Tracking objects remembering original IDs - opencv

Question

Problem Statement: I have generated a video from data to images of ANSYS Simulation of vortices formed due to flat plate plunging. The video contains vortices (in simpler terms blobs), which are ever evolving (dissociating and merging).
Sample video
Objective: The vortices are needed to be identified and labelled such that the consistency of the label is maintained. If a certain vortex has been given a label in the previous frame its label remains the same. If it dissociates the larger component (parent) should retain the same label whereas the smaller component gets a new label. If it merges then the label of larger of the two should be given to them.
Attempt: I have written a function which detects object boundary (contour detection) and then finds the center of the identiied contour. Further mapping the centroid to the one closest in the next frame provided the distance is less than certain threshold.
Attempted tracking video
Tracking algorithm:
import math
class EuclideanDistTracker:
def __init__(self):
# Store the center positions of the objects
self.center_points = {}
# Keep the count of the IDs
# each time a new object id detected, the count will increase by one
self.id_count = 0
def update(self, objects_rect):
# Objects boxes and ids
objects_bbs_ids = []
# Get center point of new object
for rect in objects_rect:
x, y, w, h = rect
cx = (x + x + w) // 2
cy = (y + y + h) // 2
# Find out if that object was detected already
same_object_detected = False
for id, pt in self.center_points.items():
dist = math.hypot(cx - pt[0], cy - pt[1])
if dist < 20: # Threshold
self.center_points[id] = (cx, cy)
print(self.center_points)
objects_bbs_ids.append([x, y, w, h, id])
same_object_detected = True
break
# New object is detected we assign the ID to that object
if same_object_detected is False:
self.center_points[self.id_count] = (cx, cy)
objects_bbs_ids.append([x, y, w, h, self.id_count])
self.id_count += 1
# Clean the dictionary by center points to remove IDS not used anymore
new_center_points = {}
for obj_bb_id in objects_bbs_ids:
_, _, _, _, object_id = obj_bb_id
center = self.center_points[object_id]
new_center_points[object_id] = center
# Update dictionary with IDs not used removed
self.center_points = new_center_points.copy()
return objects_bbs_ids
Implementing tracking algorithm to the sample video:
import cv2
import numpy as np
from tracker import *
# Create tracker object
tracker = EuclideanDistTracker()
cap = cv2.VideoCapture("Video Source")
count = 0
while True:
ret, frame = cap.read()
print("\n")
if(count != 0):
print("Frame Count: ", count)
frame = cv2.resize(frame, (0, 0), fx = 1.5, fy = 1.5)
height, width, channels = frame.shape
# 1. Object Detection
hsvFrame = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
sensitivity = 20
white_lower = np.array([0,0,255-sensitivity])
white_upper = np.array([255,sensitivity,255])
white_mask = cv2.inRange(hsvFrame, white_lower, white_upper)
# Morphological Transform, Dilation
kernal = np.ones((3, 3), "uint8")
c = 1
contours_w, hierarchy_w = cv2.findContours(white_mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_NONE)
detections = []
for contour_w in contours_w:
area = cv2.contourArea(contour_w)
if area > 200 and area < 100000:
cv2.drawContours(frame, [contour_w], -1, (0, 0, 0), 1)
x,y,w,h = cv2.boundingRect(contour_w)
detections.append([x, y, w, h])
# 2. Object Tracking
boxes_ids = tracker.update(detections)
for box_id in boxes_ids:
x, y, w, h, id = box_id
cv2.putText(frame, str(id), (x - 8, y + 8), cv2.FONT_HERSHEY_PLAIN, 2, (0, 0, 0), 2)
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 0, 0), 1)
cv2.imshow("Frame", frame)
count += 1
key = cv2.waitKey(0)
if key == 27:
break
cap.release()
cv2.destroyAllWindows()
Problem: I was able to implement continuous labelling but the problem is that the objective of retaining label for the parent vortex is not maintained. (As seen from time (t) = 0s to 9s, the largest vortex is given a label = 3, whereas from t = 9s it is given label = 9. I want that to remain as label = 3 in Attempted tracking video). Any suggestions would be helpful and guide if I am on the right track or should I use some other standard tracking algorithm or any deep learning algorithm.
PS: Sorry for the excessive text but stackoverflow denied me putting just link of the codes.