Object Detection Tutorial#
 Run on Google Colab
|
 View source on GitHub
|
 Download notebook
|
Start EVA server#
We are reusing the start server notebook for launching the EVA server.
!wget -nc "https://raw.githubusercontent.com/georgia-tech-db/eva/master/tutorials/00-start-eva-server.ipynb"
%run 00-start-eva-server.ipynb
cursor = connect_to_server()
File ‘00-start-eva-server.ipynb’ already there; not retrieving.
[notice] A new release of pip is available: 23.0.1 -> 23.1.2
[notice] To update, run: pip install --upgrade pip
Note: you may need to restart the kernel to use updated packages.
nohup eva_server > eva.log 2>&1 &
[notice] A new release of pip is available: 23.0.1 -> 23.1.2
[notice] To update, run: pip install --upgrade pip
Note: you may need to restart the kernel to use updated packages.
Download the Videos#
# Getting the video files
!wget -nc "https://www.dropbox.com/s/k00wge9exwkfxz6/ua_detrac.mp4?raw=1" -O ua_detrac.mp4
File ‘ua_detrac.mp4’ already there; not retrieving.
Load the surveillance videos for analysis#
We use regular expression to load all the videos into the table#
cursor.execute('DROP TABLE IF EXISTS ObjectDetectionVideos')
response = cursor.fetch_all()
response.as_df()
cursor.execute('LOAD VIDEO "ua_detrac.mp4" INTO ObjectDetectionVideos;')
response = cursor.fetch_all()
response.as_df()
| 0 | |
|---|---|
| 0 | Number of loaded VIDEO: 1 |
Visualize Video#
from IPython.display import Video
Video("ua_detrac.mp4", embed=True)
Register YOLO Object Detector an an User-Defined Function (UDF) in EVA#
cursor.execute("""
CREATE UDF IF NOT EXISTS Yolo
TYPE ultralytics
'model' 'yolov8m.pt';
""")
response = cursor.fetch_all()
response.as_df()
| 0 | |
|---|---|
| 0 | UDF Yolo already exists, nothing added. |
Run Object Detector on the video#
cursor.execute("""SELECT id, Yolo(data)
FROM ObjectDetectionVideos
WHERE id < 20""")
response = cursor.fetch_all()
response.as_df()
| objectdetectionvideos.id | yolo.labels | yolo.bboxes | yolo.scores | |
|---|---|---|---|---|
| 0 | 0 | [car, car, car, car, car, car, person, car, ca... | [[829.0, 277.0, 960.0, 360.0], [615.0, 216.0, ... | [0.91, 0.86, 0.85, 0.83, 0.76, 0.73, 0.72, 0.7... |
| 1 | 1 | [car, car, car, car, car, car, car, car, car, ... | [[832.0, 278.0, 960.0, 361.0], [616.0, 216.0, ... | [0.92, 0.85, 0.84, 0.83, 0.78, 0.76, 0.76, 0.7... |
| 2 | 2 | [car, car, car, car, car, car, car, person, ca... | [[836.0, 279.0, 960.0, 362.0], [618.0, 216.0, ... | [0.92, 0.84, 0.84, 0.82, 0.81, 0.75, 0.73, 0.7... |
| 3 | 3 | [car, car, car, car, car, car, car, car, car, ... | [[839.0, 280.0, 960.0, 363.0], [619.0, 217.0, ... | [0.91, 0.84, 0.82, 0.8, 0.8, 0.75, 0.74, 0.72,... |
| 4 | 4 | [car, car, car, car, car, car, car, car, car, ... | [[843.0, 281.0, 960.0, 364.0], [621.0, 218.0, ... | [0.9, 0.85, 0.83, 0.8, 0.76, 0.73, 0.72, 0.72,... |
| 5 | 5 | [car, car, car, car, car, car, person, car, ca... | [[847.0, 282.0, 960.0, 363.0], [623.0, 218.0, ... | [0.89, 0.86, 0.84, 0.8, 0.78, 0.74, 0.72, 0.72... |
| 6 | 6 | [car, car, car, car, car, car, car, person, ca... | [[851.0, 283.0, 959.0, 360.0], [625.0, 219.0, ... | [0.89, 0.87, 0.85, 0.81, 0.79, 0.73, 0.72, 0.7... |
| 7 | 7 | [car, car, car, car, car, car, car, car, car, ... | [[855.0, 284.0, 960.0, 357.0], [626.0, 220.0, ... | [0.9, 0.87, 0.84, 0.83, 0.83, 0.79, 0.73, 0.67... |
| 8 | 8 | [car, car, car, car, car, car, person, car, ca... | [[859.0, 285.0, 960.0, 357.0], [628.0, 221.0, ... | [0.89, 0.88, 0.83, 0.82, 0.79, 0.71, 0.68, 0.6... |
| 9 | 9 | [car, car, car, car, car, car, car, person, ca... | [[863.0, 286.0, 960.0, 357.0], [630.0, 222.0, ... | [0.88, 0.87, 0.84, 0.82, 0.8, 0.75, 0.74, 0.74... |
| 10 | 10 | [car, car, car, car, car, car, car, person, ca... | [[632.0, 223.0, 744.0, 284.0], [867.0, 287.0, ... | [0.88, 0.88, 0.85, 0.82, 0.8, 0.79, 0.76, 0.71... |
| 11 | 11 | [car, car, car, car, car, car, person, car, ca... | [[871.0, 289.0, 960.0, 356.0], [634.0, 223.0, ... | [0.9, 0.9, 0.85, 0.8, 0.79, 0.77, 0.69, 0.68, ... |
| 12 | 12 | [car, car, car, car, car, car, car, person, ca... | [[636.0, 223.0, 750.0, 287.0], [875.0, 290.0, ... | [0.9, 0.88, 0.83, 0.81, 0.78, 0.78, 0.78, 0.67... |
| 13 | 13 | [car, car, car, car, car, car, person, car, ca... | [[171.0, 409.0, 291.0, 539.0], [637.0, 224.0, ... | [0.9, 0.89, 0.89, 0.83, 0.81, 0.81, 0.72, 0.71... |
| 14 | 14 | [car, car, car, car, car, car, person, car, ca... | [[174.0, 405.0, 294.0, 538.0], [885.0, 291.0, ... | [0.9, 0.89, 0.88, 0.84, 0.82, 0.81, 0.75, 0.72... |
| 15 | 15 | [car, car, car, car, car, car, person, car, ca... | [[888.0, 293.0, 960.0, 355.0], [177.0, 400.0, ... | [0.89, 0.88, 0.87, 0.84, 0.82, 0.78, 0.76, 0.7... |
| 16 | 16 | [car, car, car, car, car, car, car, person, ca... | [[893.0, 293.0, 960.0, 355.0], [180.0, 396.0, ... | [0.88, 0.88, 0.87, 0.82, 0.81, 0.76, 0.75, 0.7... |
| 17 | 17 | [car, car, car, car, car, car, car, person, ca... | [[182.0, 392.0, 296.0, 519.0], [897.0, 294.0, ... | [0.9, 0.89, 0.87, 0.83, 0.82, 0.78, 0.72, 0.69... |
| 18 | 18 | [car, car, car, car, car, car, car, person, mo... | [[901.0, 295.0, 960.0, 356.0], [647.0, 225.0, ... | [0.88, 0.88, 0.83, 0.82, 0.8, 0.78, 0.75, 0.7,... |
| 19 | 19 | [car, car, car, car, car, person, car, car, ca... | [[648.0, 226.0, 770.0, 293.0], [906.0, 297.0, ... | [0.89, 0.87, 0.81, 0.8, 0.78, 0.77, 0.73, 0.72... |
Visualizing output of the Object Detector on the video#
import cv2
from pprint import pprint
from matplotlib import pyplot as plt
def annotate_video(detections, input_video_path, output_video_path):
color1=(207, 248, 64)
color2=(255, 49, 49)
thickness=4
vcap = cv2.VideoCapture(input_video_path)
width = int(vcap.get(3))
height = int(vcap.get(4))
fps = vcap.get(5)
fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v') #codec
video=cv2.VideoWriter(output_video_path, fourcc, fps, (width,height))
frame_id = 0
# Capture frame-by-frame
# ret = 1 if the video is captured; frame is the image
ret, frame = vcap.read()
while ret:
df = detections
df = df[['yolo.bboxes', 'yolo.labels']][df.index == frame_id]
if df.size:
dfLst = df.values.tolist()
for bbox, label in zip(dfLst[0][0], dfLst[0][1]):
x1, y1, x2, y2 = bbox
x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
# object bbox
frame=cv2.rectangle(frame, (x1, y1), (x2, y2), color1, thickness)
# object label
cv2.putText(frame, label, (x1, y1-10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, color1, thickness)
# frame label
cv2.putText(frame, 'Frame ID: ' + str(frame_id), (700, 500), cv2.FONT_HERSHEY_SIMPLEX, 1.2, color2, thickness)
video.write(frame)
# Stop after twenty frames (id < 20 in previous query)
if frame_id == 20:
break
# Show every fifth frame
if frame_id % 5 == 0:
plt.imshow(frame)
plt.show()
frame_id+=1
ret, frame = vcap.read()
video.release()
vcap.release()
from ipywidgets import Video, Image
input_path = 'ua_detrac.mp4'
output_path = 'video.mp4'
dataframe = response.as_df()
annotate_video(dataframe, input_path, output_path)
Video.from_file(output_path)
Dropping an User-Defined Function (UDF)#
cursor.execute("DROP UDF IF EXISTS Yolo;")
response = cursor.fetch_all()
response.as_df()
| 0 | |
|---|---|
| 0 | UDF Yolo successfully dropped |