GoFuckYourself.com - Adult Webmaster Forum - real time object detection?

- Fucking Around & Business Discussion (https://gfy.com/forumdisplay.php?f=26)

- - real time object detection? (https://gfy.com/showthread.php?t=1375680)

real time object detection?

Using old haar cascades with opencv, but getting lots of false face detections. Got any other recommendations?

Do you use a threshold?
If yes be more strict

with a proper settings of tresholds you can get some better results.
but it is better to choose other methods if equipment afford that

If you aren't doing small objects, YOLO is a good object detection algorithm

Try using Dlib’s face detector, MTCNN, or deep learning-based models such as OpenCV’s DNN module with pre-trained models (e.g., ResNet-based face detectors). Check scaleFactor and minNeighbors settings.

Quote:

Originally Posted by 2MuchMark (Post 23267156)

Yea, I have read about Dlib. I want to use on my laptop. You think it will run with real time video.

Thanks for all responses so far.

Quote:

Originally Posted by 2MuchMark (Post 23267156)

Yea, I have read about Dlib. I want to use on my laptop. You think it will run with real time video.

Thanks for all responses so far.

I used the example facedetect.py . Add a target box, when a face enters the box
moves a servo. Polulu Maestro servo controller.

Code:

import cv2

import os

import time



cmdpull = "/home/walter/maestro-linux/UscCmd --servo 5,7000"

cmdreturn = "/home/walter/maestro-linux/UscCmd --servo 5,6000"



# Load the cascade

face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')



# To capture video from webcam. 

cap = cv2.VideoCapture(2)

# To use a video file as input 

# cap = cv2.VideoCapture('filename.mp4')



while True:

    # Read the frame

    _, img = cap.read()

    # Convert to grayscale

    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

    # Detect the faces

    faces = face_cascade.detectMultiScale(gray, 1.1, 4)

   #create region of interest box and dot

    cv2.rectangle(img, (100, 100), (180, 180), (0, 0, 255), 2)

    cv2.line(img, (140, 140), (140, 140), (0, 255, 0), 5) 

    # Draw the rectangle around each face

    for (x, y, w, h) in faces:

        cv2.rectangle(img, (x, y), (x+w, y+h), (255, 0, 0), 2)

    #if face is in middle of the screen - region of interest

        if x > 100 and x < 180 and y > 100 and y < 180:

            print ("x: ",x)

            print ("y: ",y)

            time.sleep(.1)

            os.system(cmdpull)

            time.sleep(.1)

            os.system(cmdreturn)

    # Display

    cv2.imshow('img', img)

    # Stop if escape key is pressed

    k = cv2.waitKey(30) & 0xff

    if k==27:

        break

# Release the VideoCapture object

cap.release()

Quote:

Originally Posted by Colmike9 (Post 23267076)

If you aren't doing small objects, YOLO is a good object detection algorithm

Looking at YOLOv8 tutorials now. Thanks.

Scratch that for now. Will need a gpu. Having fun watching tutorials though. Now I know what Elon and that other guy were talking about when they mention Distributed Neural Network.