Object Tracking In Motion

-

Drive Link:  https://drive.google.com/drive/folders/1USa7N0JCIeGGhZhkKP18-QuziOzh8riX?usp=share_link


Code for Single object Tracking:

import cv2
import imutils

TrDict = {'csrt': cv2.TrackerCSRT_create,
         'kcf' : cv2.TrackerKCF_create,
         'boosting' : cv2.TrackerBoosting_create,
         'mil': cv2.TrackerMIL_create,
         'tld': cv2.TrackerTLD_create,
         'medianflow': cv2.TrackerMedianFlow_create,
         'mosse':cv2.TrackerMOSSE_create}

tracker = TrDict['csrt']()
#tracker = cv2.TrackerCSRT_create()

v = cv2.VideoCapture(r'mot.mp4')


ret, frame = v.read()
#frame = imutils.resize(frame,width=600)
cv2.imshow('Frame',frame)
bb = cv2.selectROI('Frame',frame)
tracker.init(frame,bb)


while True:
    ret, frame = v.read()
    if not ret:
        break
    #frame = imutils.resize(frame,width=600)
    (success,box) = tracker.update(frame)
    if success:
        (x,y,w,h) = [int(a) for a in box]
        cv2.rectangle(frame,(x,y),(x+w,y+h),(100,255,0),2)
    cv2.imshow('Frame',frame)
    key = cv2.waitKey(5) & 0xFF
    if key == ord('q'):
        break
v.release()
cv2.destroyAllWindows()


Code for Multiple Object Tracking:

import cv2
import numpy as np

TrDict = {'csrt': cv2.TrackerCSRT_create,
         'kcf' : cv2.TrackerKCF_create,
         'boosting' : cv2.TrackerBoosting_create,
         'mil': cv2.TrackerMIL_create,
         'tld': cv2.TrackerTLD_create,
         'medianflow': cv2.TrackerMedianFlow_create,
         'mosse':cv2.TrackerMOSSE_create}

trackers = cv2.legacy.MultiTracker_create()

v = cv2.VideoCapture(r'mot.mp4')

ret, frame = v.read()

k = 4
for i in range(k):
    cv2.imshow('Frame',frame)
    bbi = cv2.selectROI('Frame',frame)
    tracker_i = TrDict['csrt']()
    trackers.add(cv2.legacy.TrackerCSRT_create(),frame,bbi)


frameNumber = 2
baseDir = r'TrackingResults'

while True:
    ret, frame = v.read()
    if not ret:
        break
    (success,boxes) = trackers.update(frame)
    np.savetxt(baseDir + '/frame_'+str(frameNumber)+'.txt',boxes,fmt='%f')
    frameNumber+=1
    for box in boxes:
        (x,y,w,h) = [int(a) for a in box]
        cv2.rectangle(frame,(x,y),(x+w,y+h),(0,0,255),2)
       
    cv2.imshow('Frame',frame)
    key = cv2.waitKey(5) & 0xFF
    if key == ord('q'):
        break
v.release()
cv2.destroyAllWindows()


boxes = np.loadtxt(r'TrackingResults\frame_102.txt')

boxes

Comments

  1. Janki Devi Vocational CentreAugust 15, 2025 at 8:20 PM

    Amazing blog you are my inspiration how to write informatic blog about computer courses google skills.
    Thanks such loving blogs.
    Best Fine art Institute in Delhi
    Best Computer Institute in Delhi

    ReplyDelete

Post a Comment

Popular posts from this blog

Assignment 4: Canny Edge Detection

-
Image
Image Link:  https://drive.google.com/drive/folders/1USa7N0JCIeGGhZhkKP18-QuziOzh8riX?usp=share_link Canny Edge Detection Algorithm Basic Code: import cv2 import matplotlib.pyplot as plt import numpy as np imPth = r ' c m.jpg' img = plt.imread(imPth) plt.imshow(img, cmap = 'gray' ) E = cv2.Canny(img, 150 , 250 ) plt.subplot( 121 ) plt.imshow(img, cmap = 'gray' ) plt.axis( 'off' ) plt.subplot( 122 ) plt.imshow(E, cmap = 'gray' ) plt.axis( 'off' ) plt.show() Gaussian filter x = 0 y = - 1 sigma = 1 v = ( 1 /( 2 *np.pi*(sigma** 2 )))*np.exp(-(x** 2 + y** 2 )/( 2 *(sigma** 2 ))) v def f_getGaussianFilter ( s , sigma ):     maxX = s// 2     minX = -maxX     minY = minX     maxY = maxX     G = np.zeros((s,s))     for x in range (minX,maxX+ 1 ):         for y in range (minY,maxY+ 1 ):             v = ( 1 /( 2 *np.pi*(sigma** 2 )))*np.exp(-(x** 2 + y** 2 )/( 2 *(sigma** ...
Read more

Assignment 5 (Sutherland polygon clipping)

-
Image
Aim:  Implement Cohen Sutherland polygon clipping method to clip the polygon with respect the view-port and window. Use mouse click, keyboard interface Theory:  Line Clipping – Cohen Sutherland   In computer graphics, ' line clipping' is the process of removing lines or portions of lines outside of an area of interest. Typically, any line or part thereof which is outside of the viewing area is removed. The Cohen–Sutherland algorithm is a computer graphics algorithm used for line clipping. The algorithm divides a two-dimensional space into 9 regions (or a three-dimensional space into 27 regions), and then efficiently determines the lines and portions of lines that are visible in the center region of interest (the viewport). The algorithm was developed in 1967 during flight simulator work by Danny Cohen and Ivan Sutherland The design stage includes, excludes or partially includes the line based on where: Both endpoints are in the viewport region (bitwise OR...
Read more

Assignment 5: Hough transform Line and Circle

-
Image Link:  https://drive.google.com/drive/folders/1USa7N0JCIeGGhZhkKP18-QuziOzh8riX?usp=share_link Code Line:  import cv2 import numpy as np img = cv2.imread('sudoku.png') gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) edges = cv2.Canny(gray, 50, 150, apertureSize=3) lines = cv2.HoughLines(edges, 1, np.pi / 180, 200) for line in lines:     rho,theta = line[0]     a = np.cos(theta)     b = np.sin(theta)     x0 = a * rho     y0 = b * rho     # x1 stores the rounded off value of (r * cos(theta) - 1000 * sin(theta))     x1 = int(x0 + 1000 * (-b))     # y1 stores the rounded off value of (r * sin(theta)+ 1000 * cos(theta))     y1 = int(y0 + 1000 * (a))     # x2 stores the rounded off value of (r * cos(theta)+ 1000 * sin(theta))     x2 = int(x0 - 1000 * (-b))     # y2 stores the rounded off value of (r * sin(theta)- 1000 * cos(theta))     y2 = int(y0 - 10...
Read more