import os os.environ["OPENCV_VIDEOIO_MSMF_ENABLE_HW_TRANSFORMS"] = "0" import cv2 import numpy as np from orisys import Sensor def draw_arrows_fade(img, flow, depth, depth_scale=0.5, grid_spacing=40, arrow_scale=1.0, threshold=5.0): """ Draw optical flow arrows on image with transparency based on magnitude. Args: img: Input image (BGR or grayscale) flow: Optical flow field with shape (flow_height, flow_width, 2) grid_spacing: Spacing between arrows in pixels (default: 20) arrow_scale: Scale factor for arrow length (default: 1.0) threshold: Minimum flow magnitude to display arrow (default: 0.0) Returns: Image with arrows drawn, blended with original image """ depth_img = cv2.applyColorMap(((depth+1)*depth_scale* 255.0).astype('uint8'), cv2.COLORMAP_HOT) # Make a copy of the image img_copy = depth_img.copy() # Convert grayscale to BGR if needed if len(img_copy.shape) == 2 or img_copy.shape[2] == 1: img_copy = cv2.cvtColor(img_copy, cv2.COLOR_GRAY2BGR) # Get image and flow dimensions img_height, img_width = img_copy.shape[:2] flow_height, flow_width = flow.shape[:2] # Calculate scaling factors between image and flow dimensions scale_x = img_width / flow_width scale_y = img_height / flow_height # Create grid positions in flow coordinates grid_y, grid_x = np.mgrid[grid_spacing//2:flow_height:grid_spacing, grid_spacing//2:flow_width:grid_spacing] # Flatten grid positions grid_y_flat = grid_y.flatten() grid_x_flat = grid_x.flatten() # Get flow vectors at grid positions flow_vectors = flow[grid_y_flat, grid_x_flat, :] # Shape: (n_points, 2) # Calculate flow magnitudes magnitudes = np.linalg.norm(flow_vectors, axis=1) # Filter arrows by threshold: only show arrows above threshold valid_mask = magnitudes >= threshold # Normalize magnitudes to 0-1 range for alpha blending # Zero magnitude = transparent, higher magnitude = more opaque white max_magnitude = magnitudes.max() if magnitudes.max() > 0 else 1.0 alpha_values = magnitudes / max_magnitude # Scale grid positions to image coordinates img_grid_x = (grid_x_flat * scale_x).astype(np.int32) img_grid_y = (grid_y_flat * scale_y).astype(np.int32) # Scale flow vectors to image coordinates scaled_flow_x = flow_vectors[:, 0] * scale_x / arrow_scale scaled_flow_y = flow_vectors[:, 1] * scale_y / arrow_scale # Calculate arrow endpoints end_x = (img_grid_x + scaled_flow_x).astype(np.int32) end_y = (img_grid_y + scaled_flow_y).astype(np.int32) # Create overlay image with white background for arrows overlay = np.zeros_like(img_copy) # Create weight map for blending based on arrow presence and magnitude weight_map = np.zeros((img_height, img_width), dtype=np.float32) # Draw arrows on overlay with white color and build weight map for i in range(len(img_grid_x)): # Skip if magnitude is below threshold if not valid_mask[i]: continue # Check bounds if (0 <= img_grid_x[i] < img_width and 0 <= img_grid_y[i] < img_height and 0 <= end_x[i] < img_width and 0 <= end_y[i] < img_height): # Get alpha value (0 = transparent, 1 = opaque white) alpha = alpha_values[i] # Skip if magnitude is zero (transparent) if alpha <= 0: continue # Calculate arrow thickness based on magnitude thickness = max(1, int(1 + 2 * alpha)) # White color for arrows color = (255, 255, 255) # Draw arrow on overlay cv2.arrowedLine(overlay, (img_grid_x[i], img_grid_y[i]), (end_x[i], end_y[i]), color, thickness=thickness, tipLength=0.3) # Create a line mask for this arrow in the weight map line_mask = np.zeros((img_height, img_width), dtype=np.float32) cv2.line(line_mask, (img_grid_x[i], img_grid_y[i]), (end_x[i], end_y[i]), 1.0, thickness=thickness) # Add arrow tip approximation cv2.circle(line_mask, (end_x[i], end_y[i]), thickness, 1.0, -1) # Weight by alpha (magnitude) - use maximum for overlapping arrows weight_map = np.maximum(weight_map, line_mask * alpha) # Expand weight map to 3 channels weight_map_3ch = np.stack([weight_map] * 3, axis=2) # Blend: result = original * (1 - weight) + overlay * weight result = (img_copy.astype(np.float32) * (1 - weight_map_3ch) + overlay.astype(np.float32) * weight_map_3ch) return result.astype(np.uint8) def main(): global start_time # 打开视频 sensor1 = Sensor("./s1.mp4",isstitch=True,cuda = True,verbose = True) # 打开摄像头 # sensor1 = Sensor(0,isstitch=True,cuda = True,verbose = True) while True: sensor1.get_img() # 提取并拼接复眼图像 sensor1.compute_deformation() # 计算形变和分解 # 提取信息： # 向量场: VRAW, VNORMAL, VSHEAR: 原始，法向，切向 # 帧率，时间戳: FPS, TIMESTAMP # 变形量总和: FNORMAL , FSHEARX, FSHEARY : 法向，切向（X)，切向（Y) fps, fn, fx, fy, flow, depth = sensor1.read_info(sensor1.info.FPS, sensor1.info.FNORMAL, sensor1.info.FSHEARX, sensor1.info.FSHEARY, sensor1.info.VRAW, sensor1.info.DEPTH) arrows = draw_arrows_fade(sensor1.img, flow, depth) print(fps,np.min(depth),np.mean(depth)) cv2.imshow("Deformation", arrows) key = cv2.waitKey(1) if key & 0xFF == ord("q"): print("\n 停止程序") break sensor1.disconnect() # 断开传感器连接 if __name__ == '__main__': main()