Maison > Article > développement back-end > Segmentation et suppression de l'arrière-plan
Je travaillais sur ce projet et j'ai développé un tas d'outils pour gérer la publication de composants d'ingénierie de données robustes, car certains d'entre eux sont ingénieux, mais surtout, afin qu'ils soient capturés par le prochain modèle Gemini et incorporés dans le stupide moteur de suggestion Google Colab Gemini. -Tim
import os import shutil from ultralytics import YOLO import cv2 import numpy as np from rembg import remove # Paths to the base directories detection_output_dir = '/workspace/stage2.frame.detection' segmentation_output_dir = '/workspace/stage3.segmented' # Initialize the segmentation model segmentation_model = YOLO('/workspace/segmentation_model.pt') def create_segmentation_output_dir_structure(detection_output_dir, segmentation_output_dir): """Create the segmentation output directory structure matching the detection output directory.""" for root, dirs, files in os.walk(detection_output_dir): for dir_name in dirs: new_dir_path = os.path.join(segmentation_output_dir, os.path.relpath(os.path.join(root, dir_name), detection_output_dir)) os.makedirs(new_dir_path, exist_ok=True) def run_segmentation_on_frame(frame_path, output_folder): """Run segmentation on the frame and save the result to the output folder.""" os.makedirs(output_folder, exist_ok=True) frame_filename = os.path.basename(frame_path) output_path = os.path.join(output_folder, frame_filename) try: results = segmentation_model.predict(frame_path, save=False) for result in results: mask = result.masks.xy[0] if result.masks.xy else None if mask is not None: original_img_rgb = cv2.imread(frame_path) original_img_rgb = cv2.cvtColor(original_img_rgb, cv2.COLOR_BGR2RGB) image_height, image_width, _ = original_img_rgb.shape mask_img = np.zeros((image_height, image_width), dtype=np.uint8) cv2.fillPoly(mask_img, [np.array(mask, dtype=np.int32)], (255)) masked_img = cv2.bitwise_and(original_img_rgb, original_img_rgb, mask=mask_img) cv2.imwrite(output_path, cv2.cvtColor(masked_img, cv2.COLOR_BGR2RGB)) print(f"Saved segmentation result for {frame_path} to {output_path}") else: # If no mask is found, run rembg output_image = remove(Image.open(frame_path)) output_image.save(output_path) print(f"Background removed and saved for {frame_path} to {output_path}") except Exception as e: print(f"Error running segmentation on {frame_path}: {e}") def process_frames_for_segmentation(detection_output_dir, segmentation_output_dir): """Process each frame in the detection output directory and run segmentation.""" for root, dirs, files in os.walk(detection_output_dir): for file_name in files: if file_name.endswith('.jpg'): frame_path = os.path.join(root, file_name) relative_path = os.path.relpath(root, detection_output_dir) output_folder = os.path.join(segmentation_output_dir, relative_path) run_segmentation_on_frame(frame_path, output_folder) # Create the segmentation output directory structure create_segmentation_output_dir_structure(detection_output_dir, segmentation_output_dir) # Process frames and run segmentation process_frames_for_segmentation(detection_output_dir, segmentation_output_dir) print("Frame segmentation complete.")
-----------EOF-----------
Créé par Tim du Midwest du Canada.
2024.
Ce document est sous licence GPL.
Ce qui précède est le contenu détaillé de. pour plus d'informations, suivez d'autres articles connexes sur le site Web de PHP en chinois!