Spaces:
Sleeping
Sleeping
sd
Browse files
app.py
CHANGED
|
@@ -2,58 +2,82 @@ import cv2
|
|
| 2 |
import gradio as gr
|
| 3 |
from transformers import pipeline
|
| 4 |
from PIL import Image
|
| 5 |
-
|
| 6 |
-
|
|
|
|
| 7 |
detector = pipeline("object-detection", model="facebook/detr-resnet-50", device=-1)
|
| 8 |
|
| 9 |
def process_video(video_path):
|
| 10 |
"""
|
| 11 |
-
Procesa un video
|
|
|
|
|
|
|
| 12 |
"""
|
| 13 |
cap = cv2.VideoCapture(video_path)
|
| 14 |
if not cap.isOpened():
|
| 15 |
-
return
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
while True:
|
| 20 |
ret, frame = cap.read()
|
| 21 |
if not ret:
|
| 22 |
break
|
| 23 |
|
| 24 |
-
# Convertir el frame de BGR a RGB
|
| 25 |
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
|
| 26 |
-
|
| 27 |
-
# Convertir el array de NumPy a una imagen PIL
|
| 28 |
pil_image = Image.fromarray(frame_rgb)
|
| 29 |
|
| 30 |
-
#
|
| 31 |
results = detector(pil_image)
|
| 32 |
|
| 33 |
-
#
|
| 34 |
-
frame_counts = {"person": 0, "bicycle": 0, "motorcycle": 0}
|
| 35 |
for detection in results:
|
| 36 |
-
|
| 37 |
-
continue
|
| 38 |
label = detection["label"].lower()
|
| 39 |
-
if label in
|
| 40 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
-
#
|
| 43 |
-
|
| 44 |
-
if frame_counts[key] > max_counts[key]:
|
| 45 |
-
max_counts[key] = frame_counts[key]
|
| 46 |
|
| 47 |
cap.release()
|
| 48 |
-
|
|
|
|
| 49 |
|
| 50 |
-
# Crear la interfaz de Gradio para el Space
|
| 51 |
iface = gr.Interface(
|
| 52 |
fn=process_video,
|
| 53 |
inputs=gr.Video(label="Sube tu video"),
|
| 54 |
-
outputs="
|
| 55 |
-
title="Detecci贸n de Objetos en Video",
|
| 56 |
-
description="Carga un video y
|
| 57 |
)
|
| 58 |
|
| 59 |
if __name__ == "__main__":
|
|
|
|
| 2 |
import gradio as gr
|
| 3 |
from transformers import pipeline
|
| 4 |
from PIL import Image
|
| 5 |
+
import tempfile
|
| 6 |
+
|
| 7 |
+
# Cargar el modelo de detecci贸n de objetos usando CPU
|
| 8 |
detector = pipeline("object-detection", model="facebook/detr-resnet-50", device=-1)
|
| 9 |
|
| 10 |
def process_video(video_path):
|
| 11 |
"""
|
| 12 |
+
Procesa un video, detecta objetos y dibuja cuadros y etiquetas sobre ellos.
|
| 13 |
+
Solo se procesar谩n las detecciones de personas, bicicletas y motos.
|
| 14 |
+
Devuelve el video anotado.
|
| 15 |
"""
|
| 16 |
cap = cv2.VideoCapture(video_path)
|
| 17 |
if not cap.isOpened():
|
| 18 |
+
return None
|
| 19 |
+
|
| 20 |
+
# Obtener propiedades del video
|
| 21 |
+
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
| 22 |
+
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
| 23 |
+
fps = cap.get(cv2.CAP_PROP_FPS)
|
| 24 |
|
| 25 |
+
# Crear un archivo temporal para guardar el video de salida
|
| 26 |
+
tmp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp4")
|
| 27 |
+
output_path = tmp_file.name
|
| 28 |
+
tmp_file.close() # Se cierra para que VideoWriter pueda escribir en 茅l
|
| 29 |
+
|
| 30 |
+
# Configurar VideoWriter (utilizamos el c贸dec mp4v)
|
| 31 |
+
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
|
| 32 |
+
out = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
|
| 33 |
|
| 34 |
+
# Definir las clases a las que queremos aplicar detecci贸n
|
| 35 |
+
valid_labels = {"person", "bicycle", "motorcycle"}
|
| 36 |
+
threshold = 0.7 # Umbral de confianza
|
| 37 |
+
|
| 38 |
while True:
|
| 39 |
ret, frame = cap.read()
|
| 40 |
if not ret:
|
| 41 |
break
|
| 42 |
|
| 43 |
+
# Convertir el frame de BGR a RGB y luego a imagen PIL
|
| 44 |
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
|
|
|
|
|
|
|
| 45 |
pil_image = Image.fromarray(frame_rgb)
|
| 46 |
|
| 47 |
+
# Obtener detecciones con el pipeline
|
| 48 |
results = detector(pil_image)
|
| 49 |
|
| 50 |
+
# Dibujar cada detecci贸n v谩lida en el frame
|
|
|
|
| 51 |
for detection in results:
|
| 52 |
+
score = detection["score"]
|
|
|
|
| 53 |
label = detection["label"].lower()
|
| 54 |
+
if score < threshold or label not in valid_labels:
|
| 55 |
+
continue
|
| 56 |
+
|
| 57 |
+
# Obtener la caja del objeto en formato [xmin, ymin, width, height]
|
| 58 |
+
box = detection["box"]
|
| 59 |
+
xmin, ymin, w, h = box
|
| 60 |
+
xmax = xmin + w
|
| 61 |
+
ymax = ymin + h
|
| 62 |
+
|
| 63 |
+
# Dibujar el rect谩ngulo y la etiqueta en el frame
|
| 64 |
+
cv2.rectangle(frame, (int(xmin), int(ymin)), (int(xmax), int(ymax)), color=(0, 255, 0), thickness=2)
|
| 65 |
+
text = f"{label}: {score:.2f}"
|
| 66 |
+
cv2.putText(frame, text, (int(xmin), int(ymin)-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
|
| 67 |
|
| 68 |
+
# Escribir el frame anotado en el video de salida
|
| 69 |
+
out.write(frame)
|
|
|
|
|
|
|
| 70 |
|
| 71 |
cap.release()
|
| 72 |
+
out.release()
|
| 73 |
+
return output_path
|
| 74 |
|
|
|
|
| 75 |
iface = gr.Interface(
|
| 76 |
fn=process_video,
|
| 77 |
inputs=gr.Video(label="Sube tu video"),
|
| 78 |
+
outputs=gr.Video(label="Video procesado"),
|
| 79 |
+
title="Detecci贸n y Visualizaci贸n de Objetos en Video",
|
| 80 |
+
description="Carga un video y se detectan personas, bicicletas y motos. Los objetos se enmarcan y etiquetan, mostrando la detecci贸n en tiempo real."
|
| 81 |
)
|
| 82 |
|
| 83 |
if __name__ == "__main__":
|