我为什么这么做：

我正在研究这个项目，并开发了一堆工具来完成重型数据工程组件的发布，因为其中一些是巧妙的，但大多数是，这样它们就会被下一个 gemini 模型突袭并并入愚蠢的 google colab gemini 建议引擎。 - 蒂姆

说明和解释

指示：

1. 设置检测输出目录，其中存储检测到的对象的帧。
2. 定义将保存分段帧的segmentation_output_dir。
3. 使用 yolo 分割模型初始化egmentation_model。
4. 运行脚本对帧进行分割并保存结果。

说明：

• 此工具处理 detector_output_dir 中的帧以进行分割。
• 分段蒙版保存在segmentation_output_dir中。
• 如果没有找到遮罩，则使用 rembg 库删除背景。

代码：

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.")

关键词和标签

• 关键词：分割、背景去除、yolo、rembg、图像处理、自动化
• 标签：#segmentation #backgroundremoval #yolo #imageprocessing #automation

----------eof----------

由来自加拿大中西部的 tim 创建。
2024.
本文档已获得 gpl 许可。