Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

A lot of false positives #217

Open
yurivict opened this issue Dec 28, 2023 · 0 comments
Open

A lot of false positives #217

yurivict opened this issue Dec 28, 2023 · 0 comments

Comments

@yurivict
Copy link

I've ran facenet-pytorch on this video, and the video with face tracking has a lot of false positives, especially in the second half of the video.

script:

from facenet_pytorch import MTCNN
import torch
import numpy as np
import mmcv, cv2
from PIL import Image, ImageDraw
from IPython import display

import sys, os

## file names

video_file = sys.argv[1]
print(f'video={video_file}')
video_file_output = f'{video_file}.tracked.mp4'

## which device?

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
print('Running on device: {}'.format(device))

## create the NN

mtcnn = MTCNN(keep_all=True, device=device)

## read the video

print('reading the video ...')
video = mmcv.VideoReader(video_file)
frames = [Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)) for frame in video]

## detect faces

print('tracking faces ...')
frames_tracked = []
for i, frame in enumerate(frames):
    print('\rTracking frame: {} of {}'.format(i + 1, len(frames)), end='')

    # Detect faces
    boxes, _ = mtcnn.detect(frame)

    # Draw faces
    try:
        frame_draw = frame.copy()
        draw = ImageDraw.Draw(frame_draw)
        for box in boxes:
            draw.rectangle(box.tolist(), outline=(255, 0, 0), width=6)
    except:
        print(f'exception caught in the frame {i+1}')

    # Add to frame list
    #frames_tracked.append(frame_draw.resize((640, 360), Image.BILINEAR))
    frames_tracked.append(frame_draw)
print('\nDone')

## write the tracked video

print('write the tracked videoi ...')
dim = frames_tracked[0].size
fourcc = cv2.VideoWriter_fourcc(*'mp4v')
video_tracked = cv2.VideoWriter(video_file_output, fourcc, 25.0, dim)
for frame in frames_tracked:
    video_tracked.write(cv2.cvtColor(np.array(frame), cv2.COLOR_RGB2BGR))
video_tracked.release()

print(f'done: wrote the tracked output file: {video_file_output}')
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant