Duplicate from Prevantec/platerecognition

Co-authored-by: Cesar Abel Ramirez <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,3 @@
+.idea
+plates
+flagged

README.md

@@ -0,0 +1,14 @@
+---
+title: Platerecognition
+emoji: 📊
+colorFrom: purple
+colorTo: purple
+sdk: gradio
+sdk_version: 3.12.0
+app_file: app.py
+pinned: false
+license: openrail
+duplicated_from: Prevantec/platerecognition
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,155 @@
+import gradio as gr
+import numpy as np
+import cv2
+from norfair import Detection, Tracker, Video
+from detector.utils import detect_plates, detect_chars, imcrop, send_request, draw_text
+from threading import Thread
+
+DISTANCE_THRESHOLD_BBOX: float = 0.7
+DISTANCE_THRESHOLD_CENTROID: int = 30
+MAX_DISTANCE: int = 10000
+
+
+def yolo_to_norfair(yolo_detections):
+    norfair_detections = []
+    detections_as_xyxy = yolo_detections.xyxy[0]
+    for detection_as_xyxy in detections_as_xyxy:
+        bbox = np.array(
+            [
+                [detection_as_xyxy[0].item(), detection_as_xyxy[1].item()],
+                [detection_as_xyxy[2].item(), detection_as_xyxy[3].item()],
+            ]
+        )
+        scores = np.array(
+            [detection_as_xyxy[4].item(), detection_as_xyxy[4].item()]
+        )
+        norfair_detections.append(
+            Detection(
+                points=bbox, scores=scores, label=int(detection_as_xyxy[-1].item())
+            )
+        )
+    return norfair_detections
+
+
+def fn_image(foto):
+    plates_text = []
+    plates = detect_plates(foto)
+    records = plates.pandas().xyxy[0].to_dict(orient='records')
+    if records:
+        for plate in records:
+            xi, yi, xf, yf = int(plate['xmin']), int(plate['ymin']), int(plate['xmax']), int(plate['ymax'])
+            crop = imcrop(foto, (xi, yi, xf, yf))
+            if len(crop) > 0:
+                cv2.rectangle(foto, (xi, yi), (xf, yf), (0, 255, 0), 2)
+                text = detect_chars(crop)
+                draw_text(foto, text, (xi, yi))
+                plates_text.append(text)
+    return foto, plates_text
+
+
+def fn_video(video, initial_time, duration):
+    tracker = Tracker(
+        distance_function="iou_opt",
+        distance_threshold=DISTANCE_THRESHOLD_BBOX,
+    )
+    cap = cv2.VideoCapture(video)
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    image_size = (int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)), int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)))
+    final_video = cv2.VideoWriter('output.mp4', cv2.VideoWriter_fourcc(*'VP90'), fps, image_size)
+    num_frames = 0
+    min_frame = int(initial_time * fps)
+    max_frame = int((initial_time + duration) * fps)
+    plates = {}
+    while cap.isOpened():
+        try:
+            ret, frame = cap.read()
+            gpu_frame = cv2.cuda_GpuMat()
+            gpu_frame.upload(frame)
+            if not ret:
+                break
+            frame_copy = frame.copy()
+        except Exception as e:
+            print(e)
+            continue
+        if num_frames < min_frame:
+            num_frames += 1
+            continue
+        yolo_detections = detect_plates(gpu_frame)
+        detections = yolo_to_norfair(yolo_detections)
+        tracked_objects = tracker.update(detections=detections)
+        for obj in tracked_objects:
+            if obj.last_detection is not None:
+                bbox = obj.last_detection.points
+                bbox = int(bbox[0][0]), int(bbox[0][1]), int(bbox[1][0]), int(bbox[1][1])
+                if obj.id not in plates.keys():
+                    crop = imcrop(gpu_frame, bbox)
+                    text = detect_chars(crop)
+                    plates[obj.id] = text
+                    thread = Thread(target=send_request, args=(frame_copy, text, bbox))
+                    thread.start()
+
+                cv2.rectangle(
+                    gpu_frame,
+                    (bbox[0], bbox[1]),
+                    (bbox[2], bbox[3]),
+                    (0, 255, 0),
+                    2,
+                )
+                draw_text(gpu_frame, plates[obj.id], (bbox[0], bbox[1]))
+                cv2.putText(
+                    gpu_frame,
+                    plates[obj.id],
+                    (bbox[0], bbox[1]),
+                    cv2.FONT_HERSHEY_SIMPLEX,
+                    1,
+                    (0, 255, 0),
+                    2,
+                )
+        final_video.write(gpu_frame)
+        num_frames += 1
+        if num_frames == max_frame:
+            break
+    cap.release()
+    final_video.release()
+    return 'output.mp4', [plates[k] for k in plates.keys()]
+
+
+image_interface = gr.Interface(
+    fn=fn_image,
+    inputs="image",
+    outputs=["image", "text"],
+    title="Buscar números de placa en una imagen",
+    allow_flagging=False,
+    allow_screenshot=False,
+)
+
+video_interface = gr.Interface(
+    fn=fn_video,
+    inputs=[
+        gr.Video(type="file", label="Video"),
+        gr.Slider(0, 600, value=0, label="Tiempo inicial en segundos", step=1),
+        gr.Slider(0, 10, value=4, label="Duración en segundos", step=1),
+    ],
+    outputs=["video", "text"],
+    title="Buscar números de placa en un video",
+    allow_flagging=False,
+    allow_screenshot=False,
+)
+
+webcam_interface = gr.Interface(
+    fn_image,
+    inputs=[
+        gr.Image(source='webcam', streaming=True),
+    ],
+    outputs=gr.Image(type="file"),
+    live=True,
+    title="Buscar placa con la cámara",
+    allow_flagging=False,
+    allow_screenshot=False,
+)
+
+if __name__ == "__main__":
+    gr.TabbedInterface(
+        [image_interface, video_interface],
+        ["Fotos", "Videos"],
+    ).launch()

detector/static/chars.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216d9926ea5ac6195b420b98b668fe8a404f180753e83032904bbcf90906b76d
+size 14516597

detector/static/plates.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34eb52d76e7dcf3e5a5d855ddb8ca95d88633c45bfa08f52e0985e2735e9754c
+size 173134301

detector/utils.py

@@ -0,0 +1,91 @@
+import torch
+import numpy as np
+import cv2
+import os
+from datetime import datetime
+from json import dumps
+import requests
+
+BASE_DIR = os.path.abspath(os.getcwd())
+
+device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
+print('Loading models...', device)
+
+model_plates = torch.hub.load('ultralytics/yolov5', 'custom',
+                              path=os.path.join(BASE_DIR, 'detector', 'static', 'plates.pt'), device=device)
+
+model_chars = torch.hub.load('ultralytics/yolov5', 'custom',
+                             path=os.path.join(BASE_DIR, 'detector', 'static', 'chars.pt'), device=device)
+
+
+def pad_img_to_fit_bbox(img, x1, x2, y1, y2):
+    img = np.pad(img, ((np.abs(np.minimum(0, y1)), np.maximum(y2 - img.shape[0], 0)),
+                       (np.abs(np.minimum(0, x1)), np.maximum(x2 - img.shape[1], 0)), (0, 0)), mode="constant")
+    y1 += np.abs(np.minimum(0, y1))
+    y2 += np.abs(np.minimum(0, y1))
+    x1 += np.abs(np.minimum(0, x1))
+    x2 += np.abs(np.minimum(0, x1))
+    return img, x1, x2, y1, y2
+
+
+def imcrop(img, bbox):
+    x1, y1, x2, y2 = bbox
+    if x1 < 0 or y1 < 0 or x2 > img.shape[1] or y2 > img.shape[0]:
+        img, x1, x2, y1, y2 = pad_img_to_fit_bbox(img, x1, x2, y1, y2)
+    return img[y1:y2, x1:x2, :]
+
+
+def detect_plates(img):
+    return model_plates(img)
+
+
+def detect_chars(img):
+    img = cv2.resize(img, (640, 320))
+    detect = model_chars(img)
+    records = detect.pandas().xyxy[0].to_dict(orient='records')
+    text = ''
+    if records:
+        records = sorted(records, key=lambda d: d['xmin'])
+        text = ''.join([i.get('name') for i in records])
+    return text
+
+
+def draw_text(img, text,
+              pos=(0, 0),
+              font_scale=1,
+              font_thickness=2,
+              text_color=(0, 255, 0),
+              text_color_bg=(0, 0, 0)
+              ):
+    x, y = pos
+    text_size, _ = cv2.getTextSize(text, 0, font_scale, font_thickness)
+    text_w, text_h = text_size
+    cv2.rectangle(img, pos, (x + text_w, y - text_h), text_color_bg, -1)
+    cv2.putText(img, text, (x, y), 0, font_scale, text_color, font_thickness)
+
+
+def send_request(frame, text, bbox):
+    cv2.rectangle(
+        frame,
+        (bbox[0], bbox[1]),
+        (bbox[2], bbox[3]),
+        (0, 255, 0),
+        2,
+    )
+    draw_text(frame, text, (bbox[0], bbox[1]))
+    url = "https://api.prevantec.com/toll-plates"
+    data = {
+        "number": text,
+        "camera": "camera_1",
+        "spot_on": str(datetime.now()),
+    }
+    if not os.path.exists(os.path.join(BASE_DIR, 'plates')):
+        os.makedirs(os.path.join(BASE_DIR, 'plates'))
+    filename = os.path.join(BASE_DIR, 'plates', f'{text}.jpg')
+    cv2.imwrite(filename, frame)
+    payload = {'data': dumps(data)}
+    files = [
+        ('files', (f'{text}.jpg', open(filename, 'rb'), 'image/jpg'))
+    ]
+    headers = {}
+    requests.request("POST", url, headers=headers, data=payload, files=files)

requirements.txt

@@ -0,0 +1,127 @@
+absl-py==1.3.0
+aiohttp==3.8.3
+aiosignal==1.3.1
+anyio==3.6.2
+appnope==0.1.3
+asttokens==2.2.0
+async-timeout==4.0.2
+attrs==22.1.0
+backcall==0.2.0
+bcrypt==4.0.1
+cachetools==5.2.0
+certifi==2021.5.30
+cffi==1.15.1
+chardet==4.0.0
+charset-normalizer==2.1.1
+click==8.1.3
+commonmark==0.9.1
+contourpy==1.0.6
+cryptography==38.0.4
+cycler==0.11.0
+decorator==5.1.1
+easyocr==1.6.2
+executing==1.2.0
+fastapi==0.88.0
+ffmpy==0.3.0
+filterpy==1.4.5
+fonttools==4.38.0
+frozenlist==1.3.3
+fsspec==2022.11.0
+gitdb==4.0.10
+GitPython==3.1.29
+glob2==0.7
+google-auth==2.15.0
+google-auth-oauthlib==0.4.6
+gradio==3.12.0
+grpcio==1.51.1
+h11==0.12.0
+httpcore==0.15.0
+httpx==0.23.1
+idna==3.4
+imageio==2.22.4
+importlib-metadata==5.1.0
+imutils==0.5.4
+ipython==8.7.0
+jedi==0.18.2
+Jinja2==3.1.2
+kiwisolver==1.4.4
+linkify-it-py==1.0.3
+Markdown==3.4.1
+markdown-it-py==2.1.0
+MarkupSafe==2.1.1
+matplotlib==3.6.2
+matplotlib-inline==0.1.6
+mdit-py-plugins==0.3.3
+mdurl==0.1.2
+multidict==6.0.3
+networkx==2.8.8
+ninja==1.11.1
+norfair==2.1.1
+numpy==1.23.5
+oauthlib==3.2.2
+opencv-python==4.5.5.64
+opencv-python-headless==4.5.4.60
+orjson==3.8.3
+packaging==21.3
+pandas==1.5.2
+paramiko==2.12.0
+parso==0.8.3
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==9.3.0
+prompt-toolkit==3.0.33
+protobuf==3.20.3
+psutil==5.9.4
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pyclipper==1.3.0.post4
+pycparser==2.21
+pycryptodome==3.16.0
+pydantic==1.10.2
+pydub==0.25.1
+Pygments==2.13.0
+PyNaCl==1.5.0
+pyparsing==3.0.9
+python-bidi==0.4.2
+python-dateutil==2.8.2
+python-dotenv==0.21.0
+python-multipart==0.0.5
+pytz==2022.6
+PyWavelets==1.4.1
+PyYAML==6.0
+requests==2.28.1
+requests-oauthlib==1.3.1
+requests-toolbelt==0.10.1
+rfc3986==1.5.0
+rich==12.6.0
+rsa==4.9
+scikit-image==0.19.3
+scipy==1.9.3
+seaborn==0.12.1
+Shapely==1.8.5.post1
+six==1.16.0
+smmap==5.0.0
+sniffio==1.3.0
+stack-data==0.6.2
+starlette==0.22.0
+tensorboard==2.11.0
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+thop==0.1.1.post2209072238
+tifffile==2022.10.10
+torch==1.13.0
+torchvision==0.14.0
+tqdm==4.64.1
+traitlets==5.6.0
+typing_extensions==4.4.0
+uc-micro-py==1.0.1
+urllib3==1.26.13
+uvicorn==0.20.0
+wcwidth==0.2.5
+websockets==10.4
+Werkzeug==2.2.2
+wget==3.2
+yarl==1.8.2
+zipp==3.11.0