first commit

CCPD2019

@@ -0,0 +1 @@
+/mnt/Gpan/BaiduNetdiskDownload/CCPD2019/

README.md

@@ -0,0 +1,36 @@
+环境配置:
+
+```
+pip install -r  requirements.txt
+```
+
+运行:
+
+```
+python detect_plate.py
+```
+
+测试文件夹imgs，结果保存再 result 文件夹中
+
+parser.add_argument('--image_path', type=str, default='imgs', help='source')  # file/folder, 0 for webcam
+
+--image_path 修改为自己的路劲即可
+
+车牌检测参考：
+
+yolov5-face:
+
+[deepcam-cn/yolov5-face: YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022) (github.com)](https://github.com/deepcam-cn/yolov5-face)
+
+车牌识别参考：
+
+crnn:
+
+[bgshih/crnn: Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition. (github.com)](https://github.com/bgshih/crnn)
+
+
+支持如下：
+
+1.蓝牌 2.黄牌 3.双层黄牌 4.农用车牌 5 警车 6 校车 7 教练车 8 港澳车牌 9 使领馆 10 武警 11 新能源 12 等等。。。
+
+![Image text](result/3.jpg)

ccpd

@@ -0,0 +1 @@
+../datasets/ccpd/

ccpd_process.py

@@ -0,0 +1,196 @@
+import os
+import shutil
+import cv2
+import numpy as np
+def allFilePath(rootPath,allFIleList):
+    fileList = os.listdir(rootPath)
+    for temp in fileList:
+        if os.path.isfile(os.path.join(rootPath,temp)):
+            if temp.endswith(".jpg"):
+                allFIleList.append(os.path.join(rootPath,temp))
+        else:
+            allFilePath(os.path.join(rootPath,temp),allFIleList)
+
+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
+    pts=pts[:4,:]
+    rect = np.zeros((5, 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
+    return rect
+
+def get_partical_ccpd():
+    ccpd_dir = r"/mnt/Gpan/BaiduNetdiskDownload/CCPD1/CCPD2020/ccpd_green"
+    save_Path = r"ccpd/green_plate"
+    folder_list = os.listdir(ccpd_dir)
+    for folder_name in folder_list:
+        count=0
+        folder_path = os.path.join(ccpd_dir,folder_name)
+        if os.path.isfile(folder_path):
+            continue
+        if folder_name == "ccpd_fn":
+            continue
+        name_list = os.listdir(folder_path)
+
+        save_folder=save_Path
+        if not os.path.exists(save_folder):
+            os.mkdir(save_folder)
+
+        for name in name_list:
+            file_path = os.path.join(folder_path,name)
+            count+=1
+            if count>1000:
+                break
+            new_file_path =os.path.join(save_folder,name)
+            shutil.move(file_path,new_file_path)
+            print(count,new_file_path)
+
+def get_rect_and_landmarks(img_path):
+   file_name = img_path.split("/")[-1].split("-")
+   landmarks_np =np.zeros((5,2))
+   rect = file_name[2].split("_")
+   landmarks=file_name[3].split("_")
+   rect_str = "&".join(rect)
+   landmarks_str= "&".join(landmarks)
+   rect= rect_str.split("&")
+   landmarks=landmarks_str.split("&")
+   rect=[int(x) for x in rect]
+   landmarks=[int(x) for x in landmarks]
+   for i in range(4):
+        landmarks_np[i][0]=landmarks[2*i]
+        landmarks_np[i][1]=landmarks[2*i+1]
+   middle_landmark_w =int((landmarks[4]+landmarks[6])/2) 
+   middle_landmark_h =int((landmarks[5]+landmarks[7])/2) 
+   landmarks.append(middle_landmark_w)
+   landmarks.append(middle_landmark_h)
+   landmarks_np_new=order_points(landmarks_np)
+   landmarks_np_new[4]=np.array([middle_landmark_w,middle_landmark_h])
+   return rect,landmarks,landmarks_np_new
+
+def x1x2y1y2_yolo(rect,landmarks,img):
+    h,w,c =img.shape
+    rect[0] = max(0, rect[0])
+    rect[1] = max(0, rect[1])
+    rect[2] = min(w - 1, rect[2]-rect[0])
+    rect[3] = min(h - 1, rect[3]-rect[1])
+    annotation = np.zeros((1, 14))
+    annotation[0, 0] = (rect[0] + rect[2] / 2) / w  # cx
+    annotation[0, 1] = (rect[1] + rect[3] / 2) / h  # cy
+    annotation[0, 2] = rect[2] / w  # w
+    annotation[0, 3] = rect[3] / h  # h
+
+    annotation[0, 4] = landmarks[0] / w  # l0_x
+    annotation[0, 5] = landmarks[1] / h  # l0_y
+    annotation[0, 6] = landmarks[2] / w  # l1_x
+    annotation[0, 7] = landmarks[3] / h  # l1_y
+    annotation[0, 8] = landmarks[4] / w  # l2_x
+    annotation[0, 9] = landmarks[5] / h # l2_y
+    annotation[0, 10] = landmarks[6] / w  # l3_x
+    annotation[0, 11] = landmarks[7] / h  # l3_y
+    annotation[0, 12] = landmarks[8] / w  # l4_x
+    annotation[0, 13] = landmarks[9] / h  # l4_y
+    return annotation
+
+def xywh2yolo(rect,landmarks_sort,img):
+    h,w,c =img.shape
+    rect[0] = max(0, rect[0])
+    rect[1] = max(0, rect[1])
+    rect[2] = min(w - 1, rect[2]-rect[0])
+    rect[3] = min(h - 1, rect[3]-rect[1])
+    annotation = np.zeros((1, 14))
+    annotation[0, 0] = (rect[0] + rect[2] / 2) / w  # cx
+    annotation[0, 1] = (rect[1] + rect[3] / 2) / h  # cy
+    annotation[0, 2] = rect[2] / w  # w
+    annotation[0, 3] = rect[3] / h  # h
+
+    annotation[0, 4] = landmarks_sort[0][0] / w  # l0_x
+    annotation[0, 5] = landmarks_sort[0][1] / h  # l0_y
+    annotation[0, 6] = landmarks_sort[1][0] / w  # l1_x
+    annotation[0, 7] = landmarks_sort[1][1] / h  # l1_y
+    annotation[0, 8] = landmarks_sort[2][0] / w  # l2_x
+    annotation[0, 9] = landmarks_sort[2][1] / h # l2_y
+    annotation[0, 10] = landmarks_sort[3][0] / w  # l3_x
+    annotation[0, 11] = landmarks_sort[3][1] / h  # l3_y
+    annotation[0, 12] = landmarks_sort[4][0] / w  # l4_x
+    annotation[0, 13] = landmarks_sort[4][1] / h  # l4_y
+    return annotation
+
+def yolo2x1y1x2y2(annotation,img):
+    h,w,c = img.shape
+    rect= annotation[:,0:4].squeeze().tolist()
+    landmarks=annotation[:,4:].squeeze().tolist()
+    rect_w = w*rect[2]
+    rect_h =h*rect[3]
+    rect_x =int(rect[0]*w-rect_w/2)
+    rect_y = int(rect[1]*h-rect_h/2)
+    new_rect=[rect_x,rect_y,rect_x+rect_w,rect_y+rect_h]
+    for i in range(5):
+        landmarks[2*i]=landmarks[2*i]*w
+        landmarks[2*i+1]=landmarks[2*i+1]*h
+    return new_rect,landmarks
+
+def write_lable(file_path):
+    pass
+
+
+if __name__ == '__main__':
+   file_root = r"ccpd/val"
+   file_list=[]
+   count=0
+   allFilePath(file_root,file_list)
+   for img_path in file_list:
+        count+=1
+        # img_path = r"ccpd_yolo_test/02-90_85-173&466_452&541-452&553_176&556_178&463_454&460-0_0_6_26_15_26_32-68-53.jpg"
+        text_path= img_path.replace(".jpg",".txt")
+        img =cv2.imread(img_path)
+        rect,landmarks,landmarks_sort=get_rect_and_landmarks(img_path)
+        # annotation=x1x2y1y2_yolo(rect,landmarks,img)
+        annotation=xywh2yolo(rect,landmarks_sort,img)
+        str_label = "0 "
+        for i in range(len(annotation[0])):
+                str_label = str_label + " " + str(annotation[0][i])
+        str_label = str_label.replace('[', '').replace(']', '')
+        str_label = str_label.replace(',', '') + '\n'
+        with open(text_path,"w") as f:
+                f.write(str_label)
+        print(count,img_path)
+    # get_partical_ccpd()
+    # file_root = r"ccpd/green_plate"
+    # file_list=[]
+    # allFilePath(file_root,file_list)
+    # count=0
+    # for img_path in file_list:
+    #     img_name = img_path.split(os.sep)[-1]
+    #     if not "&" in img_name:
+    #         count+=1
+    #         os.remove(img_path)
+    #         print(count,img_path)
+
+        # new_rect,new_landmarks=yolo2x1y1x2y2(annotation,img)
+        # rect= [int(x) for x in  new_rect]
+        # cv2.rectangle(img,(rect[0],rect[1]),(rect[2],rect[3]),(255,0,0),2)
+        # colors=[(0,255,0),(0,255,255),(255,255,0),(255,255,255),(255,0,255)] #绿 黄 青 白 
+        # for i in range(5):
+        #   cv2.circle(img,(landmarks[2*i],landmarks[2*i+1]),2,colors[i],2)
+        # cv2.imwrite("1.jpg",img)
+    #    print(rect,landmarks)
+        # get_partical_ccpd()
+
+
+

ccpd_yolo_test/02-90_85-173&466_452&541-452&553_176&556_178&463_454&460-0_0_6_26_15_26_32-68-53.txt

@@ -0,0 +1 @@
+0  0.6277 0.4767 0.2444 0.4793 0.2472 0.3991 0.6305 0.3965 0.4388 0.3974

ccpd_yolo_test/02-90_85-173&466_452&541-452&553_176&556_178&463_454&460-0_0_6_26_15_26_32-68-531.txt

@@ -0,0 +1 @@
+0  0.4340277777777778 0.434051724137931 0.3875 0.06465517241379311 0.24722222222222223 0.39913793103448275 0.6305555555555555 0.39655172413793105 0.6277777777777778 0.47672413793103446 0.24444444444444444 0.4793103448275862 0.4388888888888889 0.39741379310344827

data/argoverse_hd.yaml

@@ -0,0 +1,21 @@
+# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/
+# Train command: python train.py --data argoverse_hd.yaml
+# Default dataset location is next to /yolov5:
+#   /parent_folder
+#     /argoverse
+#     /yolov5
+
+
+# download command/URL (optional)
+download: bash data/scripts/get_argoverse_hd.sh
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../argoverse/Argoverse-1.1/images/train/  # 39384 images
+val: ../argoverse/Argoverse-1.1/images/val/  # 15062 iamges
+test: ../argoverse/Argoverse-1.1/images/test/  # Submit to: https://eval.ai/web/challenges/challenge-page/800/overview
+
+# number of classes
+nc: 8
+
+# class names
+names: [ 'person',  'bicycle',  'car',  'motorcycle',  'bus',  'truck',  'traffic_light',  'stop_sign' ]

data/coco.yaml

@@ -0,0 +1,35 @@
+# COCO 2017 dataset http://cocodataset.org
+# Train command: python train.py --data coco.yaml
+# Default dataset location is next to /yolov5:
+#   /parent_folder
+#     /coco
+#     /yolov5
+
+
+# download command/URL (optional)
+download: bash data/scripts/get_coco.sh
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../coco/train2017.txt  # 118287 images
+val: ../coco/val2017.txt  # 5000 images
+test: ../coco/test-dev2017.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
+
+# number of classes
+nc: 80
+
+# class names
+names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
+         'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
+         'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+         'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
+         'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
+         'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+         'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
+         'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
+         'hair drier', 'toothbrush' ]
+
+# Print classes
+# with open('data/coco.yaml') as f:
+#   d = yaml.load(f, Loader=yaml.FullLoader)  # dict
+#   for i, x in enumerate(d['names']):
+#     print(i, x)

data/coco128.yaml

@@ -0,0 +1,28 @@
+# COCO 2017 dataset http://cocodataset.org - first 128 training images
+# Train command: python train.py --data coco128.yaml
+# Default dataset location is next to /yolov5:
+#   /parent_folder
+#     /coco128
+#     /yolov5
+
+
+# download command/URL (optional)
+download: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../coco128/images/train2017/  # 128 images
+val: ../coco128/images/train2017/  # 128 images
+
+# number of classes
+nc: 80
+
+# class names
+names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
+         'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
+         'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+         'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
+         'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
+         'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+         'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
+         'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
+         'hair drier', 'toothbrush' ]

data/hyp.finetune.yaml

@@ -0,0 +1,38 @@
+# Hyperparameters for VOC finetuning
+# python train.py --batch 64 --weights yolov5m.pt --data voc.yaml --img 512 --epochs 50
+# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
+
+
+# Hyperparameter Evolution Results
+# Generations: 306
+#                   P         R     mAP.5 mAP.5:.95       box       obj       cls
+# Metrics:        0.6     0.936     0.896     0.684    0.0115   0.00805   0.00146
+
+lr0: 0.0032
+lrf: 0.12
+momentum: 0.843
+weight_decay: 0.00036
+warmup_epochs: 2.0
+warmup_momentum: 0.5
+warmup_bias_lr: 0.05
+box: 0.0296
+cls: 0.243
+cls_pw: 0.631
+obj: 0.301
+obj_pw: 0.911
+iou_t: 0.2
+anchor_t: 2.91
+# anchors: 3.63
+fl_gamma: 0.0
+hsv_h: 0.0138
+hsv_s: 0.664
+hsv_v: 0.464
+degrees: 0.373
+translate: 0.245
+scale: 0.898
+shear: 0.602
+perspective: 0.0
+flipud: 0.00856
+fliplr: 0.5
+mosaic: 1.0
+mixup: 0.243