Template Matching and Tracking

import os, sys import cv2 import numpy as np import matplotlib.pyplot as plt

slope, offset = 3, 1.5 x = np.random.rand(200)*2 y = slope*x + offset + np.random.randn(200)*0.2 X = np.stack([x, np.ones_like(x)]).T w_est, residuals, rank, singular_values = np.linalg.lstsq(X, y) print(w_est) # Equivalently # w_est = np.linalg.solve(X.T @ X, X.T @ y) slope_est, offset_est = w_est plt.figure(figsize=(6, 10)) plt.scatter(x, y, color='k', alpha=0.2) plt.plot(x, slope*x + offset, 'g--') plt.plot(x, slope_est*x + offset_est, 'b-.', alpha=0.5)

full_image = cv2.cvtColor(cv2.imread("/work/images/Wheres_Waldo_Full.png"), cv2.COLOR_BGR2RGB) waldo_image = cv2.cvtColor(cv2.imread("/work/images/Wheres_Waldo_Waldo.png"), cv2.COLOR_BGR2RGB) image = full_image.astype(np.float32)/255 kernel = waldo_image.astype(np.float32)/255 fig, ax = plt.subplots(1,2,figsize=(12, 6)) ax[0].imshow(image) ax[1].imshow(kernel) # waldo_filter = cv2.filter2D(image, -1, kernel, borderType=cv2.BORDER_CONSTANT) # See here: https://docs.opencv.org/3.4/de/da9/tutorial_template_matching.html waldo_template_match = cv2.matchTemplate(image, kernel, cv2.TM_CCOEFF_NORMED) waldo_position = np.abs(waldo_template_match) print(f"Mean: {np.mean(waldo_position)}, Std: {np.std(waldo_position)}, [Min, Max]: [{np.min(waldo_position)}, {np.max(waldo_position)}]") plt.figure(figsize=(20,10)) print(waldo_position.shape) viz = np.tile(np.pad(waldo_position / np.max(waldo_position), [[20, 19], [20, 19]])[:,:,None], (1, 1, 3)) plt.imshow(0.9*viz + 0.1 * image) y, x = np.unravel_index(waldo_position.argmax(), waldo_position.shape) print(x, y) plt.scatter(x+20, y+20, s=400, color='r', marker='o', facecolors='none')

# From the Project 1 code def get_num_frames(input_filename): cap = cv2.VideoCapture(input_filename) # try the fast way nframes = cap.get(cv2.CAP_PROP_FRAME_COUNT) width = cap.get(cv2.CAP_PROP_FRAME_WIDTH) height = cap.get(cv2.CAP_PROP_FRAME_HEIGHT) fps = cap.get(cv2.CAP_PROP_FPS) if not fps > 1: # fps buggy sometimes fps = 30.0 if nframes > 1 and width > 1 and height > 1: # it worked return int(nframes), int(width), int(height), fps # the slow way cnt = 0 while True: ok, frame = cap.read() if not ok or frame is None: break height, width = frame.shape[:2] cnt += 1 return cnt, width, height, fps ### Code to read and write videos input_filename = '/work/images/Rubiks_Tracking.MOV' if not os.path.exists(input_filename): print('error:', input_filename, 'does not exist') sys.exit(1) # Create the output video path_prefix, basename = os.path.split(input_filename) basename, _ = os.path.splitext(basename) # Get video properties nframes, width, height, fps = get_num_frames(input_filename) # Create output writer # fourcc, ext = (cv2.VideoWriter_fourcc('m', 'p', '4', 'v'), 'mp4') # output_filename = os.path.join(path_prefix, basename + '_captured.' + ext) # writer = cv2.VideoWriter(output_filename, fourcc, fps, (width, height)) # Write out frames cap = cv2.VideoCapture(input_filename) fig, ax = plt.subplots(2, 5, figsize=(5*4, 2*6)) myframes = [] for frame_idx in range(nframes): # Get 10 frames ok, frame = cap.read() frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB) if frame_idx > 85 and len(myframes) < 10: myframes.append(frame) if not ok or frame is None or len(myframes) >= 10: break for i in range(len(myframes)): if i < 5: ax[0, i % 5].imshow(myframes[i]) else: ax[1, i % 5].imshow(myframes[i]) print(f"Total number of frames: {frame_idx}") cap.release()

# Select frames cur_frame = np.mean(myframes[0]/255.0, -1) next_frame = np.mean(myframes[1]/255.0, -1) # Make template y0, x0, h, w = 750, 430, 220, 350 template = cur_frame[y0:y0+h, x0:x0+w].copy() plt.figure(figsize=(3, 4)) plt.imshow(template) # Draw bounding box bbox_img = cv2.rectangle(cur_frame.copy(), (x0, y0), (x0+w, y0+h), 1, 10) fig, ax = plt.subplots(1, 2, figsize=(2*3, 4)) ax[0].imshow(bbox_img) ax[1].imshow(next_frame)

fig, ax = plt.subplots(1,3,figsize=(3*4,6)) ErrorI = (cur_frame[y0:y0+h, x0:x0+w] -next_frame[y0:y0+h, x0:x0+w]) Ix, Iy = cv2.Sobel(cur_frame[y0:y0+h, x0:x0+w], -1, 1, 0), cv2.Sobel(cur_frame[y0:y0+h, x0:x0+w], -1, 0, 1) ax[0].imshow(np.abs(ErrorI)) ax[1].imshow(np.abs(Ix)) ax[2].imshow(np.abs(Iy))