+def order_points(pts):
+    # initialzie a list of coordinates that will be ordered
+    # such that the first entry in the list is the top-left,
+    # the second entry is the top-right, the third is the
+    # bottom-right, and the fourth is the bottom-left
+    
+    '''
+    rect = np.zeros((4, 2), dtype = "float32")
+ 
+    # the top-left point will have the smallest sum, whereas
+    # the bottom-right point will have the largest sum
+    s = pts.sum(axis = 1)
+    rect[0] = pts[np.argmin(s)]
+    rect[2] = pts[np.argmax(s)]
+ 
+    # now, compute the difference between the points, the
+    # top-right point will have the smallest difference,
+    # whereas the bottom-left will have the largest difference
+    diff = np.diff(pts, axis = 1)
+    rect[1] = pts[np.argmin(diff)]
+    rect[3] = pts[np.argmax(diff)]
+ 
+    # return the ordered coordinates
+    '''
+    rect = np.zeros((4, 2), dtype = "float32")
+    
+    rect[0]=pts[0]
+    rect[1]=pts[2]
+    rect[2]=pts[3]
+    rect[3]=pts[1]
+    
+    return rect
+
+def four_point_transform(image, pts,padding):
+    # obtain a consistent order of the points and unpack them
+    # individually
+    rect = order_points(pts)
+    (tl, tr, br, bl) = rect
+ 
+    # compute the width of the new image, which will be the
+    # maximum distance between bottom-right and bottom-left
+    # x-coordiates or the top-right and top-left x-coordinates
+    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
+    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
+    maxWidth = max(int(widthA), int(widthB))
+ 
+    # compute the height of the new image, which will be the
+    # maximum distance between the top-right and bottom-right
+    # y-coordinates or the top-left and bottom-left y-coordinates
+    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
+    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
+    maxHeight = max(int(heightA), int(heightB))
+ 
+    # now that we have the dimensions of the new image, construct
+    # the set of destination points to obtain a "birds eye view",
+    # (i.e. top-down view) of the image, again specifying points
+    # in the top-left, top-right, bottom-right, and bottom-left
+    # order    
+
+    dst = np.array([
+        [0, 0],
+        [maxWidth - 1, 0],
+        [maxWidth - 1, maxHeight - 1],
+        [0, maxHeight - 1]], dtype = "float32")
+    # compute the perspective transform matrix and then apply it
+    M = cv2.getPerspectiveTransform(rect, dst)
+    warped = cv2.warpPerspective(image, M, (maxWidth+padding, maxHeight))    
+ 
+    # return the warped image
+    return warped
+
+def align_with_template(image,landmarks,padding):
+    # 取得車牌頂點座標
+    # 左上左下 右上右下
+    try:                        
+        oring_landmarks=list(map(int, landmarks))
+        left_top_landmark=oring_landmarks[:2]
+        left_bottom_landmark=oring_landmarks[2:4]
+        right_top_landmark=oring_landmarks[4:6]
+        right_bottom_landmark=oring_landmarks[6:8]
+        src_points = np.array([left_top_landmark, left_bottom_landmark,right_top_landmark, right_bottom_landmark], dtype = "float32")
+        transform_plate=map_to_template(image,src_points,padding)
+        return transform_plate
+    except Exception as e:
+        print(e)
+        return False
+
+def map_to_template(image,pts,padding):
+    rect = order_points(pts)
+    template_4ps=[[79,866],[79,1589],[1126,866],[1126,1589]]
+    #  左上    左下    右上      右下
+    # [79,866,79,1589,1126,866,1126,1589]
+    dst = np.array([
+    template_4ps[0],  # 左上
+    template_4ps[2], # 右上
+    template_4ps[3],# 右下
+    template_4ps[1]] # 左下
+    , dtype = "float32")
+
+    M = cv2.getPerspectiveTransform(rect, dst)
+    warped = cv2.warpPerspective(image, M, (1191, 1685))
+    x1,y1,x2,y2= template_4ps[0][0],template_4ps[0][1],template_4ps[3][0],template_4ps[3][1]
+    return warped[y1-padding:y2+padding,x1-padding:x2+padding]
\ No newline at end of file

PlanB_test0609.py

@@ -30,10 +30,10 @@ yolo = TrtYOLOSHM()
 easyLPR=EZLPR()
 
 #source="/home/tx2/Videos/20220504173000.mp4"
-#source="/home/tx2/Videos/Kevin_Car.MOV"
+source="/home/tx2/Videos/Kevin_Car.MOV"
 #source = "../Ch17-20220314-190000.mp4"
 
-source="rtsp://192.168.5.218/txg/01"
+#source="rtsp://192.168.5.218/txg/01"
 #source="rtsp://140.120.65.31/live.sdp"
 cam=Camera(1,source,encoder = "h265",width=1920,height=1080)
 
@@ -123,9 +123,8 @@ try:
 
                 InputLPR_span,stime=time_span(stime) # !
                      
-                for index,platNum in easyLPR.out():
+                for index,platNum,vechile_img,plate_img in easyLPR.out():
                     if index in CT.objects:
-                        print(index, platNum)
                         CT.objects[index].update_lpr_candis(platNum)
                 OutputLPR_span,stime=time_span(stime) # !
                 
@@ -143,7 +142,7 @@ try:
 
                 total_span=time.time()-staic_stime
                 
-                sys.stdout.write(f"\rObject Count:{CT.nextObjectID}, Fps:{int(np.mean(FPS))}")
+                #sys.stdout.write(f"\rObject Count:{CT.nextObjectID}, Fps:{int(np.mean(FPS))}")
 
 #                 sys.stdout.write(f"\rObject Count:{CT.nextObjectID}, Fps:{int(1/(total_span))}"
 #                       f",yolo_span:{int((yolo_span/total_span)*100)}%"

test_camera.ipynb

@@ -170,7 +170,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "f5590c70",
    "metadata": {},
    "outputs": [
@@ -178,7 +178,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "30.0\n"
+      "60.0\n"
      ]
     },
     {
@@ -188,7 +188,7 @@
      "traceback": [
       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
       "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-3-4323a410c5ab>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     32\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mret\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     33\u001b[0m             \u001b[0;31m#VioWri.Frame = frame\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 34\u001b[0;31m             \u001b[0mwriter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mframe\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     35\u001b[0m \u001b[0;31m#             cv2.imshow(\"1\",frame)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     36\u001b[0m \u001b[0;31m#             key=cv2.waitKey(1)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m<ipython-input-2-4323a410c5ab>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m     32\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mret\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     33\u001b[0m             \u001b[0;31m#VioWri.Frame = frame\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 34\u001b[0;31m             \u001b[0mwriter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mframe\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     35\u001b[0m \u001b[0;31m#             cv2.imshow(\"1\",frame)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     36\u001b[0m \u001b[0;31m#             key=cv2.waitKey(1)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
       "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
      ]
     }

test_influx.ipynb

 {
  "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "3ec02b9e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "False\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "\n",
+    "a=False\n",
+    "\n",
+    "if a is False :\n",
+    "    print(a)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 4,