UAV/utils/odm_monitor.py

import os
import time
import logging
import subprocess
from typing import Dict, Tuple
import pandas as pd
import numpy as np
from osgeo import gdal


class NotOverlapError(Exception):
    """图像重叠度不足异常"""
    pass


class DockerNotRunError(Exception):
    """Docker未启动异常"""
    pass


class DockerShareError(Exception):
    """Docker目录共享异常"""
    pass


class OutOfMemoryError(Exception):
    """内存不足异常"""
    pass


class StrangeValuesError(Exception):
    """异常值异常"""
    pass


class ODMProcessMonitor:
    """ODM处理监控器"""

    def __init__(self, output_dir: str, mode: str = "快拼模式"):
        self.output_dir = output_dir
        self.logger = logging.getLogger('UAV_Preprocess.ODMMonitor')
        self.mode = mode

    def _check_success(self, grid_dir: str) -> bool:
        """检查ODM是否执行成功

        检查项目:
        1. 必要的文件夹是否存在
        2. 正射影像是否生成且有效
        3. 正射影像文件大小是否正常
        """
        # 检查必要文件夹
        success_markers = ['odm_orthophoto']
        if self.mode != "快拼模式":
            success_markers.extend(['odm_texturing', 'odm_georeferencing'])

        if not all(os.path.exists(os.path.join(grid_dir, 'project', marker)) for marker in success_markers):
            self.logger.error("必要的文件夹未生成")
            return False

        # 检查正射影像文件
        ortho_path = os.path.join(
            grid_dir, 'project', 'odm_orthophoto', 'odm_orthophoto.original.tif')
        if not os.path.exists(ortho_path):
            self.logger.error("正射影像文件未生成")
            return False

        # 检查文件大小
        file_size_mb = os.path.getsize(ortho_path) / (1024 * 1024)  # 转换为MB
        if file_size_mb < 1:
            self.logger.error(f"正射影像文件过小: {file_size_mb:.2f}MB")
            return False

        try:
            # 打开影像文件
            ds = gdal.Open(ortho_path)
            if ds is None:
                self.logger.error("无法打开正射影像文件")
                return False

            # 读取第一个波段
            band = ds.GetRasterBand(1)

            # 获取统计信息
            stats = band.GetStatistics(False, True)
            if stats is None:
                self.logger.error("无法获取影像统计信息")
                return False

            min_val, max_val, mean, std = stats

            # 计算空值比例
            no_data_value = band.GetNoDataValue()
            array = band.ReadAsArray()
            if no_data_value is not None:
                no_data_ratio = np.sum(array == no_data_value) / array.size
            else:
                no_data_ratio = 0

            # 检查空值比例是否过高（超过50%）
            if no_data_ratio > 0.5:
                self.logger.error(f"正射影像空值比例过高: {no_data_ratio:.2%}")
                return False

            # 检查影像是否全黑或全白
            if max_val - min_val < 1:
                self.logger.error("正射影像可能无效：像素值范围过小")
                return False

            ds = None  # 关闭数据集
            return True

        except Exception as e:
            self.logger.error(f"检查正射影像时发生错误: {str(e)}")
            return False

    def run_odm_with_monitor(self, grid_dir: str, grid_id: tuple, fast_mode: bool = True, produce_dem: bool = False) -> Tuple[bool, str]:
        """运行ODM命令"""
        if produce_dem and fast_mode:
            self.logger.error("快拼模式下无法生成DEM，请调整生产参数")
            return False, "快拼模式下无法生成DEM，请调整生产参数"

        self.logger.info(f"开始处理网格 ({grid_id[0]},{grid_id[1]})")
        max_retries = 3
        current_try = 0
        use_lowest_quality = True  # 初始使用lowest quality

        while current_try < max_retries:
            current_try += 1
            self.logger.info(
                f"第 {current_try} 次尝试处理网格 ({grid_id[0]},{grid_id[1]})")

            try:
                # 构建Docker命令
                grid_dir = grid_dir[0].lower()+grid_dir[1:].replace('\\', '/')
                docker_command = (
                    f"docker run --gpus all -ti --rm "
                    f"-v {grid_dir}:/datasets "
                    f"opendronemap/odm:gpu "
                    f"--project-path /datasets project "
                    f"--max-concurrency 15 "
                    f"--force-gps "
                )

                # 根据是否使用lowest quality添加参数
                if use_lowest_quality:
                    docker_command += f"--feature-quality lowest "

                docker_command += f"--orthophoto-resolution 10 "

                if produce_dem:
                    docker_command += (
                        f"--dsm "
                        f"--dtm "
                    )

                if fast_mode:
                    docker_command += (
                        f"--fast-orthophoto "
                        f"--skip-3dmodel "
                    )

                docker_command += "--rerun-all"
                self.logger.info(docker_command)

                result = subprocess.run(
                    docker_command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
                stdout, stderr = result.stdout.decode(
                    'utf-8'), result.stderr.decode('utf-8')

                stdout_lines = stdout.strip().split('\n')
                last_lines = '\n'.join(
                    stdout_lines[-50:] if len(stdout_lines) > 10 else stdout_lines)
                self.logger.info(f"==========stdout==========: {last_lines}")

                if stderr:
                    self.logger.error(f"docker run指令执行失败")
                    self.logger.error(f"==========stderr==========: {stderr}")
                    if "error during connect" in stderr or "The system cannot find the file specified" in stderr:
                        raise DockerNotRunError
                    elif "user declined directory sharing" in stderr:
                        raise DockerShareError
                    else:
                        raise Exception(f"Docker运行失败，需要人工排查错误")
                # TODO 处理时间组删除，删多了的情况
                else:
                    self.logger.info("docker run指令执行成功")
                    if "ODM app finished" in last_lines:
                        self.logger.info("ODM处理完成")
                        if self._check_success(grid_dir):
                            self.logger.info(
                                f"网格 ({grid_id[0]},{grid_id[1]}) 处理成功")
                            return True, ""
                        else:
                            self.logger.error(
                                f"虽然ODM处理完成，但是生产产品质量可能不合格，需要人工检查")
                            raise Exception(f"虽然ODM处理完成，但是生产产品质量可能不合格，需要人工检查")
                    elif "enough overlap" in last_lines:
                        raise NotOverlapError
                    elif "out of memory" in last_lines:
                        raise OutOfMemoryError
                    elif "strange values" in last_lines:
                        raise StrangeValuesError
                    else:
                        raise Exception(f"ODM处理失败，需要人工排查错误")

            except NotOverlapError:
                if use_lowest_quality:
                    self.logger.warning(
                        "检测到not overlap错误，移除lowest quality参数后重试")
                    use_lowest_quality = False
                    continue
                else:
                    self.logger.error(
                        "即使移除lowest quality参数后仍然出现not overlap错误")
                    return False, "图像重叠度不足，请检查数据集的采样间隔情况"

            except DockerNotRunError:
                self.logger.error("Docker服务未启动")
                return False, "Docker没有启动，请启动Docker"

            except DockerShareError:
                self.logger.error("Docker无法访问目录")
                return False, "Docker无法访问数据目录或输出目录，请检查目录权限和共享设置"

            except OutOfMemoryError:
                self.logger.error("内存不足，请减少输入图像的数量")
                return False, "内存不足"
            except StrangeValuesError:
                self.logger.error("重建过程中出现异常值")
                return False, "检测到异常值，请检查输入数据集的采样间隔情况"

            time.sleep(10)

        return False, f"网格 ({grid_id[0]},{grid_id[1]}) 处理失败"

    def process_all_grids(self, grid_points: Dict[tuple, pd.DataFrame], produce_dem: bool) -> Dict[tuple, pd.DataFrame]:
        """处理所有网格

        Returns:
            Dict[tuple, pd.DataFrame]: 成功处理的网格点数据字典
        """
        self.logger.info("开始执行网格处理")
        successful_grid_points = {}
        failed_grids = []

        for grid_id, points in grid_points.items():
            grid_dir = os.path.join(
                self.output_dir, f'grid_{grid_id[0]}_{grid_id[1]}'
            )

            try:
                success, error_msg = self.run_odm_with_monitor(
                    grid_dir=grid_dir,
                    grid_id=grid_id,
                    fast_mode=(self.mode == "快拼模式"),
                    produce_dem=produce_dem
                )

                if success:
                    successful_grid_points[grid_id] = points
                else:
                    self.logger.error(
                        f"网格 ({grid_id[0]},{grid_id[1]}) 处理失败: {error_msg}")
                    failed_grids.append((grid_id, error_msg))

            except Exception as e:
                error_msg = str(e)
                self.logger.error(
                    f"处理网格 ({grid_id[0]},{grid_id[1]}) 时发生异常: {error_msg}")
                failed_grids.append((grid_id, error_msg))

        # 汇总处理结果
        total_grids = len(grid_points)
        failed_count = len(failed_grids)
        success_count = len(successful_grid_points)

        self.logger.info(
            f"网格处理完成。总计: {total_grids}, 成功: {success_count}, 失败: {failed_count}")
        if failed_grids:
            self.logger.error("失败的网格:")
            for grid_id, error_msg in failed_grids:
                self.logger.error(
                    f"网格 ({grid_id[0]},{grid_id[1]}): {error_msg}")

        if len(successful_grid_points) == 0:
            raise Exception("所有网格处理都失败，无法继续处理")

        return successful_grid_points