From f247906d17d621aba6429a402d89d98dc22a017e Mon Sep 17 00:00:00 2001 From: bluepulsar Date: Sat, 3 Jan 2026 11:11:53 +0800 Subject: [PATCH] remove files --- test_depth.py | 119 ----------- test_depth_v2.py | 79 -------- test_foe_depth.py | 451 ------------------------------------------ test_foe_depth_v2.py | 462 ------------------------------------------- 4 files changed, 1111 deletions(-) delete mode 100644 test_depth.py delete mode 100644 test_depth_v2.py delete mode 100644 test_foe_depth.py delete mode 100644 test_foe_depth_v2.py diff --git a/test_depth.py b/test_depth.py deleted file mode 100644 index d11ca8a..0000000 --- a/test_depth.py +++ /dev/null @@ -1,119 +0,0 @@ -import os -os.environ["OPENCV_VIDEOIO_MSMF_ENABLE_HW_TRANSFORMS"] = "0" # Windows 下禁用硬件加速,避免兼容性问题 - -import cv2 -import orisys -import numpy as np -from scipy.ndimage import gaussian_filter - - -def get_depth(div, fps, H=400, W=400, Z0=30, win_size=10): - # Precompute - dt = 1.0 / fps # e.g., 1/30 - Z_map = np.full((H, W), Z0, dtype=np.float32) # initial depth map - - - for win_y in range(0, H, win_size): - for win_x in range(0, W, win_size): - y1, y2 = win_y, min(win_y + win_size, H) - x1, x2 = win_x, min(win_x + win_size, W) - - # Robust divergence estimate - D_win = np.median(div[y1:y2, x1:x2]) - - # Avoid numerical issues - if np.abs(D_win) < 1e-3: - continue - - # Update depth in window - Z_old = Z_map[y1, x1] # or use window mean - Z_new = Z_old * np.exp(-0.5 * D_win * dt) - - # Optionally fuse with dot-based depth if available - # Z_new = alpha * Z_new + (1 - alpha) * Z_from_dots - - Z_map[y1:y2, x1:x2] = Z_new - return Z_map - -def main(): - - - # 方式1: 从视频文件读取 - # sensor = orisys.Sensor("./s1.mp4", isstitch=True, cuda=True, verbose=True) - - # 方式2: 从摄像头读取(取消注释使用) - sensor = orisys.Sensor(0, isstitch=True, cuda=True, verbose=True) - - print("\n按 'q' 退出程序,按 'r' 重置光流追踪器") - - while True: - # 步骤 2.1: 获取并拼接图像 - sensor.get_img() - - # 步骤 2.2: 计算形变场 - sensor.compute_deformation() - - fps, flow,vnormal, depth = sensor.read_info( - sensor.info.FPS, - sensor.info.VRAW, - sensor.info.VNORMAL, - sensor.info.DEPTH - ) - - # depth = get_depth_improved(vnormal, fps) - - print(f"FPS: {fps:5.1f}, 深度: {np.min(depth):8.2f}, {np.mean(depth):8.2f}, {np.max(depth):8.2f}") - - - - - arrows = orisys.util.draw_arrows( - sensor.img.copy(), # 使用 copy() 避免修改原图 - vnormal, - threshold=5, - grid_spacing=10, - arrow_scale=1.0 - ) - cv2.imshow("形变场 Deformation", arrows) - - # # 绘制深度图(热力图) - # # 深度值缩放:中心值 30,范围 ±10(即 20-40 映射到 0-255) - # depth_center = 30 # 中心深度值 - # depth_range = 5 # 变化范围 ±10 - # depth_normalized = (depth - (depth_center - depth_range)) / (2 * depth_range) # 归一化到 0-1 - # depth_normalized = np.clip(depth_normalized, 0, 1) # 限制在 0-1 范围 - depth_img = cv2.applyColorMap( - (depth * 255.0).astype('uint8'), - cv2.COLORMAP_HOT - ) - cv2.imshow("深度图 Depth", depth_img) - - mag_img = orisys.util.draw_magnitude_map( - sensor.img.copy(), - vnormal, - threshold=5, - colormap=cv2.COLORMAP_HOT - ) - cv2.imshow("magnitude map", mag_img) - - # ===================================================================== - # 4. 键盘控制 - # ===================================================================== - key = cv2.waitKey(1) & 0xFF - if key == ord("q"): - print("\n退出程序...") - break - if key == ord("r"): - # 重置光流追踪器(当追踪漂移时使用) - sensor.reset() - print("光流追踪器已重置") - - # ========================================================================= - # 5. 清理资源 - # ========================================================================= - sensor.disconnect() # 释放视频源和相关资源 - cv2.destroyAllWindows() - - -if __name__ == '__main__': - main() diff --git a/test_depth_v2.py b/test_depth_v2.py deleted file mode 100644 index 7c2484b..0000000 --- a/test_depth_v2.py +++ /dev/null @@ -1,79 +0,0 @@ -import os -os.environ["OPENCV_VIDEOIO_MSMF_ENABLE_HW_TRANSFORMS"] = "0" # Windows 下禁用硬件加速,避免兼容性问题 - -import cv2 -import orisys -import numpy as np -from scipy.ndimage import gaussian_filter - - -def main(): - - - # 方式1: 从视频文件读取 - # sensor = orisys.Sensor("./s1.mp4", isstitch=True, cuda=True, verbose=True) - - # 方式2: 从摄像头读取(取消注释使用) - sensor = orisys.Sensor(0, isstitch=True, cuda=True, verbose=True) - - print("\n按 'q' 退出程序,按 'r' 重置光流追踪器") - - while True: - # 步骤 2.1: 获取并拼接图像 - sensor.get_img() - - # 步骤 2.2: 计算形变场 - sensor.compute_deformation() - - fps, flow,vnormal, depth = sensor.read_info( - sensor.info.FPS, - sensor.info.VRAW, - sensor.info.VNORMAL, - sensor.info.DEPTH - ) - - arrows = orisys.util.draw_arrows( - sensor.img.copy(), # 使用 copy() 避免修改原图 - vnormal, - threshold=5, - grid_spacing=10, - arrow_scale=1.0 - ) - cv2.imshow("形变场 Deformation", arrows) - - mag = np.sqrt(vnormal[:, :, 0]**2 + vnormal[:, :, 1]**2) - mag = gaussian_filter(mag, sigma=12) - - mag_div = np.gradient(mag, axis=1) + np.gradient(mag, axis=0) - mag_div = np.where(mag_div>0, mag_div, 0) - - mag_img = cv2.applyColorMap( - (mag_div/0.2 * 255.0).astype('uint8'), - cv2.COLORMAP_JET - ) - cv2.imshow("magnitude map", mag_img) - - # print(np.median(mag), np.min(mag), np.max(mag)) - print(np.median(mag_div), np.min(mag_div), np.max(mag_div)) - - # ===================================================================== - # 4. 键盘控制 - # ===================================================================== - key = cv2.waitKey(1) & 0xFF - if key == ord("q"): - print("\n退出程序...") - break - if key == ord("r"): - # 重置光流追踪器(当追踪漂移时使用) - sensor.reset() - print("光流追踪器已重置") - - # ========================================================================= - # 5. 清理资源 - # ========================================================================= - sensor.disconnect() # 释放视频源和相关资源 - cv2.destroyAllWindows() - - -if __name__ == '__main__': - main() diff --git a/test_foe_depth.py b/test_foe_depth.py deleted file mode 100644 index 3d9041b..0000000 --- a/test_foe_depth.py +++ /dev/null @@ -1,451 +0,0 @@ -import os -os.environ["OPENCV_VIDEOIO_MSMF_ENABLE_HW_TRANSFORMS"] = "0" # Windows 下禁用硬件加速,避免兼容性问题 - -import cv2 -import orisys -import numpy as np -from scipy.ndimage import gaussian_filter - -def create_colorbar(min_val, max_val, height=400, width=60, colormap=cv2.COLORMAP_JET): - """ - 创建颜色条图像,显示深度值的颜色映射尺度。 - - Args: - min_val: 最小值 - max_val: 最大值 - height: 颜色条高度(默认400) - width: 颜色条宽度(默认60) - colormap: OpenCV颜色映射(默认JET) - - Returns: - np.ndarray: 包含颜色条和标签的BGR图像 - """ - # 创建颜色条:从0到255的渐变(从底部到顶部) - gradient = np.linspace(255, 0, height, dtype=np.uint8).reshape(-1, 1) - gradient = np.tile(gradient, (1, width)) - colorbar = cv2.applyColorMap(gradient, colormap) - - # 添加文本标签 - font = cv2.FONT_HERSHEY_SIMPLEX - font_scale = 0.4 - thickness = 1 - color = (255, 255, 255) # 白色文字 - - # 在顶部显示最大值 - max_text = f"{max_val:.1f}" - (text_width, text_height), _ = cv2.getTextSize(max_text, font, font_scale, thickness) - cv2.putText(colorbar, max_text, (width - text_width - 5, text_height + 5), - font, font_scale, color, thickness, cv2.LINE_AA) - - # 在中间显示中值 - mid_val = (min_val + max_val) / 2 - mid_text = f"{mid_val:.1f}" - (text_width, text_height), _ = cv2.getTextSize(mid_text, font, font_scale, thickness) - cv2.putText(colorbar, mid_text, (width - text_width - 5, height // 2 + text_height // 2), - font, font_scale, color, thickness, cv2.LINE_AA) - - # 在底部显示最小值 - min_text = f"{min_val:.1f}" - (text_width, text_height), _ = cv2.getTextSize(min_text, font, font_scale, thickness) - cv2.putText(colorbar, min_text, (width - text_width - 5, height - 5), - font, font_scale, color, thickness, cv2.LINE_AA) - - return colorbar - -def add_colorbar_to_image(image, min_val, max_val, colormap=cv2.COLORMAP_JET): - """ - 将颜色条添加到图像右侧。 - - Args: - image: 原始图像 - min_val: 最小值 - max_val: 最大值 - colormap: OpenCV颜色映射(默认JET) - - Returns: - np.ndarray: 添加了颜色条的图像 - """ - h, w = image.shape[:2] - colorbar = create_colorbar(min_val, max_val, height=h, width=60, colormap=colormap) - - # 水平拼接图像和颜色条 - combined = np.hstack([image, colorbar]) - return combined - -def estimate_depth(foe=None, flow=None, init_depth=None, min_radial_flow=0.01, T_z=1.0, - expansion_mask=None, contraction_mask=None): - """ - 基于FOE(扩张焦点)和光流场估计深度。 - - Args: - foe: FOE坐标,可以是: - - (x, y) 元组或列表 - - None(如果未提供,返回零深度图) - flow: 光流场,形状为 (H, W, 2) 的 numpy 数组,包含 u 和 v 分量 - init_depth: 初始深度值,可以是: - - 标量:用于统一缩放深度 - - numpy数组:用于逐像素参考深度(会进行混合) - - None:不进行缩放 - min_radial_flow: 最小径向流阈值,避免除零(默认0.01) - T_z: 平移速度参数,用于深度计算(默认1.0) - expansion_mask: 扩张区域掩码(可选),如果提供,只在掩码内计算深度 - contraction_mask: 收缩区域掩码(可选),如果提供,只在掩码内计算深度 - - Returns: - np.ndarray: 深度图,形状为 (H, W) - - Examples: - # 使用FOE坐标和vnormal估计深度 - depth = estimate_depth(foe=(cx, cy), flow=vnormal, init_depth=30) - - # 使用FOE列表和掩码 - depth = estimate_depth(foe=[cx, cy], flow=vnormal, expansion_mask=expansion_mask, contraction_mask=contraction_mask) - """ - if flow is None: - raise ValueError("flow parameter is required") - - H, W = flow.shape[:2] - u, v = flow[..., 0], flow[..., 1] - - # 创建有效掩码:扩张和收缩区域的并集 - if expansion_mask is not None or contraction_mask is not None: - if expansion_mask is not None and contraction_mask is not None: - valid_mask = expansion_mask | contraction_mask - elif expansion_mask is not None: - valid_mask = expansion_mask - else: - valid_mask = contraction_mask - else: - # 如果没有提供掩码,使用全图 - valid_mask = np.ones((H, W), dtype=bool) - - # 提取FOE坐标 - if foe is None: - # 如果没有提供FOE,返回零深度图 - return np.zeros((H, W), dtype=np.float32) - - if isinstance(foe, (tuple, list, np.ndarray)): - if len(foe) >= 2: - fx, fy = float(foe[0]), float(foe[1]) - else: - raise ValueError(f"FOE coordinates must have at least 2 elements, got {len(foe)}") - else: - raise ValueError(f"FOE must be a tuple, list, or array, got {type(foe)}") - - # 确保FOE坐标在图像范围内 - fx = np.clip(fx, 0, W - 1) - fy = np.clip(fy, 0, H - 1) - - # 创建坐标网格 - yy, xx = np.meshgrid(np.arange(H), np.arange(W), indexing='ij') - - # 计算从FOE到每个点的径向向量 - rx = xx - fx - ry = yy - fy - r = np.sqrt(rx**2 + ry**2) - - # 避免除零:在FOE点附近使用小值 - r_safe = np.maximum(r, 1.0) - - # 计算径向单位向量 - radial_unit_x = rx / r_safe - radial_unit_y = ry / r_safe - - # 计算径向流(光流在径向方向上的投影) - # 正值表示远离FOE,负值表示朝向FOE - radial_flow = u * radial_unit_x + v * radial_unit_y - - # 创建掩码:FOE附近区域(半径内) - foe_radius = 10 # FOE附近的半径(像素) - mask_foe_region = r < foe_radius - - # 处理FOE附近区域:使用邻域的中位数径向流(更稳健) - if np.any(mask_foe_region): - # 创建FOE区域的扩展掩码(用于获取邻域值) - mask_foe_extended = r < (foe_radius + 5) - if np.any(mask_foe_extended & ~mask_foe_region): - # 使用FOE区域外的邻域值的中位数 - neighbor_flow = radial_flow[mask_foe_extended & ~mask_foe_region] - if len(neighbor_flow) > 0: - radial_flow[mask_foe_region] = np.median(neighbor_flow) - else: - radial_flow[mask_foe_region] = 0.0 - else: - # 如果没有邻域值,使用全局中位数 - if np.any(~mask_foe_region): - radial_flow[mask_foe_region] = np.median(radial_flow[~mask_foe_region]) - else: - radial_flow[mask_foe_region] = 0.0 - - # 深度计算:Z = (T_z * r) / radial_flow - # 当径向流为正(远离FOE)时,深度为正 - radial_flow_safe = np.where( - np.abs(radial_flow) < min_radial_flow, - np.sign(radial_flow) * min_radial_flow, - radial_flow - ) - - # 计算相对深度(仅在有效掩码内) - depth = np.zeros((H, W), dtype=np.float32) - - # 只在有效掩码内计算深度 - if np.any(valid_mask): - depth_valid = (T_z * r[valid_mask]) / np.maximum(np.abs(radial_flow_safe[valid_mask]), min_radial_flow) - depth_valid = np.abs(depth_valid) # 使用绝对值 - depth[valid_mask] = depth_valid - - # 对于掩码外的像素,设置为掩码内的最低深度值 - if np.any(valid_mask): - min_depth_in_mask = np.min(depth[valid_mask]) - depth[~valid_mask] = min_depth_in_mask - else: - # 如果没有有效掩码,使用初始深度或0 - depth.fill(init_depth if init_depth is not None and np.isscalar(init_depth) else 0.0) - - # 处理FOE附近区域:使用平滑后的值 - if np.any(mask_foe_region): - depth_smoothed = gaussian_filter(depth, sigma=15) - depth[mask_foe_region] = depth_smoothed[mask_foe_region] - - # 应用高斯滤波平滑整个深度图,减少噪声和伪影 - depth = gaussian_filter(depth, sigma=15) - - # 缩放深度(如果提供了初始深度,只使用掩码内的值) - if init_depth is not None: - if np.isscalar(init_depth): - # 统一缩放:将深度中位数缩放到init_depth(只使用掩码内的值) - if np.any(valid_mask): - valid_depth = depth[valid_mask & (depth > 0)] - if len(valid_depth) > 0: - median_depth = np.median(valid_depth) - if median_depth > 0: - scale = init_depth / median_depth - depth *= scale - elif isinstance(init_depth, np.ndarray): - # 逐像素参考深度:计算缩放因子并混合(只使用掩码内的值) - if init_depth.shape == depth.shape and np.any(valid_mask): - valid_ref = valid_mask & (init_depth > 0) & (depth > 0) - if np.any(valid_ref): - # 计算缩放因子 - scale = np.median(init_depth[valid_ref] / depth[valid_ref]) - depth *= scale - - # 可选:与参考深度混合 - alpha = 0.3 # 混合因子 - depth = alpha * depth + (1 - alpha) * init_depth - - # 缩放后,确保掩码外的像素保持为掩码内的最低深度值 - if np.any(valid_mask): - min_depth_in_mask = np.min(depth[valid_mask]) - depth[~valid_mask] = min_depth_in_mask - - # 后处理:处理异常值 - depth = np.nan_to_num(depth, nan=0.0, posinf=1000.0, neginf=0.0) - - # 裁剪到合理范围(使用百分位数,但只在掩码内) - if np.any(valid_mask) and np.any(depth[valid_mask] > 0): - p1, p99 = np.percentile(depth[valid_mask & (depth > 0)], [1, 99]) - depth = np.clip(depth, p1, p99) - - # 最终平滑:对FOE附近区域再次应用平滑,确保伪影被消除 - depth_final_smooth = gaussian_filter(depth, sigma=15) - - # 重新计算FOE附近掩码 - rx = xx - fx - ry = yy - fy - r = np.sqrt(rx**2 + ry**2) - mask_foe_region = r < foe_radius - - # 在FOE附近区域使用更平滑的值(但只在有效掩码内) - if np.any(mask_foe_region & valid_mask): - depth[mask_foe_region & valid_mask] = depth_final_smooth[mask_foe_region & valid_mask] - - # 确保掩码外的像素保持为掩码内的最低深度值 - if np.any(valid_mask): - min_depth_in_mask = np.min(depth[valid_mask]) - depth[~valid_mask] = min_depth_in_mask - - return depth.astype(np.float32) - - - -def main(): - - - # 方式1: 从视频文件读取 - # sensor = orisys.Sensor("./s1.mp4", isstitch=True, cuda=True, verbose=True) - - # 方式2: 从摄像头读取(取消注释使用) - sensor = orisys.Sensor(0, isstitch=True, cuda=True, verbose=True) - - print("\n按 'q' 退出程序,按 'r' 重置光流追踪器") - - while True: - # 步骤 2.1: 获取并拼接图像 - sensor.get_img() - - # 步骤 2.2: 计算形变场 - sensor.compute_deformation() - - fps, flow,vnormal, depth = sensor.read_info( - sensor.info.FPS, - sensor.info.VRAW, - sensor.info.VNORMAL, - sensor.info.DEPTH - ) - - # depth = get_depth_improved(vnormal, fps) - - - arrows = orisys.util.draw_arrows( - sensor.img.copy(), # 使用 copy() 避免修改原图 - vnormal, - threshold=5, - grid_spacing=10, - arrow_scale=1.0 - ) - cv2.imshow("形变场 Deformation", arrows) - - # # 绘制深度图(热力图) - # # 深度值缩放:中心值 30,范围 ±10(即 20-40 映射到 0-255) - - - mag_img = orisys.util.draw_magnitude_map( - sensor.img.copy(), - vnormal, - threshold=5, - colormap=cv2.COLORMAP_HOT, - downsample_factor = 1 - ) - cv2.imshow("magnitude map", mag_img) - - # 计算扩张焦点 - # foe_result = orisys.util.compute_foe(vnormal,min_magnitude=1,expansion_threshold=0.01,downsample_factor=1) - foe_result = sensor.get_contact(multiple_foe=False, min_magnitude=1, expansion_threshold=0.01, downsample_factor=1,denoise_sigma=15) - # 在图像上绘制焦点和区域 - image_with_foe = orisys.util.draw_foe(sensor.img.copy(), foe_result) - cv2.imshow("Focus of Expansion", image_with_foe) - - divergence = foe_result['divergence_map'] - divergence = np.where(divergence>0, divergence, 0) - - # 计算散度统计信息 - div_min = np.min(divergence) - div_max = np.max(divergence) - div_median = np.median(divergence) - print(f"散度统计: min={div_min:8.4f}, median={div_median:8.4f}, max={div_max:8.4f}") - - # 归一化散度值到0-255范围(使用绝对值,然后归一化) - div_abs = np.abs(divergence) - if div_abs.max() > div_abs.min(): - div_normalized = ((div_abs - div_abs.min()) / (div_abs.max() - div_abs.min()) * 255).astype(np.uint8) - else: - div_normalized = np.zeros_like(div_abs, dtype=np.uint8) - - # 应用颜色映射(使用JET:蓝色=低散度,红色=高散度) - divergence_colored = cv2.applyColorMap(div_normalized, cv2.COLORMAP_JET) - - # 添加颜色条显示散度尺度 - div_display_min = div_abs.min() - div_display_max = div_abs.max() - divergence_with_colorbar = add_colorbar_to_image(divergence_colored, div_display_min, div_display_max, cv2.COLORMAP_JET) - cv2.imshow("divergence map", divergence_with_colorbar) - - # 检查是否找到FOE - if 'foe_point' in foe_result and foe_result.get('is_foe_found', False): - (cx, cy) = foe_result['foe_point'] - # 使用FOE坐标和vnormal估计深度,传入扩张和收缩掩码 - Z_rel = estimate_depth( - foe=(cx, cy), - flow=vnormal, - init_depth=30, - T_z=1.0, - expansion_mask=foe_result.get('expansion_mask'), - contraction_mask=foe_result.get('contraction_mask') - ) - - # 计算深度统计信息(用于颜色映射缩放) - z_min = np.min(Z_rel) - z_max = np.max(Z_rel) - z_median = np.median(Z_rel) - - # 打印深度统计信息 - print(f"FPS: {fps:5.1f}, FOE: ({cx:3d}, {cy:3d})") - print(f" 深度统计 (用于颜色映射缩放): min={z_min:8.2f}, median={z_median:8.2f}, max={z_max:8.2f}") - - # 智能颜色映射缩放:根据统计信息设置合理的显示范围 - # 如果最大值远大于中位数,说明存在异常值,使用百分位数范围 - if z_max > 5 * z_median: - # 存在异常值:使用百分位数范围,以median为中心 - z_p1 = np.percentile(Z_rel, 1) - z_p99 = np.percentile(Z_rel, 99) - z_p5 = np.percentile(Z_rel, 5) - z_p95 = np.percentile(Z_rel, 95) - - # 计算以median为中心的对称范围 - # 使用5%和95%百分位数来确定主要数据范围 - range_low = z_median - z_p5 - range_high = z_p95 - z_median - range_symmetric = max(range_low, range_high) - - # 设置显示范围:median ± 对称范围,但不小于1%和99%百分位数 - z_display_min = max(z_p1, z_median - 2 * range_symmetric) - z_display_max = min(z_p99, z_median + 2 * range_symmetric) - - print(f" 使用百分位数范围 (避免异常值): [{z_display_min:8.2f}, {z_display_max:8.2f}]") - else: - # 正常范围:使用min-max - z_display_min = z_min - z_display_max = z_max - print(f" 使用完整范围: [{z_display_min:8.2f}, {z_display_max:8.2f}]") - - # 裁剪深度值到显示范围并归一化 - depth_clipped = np.clip(Z_rel, z_display_min, z_display_max) - depth_normalized = (depth_clipped - z_display_min) / (z_display_max - z_display_min + 1e-6) - depth_normalized = np.clip(depth_normalized, 0, 1) - - # 使用JET颜色映射显示深度图(蓝色=低深度,红色=高深度) - depth_colored = cv2.applyColorMap((depth_normalized * 255).astype(np.uint8), cv2.COLORMAP_JET) - - # 添加颜色条显示深度尺度 - depth_with_colorbar = add_colorbar_to_image(depth_colored, z_display_min, z_display_max, cv2.COLORMAP_JET) - cv2.imshow("Depth Map", depth_with_colorbar) - else: - # 如果没有找到FOE,显示提示信息 - print("No FOE found, skipping depth estimation") - # 显示一个默认的深度图 - Z_rel = np.full((sensor.img.shape[0], sensor.img.shape[1]), 30.0, dtype=np.float32) - depth_colored = cv2.applyColorMap((Z_rel * 8).astype(np.uint8), cv2.COLORMAP_HOT) - - # 添加颜色条 - depth_with_colorbar = add_colorbar_to_image(depth_colored, 0.0, 30.0, cv2.COLORMAP_HOT) - cv2.imshow("Depth Map", depth_with_colorbar) - - # 计算多个扩张焦点 - # foe_result = orisys.util.compute_multiple_foe(vnormal, min_contour_area=3000,min_magnitude=1,expansion_threshold=0.001,downsample_factor=10) - - # # 在图像上绘制多个焦点和区域 - # image_with_foe = orisys.util.draw_multiple_foe(sensor.img.copy(), foe_result) - # cv2.imshow("Multiple FOE", image_with_foe) - - # ===================================================================== - # 4. 键盘控制 - # ===================================================================== - key = cv2.waitKey(1) & 0xFF - if key == ord("q"): - print("\n退出程序...") - break - if key == ord("r"): - # 重置光流追踪器(当追踪漂移时使用) - sensor.reset() - print("光流追踪器已重置") - - # ========================================================================= - # 5. 清理资源 - # ========================================================================= - sensor.disconnect() # 释放视频源和相关资源 - cv2.destroyAllWindows() - - -if __name__ == '__main__': - main() diff --git a/test_foe_depth_v2.py b/test_foe_depth_v2.py deleted file mode 100644 index 50f1d20..0000000 --- a/test_foe_depth_v2.py +++ /dev/null @@ -1,462 +0,0 @@ -import os -os.environ["OPENCV_VIDEOIO_MSMF_ENABLE_HW_TRANSFORMS"] = "0" # Windows 下禁用硬件加速,避免兼容性问题 - -import cv2 -import orisys -import numpy as np -from scipy.ndimage import gaussian_filter, binary_dilation - -def create_colorbar(min_val, max_val, height=400, width=60, colormap=cv2.COLORMAP_JET): - """ - 创建颜色条图像,显示深度值的颜色映射尺度。 - - Args: - min_val: 最小值 - max_val: 最大值 - height: 颜色条高度(默认400) - width: 颜色条宽度(默认60) - colormap: OpenCV颜色映射(默认JET) - - Returns: - np.ndarray: 包含颜色条和标签的BGR图像 - """ - # 创建颜色条:从0到255的渐变(从底部到顶部) - gradient = np.linspace(255, 0, height, dtype=np.uint8).reshape(-1, 1) - gradient = np.tile(gradient, (1, width)) - colorbar = cv2.applyColorMap(gradient, colormap) - - # 添加文本标签 - font = cv2.FONT_HERSHEY_SIMPLEX - font_scale = 0.4 - thickness = 1 - color = (255, 255, 255) # 白色文字 - - # 在顶部显示最大值 - max_text = f"{max_val:.1f}" - (text_width, text_height), _ = cv2.getTextSize(max_text, font, font_scale, thickness) - cv2.putText(colorbar, max_text, (width - text_width - 5, text_height + 5), - font, font_scale, color, thickness, cv2.LINE_AA) - - # 在中间显示中值 - mid_val = (min_val + max_val) / 2 - mid_text = f"{mid_val:.1f}" - (text_width, text_height), _ = cv2.getTextSize(mid_text, font, font_scale, thickness) - cv2.putText(colorbar, mid_text, (width - text_width - 5, height // 2 + text_height // 2), - font, font_scale, color, thickness, cv2.LINE_AA) - - # 在底部显示最小值 - min_text = f"{min_val:.1f}" - (text_width, text_height), _ = cv2.getTextSize(min_text, font, font_scale, thickness) - cv2.putText(colorbar, min_text, (width - text_width - 5, height - 5), - font, font_scale, color, thickness, cv2.LINE_AA) - - return colorbar - -def add_colorbar_to_image(image, min_val, max_val, colormap=cv2.COLORMAP_JET): - """ - 将颜色条添加到图像右侧。 - - Args: - image: 原始图像 - min_val: 最小值 - max_val: 最大值 - colormap: OpenCV颜色映射(默认JET) - - Returns: - np.ndarray: 添加了颜色条的图像 - """ - h, w = image.shape[:2] - colorbar = create_colorbar(min_val, max_val, height=h, width=60, colormap=colormap) - - # 水平拼接图像和颜色条 - combined = np.hstack([image, colorbar]) - return combined - -def estimate_depth(foe=None, flow=None, init_depth=None, min_radial_flow=0.01, T_z=1.0, - expansion_mask=None, contraction_mask=None): - """ - 基于FOE(扩张焦点)和光流场估计深度。 - - Args: - foe: FOE坐标,可以是: - - (x, y) 元组或列表 - - None(如果未提供,返回零深度图) - flow: 光流场,形状为 (H, W, 2) 的 numpy 数组,包含 u 和 v 分量 - init_depth: 初始深度值,可以是: - - 标量:用于统一缩放深度 - - numpy数组:用于逐像素参考深度(会进行混合) - - None:不进行缩放 - min_radial_flow: 最小径向流阈值,避免除零(默认0.01) - T_z: 平移速度参数,用于深度计算(默认1.0) - expansion_mask: 扩张区域掩码(可选),如果提供,只在掩码内计算深度 - contraction_mask: 收缩区域掩码(可选),如果提供,只在掩码内计算深度 - - Returns: - np.ndarray: 深度图,形状为 (H, W) - - Examples: - # 使用FOE坐标和vnormal估计深度 - depth = estimate_depth(foe=(cx, cy), flow=vnormal, init_depth=30) - - # 使用FOE列表和掩码 - depth = estimate_depth(foe=[cx, cy], flow=vnormal, expansion_mask=expansion_mask, contraction_mask=contraction_mask) - """ - if flow is None: - raise ValueError("flow parameter is required") - - H, W = flow.shape[:2] - u, v = flow[..., 0], flow[..., 1] - - # 创建有效掩码:如果提供了expansion_mask,将其扩展20% - if expansion_mask is not None: - # 计算膨胀核大小:基于expansion_mask的实际尺寸 - # 找到mask的边界框,计算其特征尺寸 - mask_coords = np.where(expansion_mask) - if len(mask_coords[0]) > 0: - # 计算mask的边界框尺寸 - y_min, y_max = mask_coords[0].min(), mask_coords[0].max() - x_min, x_max = mask_coords[1].min(), mask_coords[1].max() - mask_width = x_max - x_min + 1 - mask_height = y_max - y_min + 1 - # 使用mask的平均尺寸的20%作为核半径 - avg_size = (mask_width + mask_height) / 2 - kernel_radius = max(3, int(avg_size * 0.2 * 0.5)) # 20%扩展,核半径约为尺寸的10% - else: - # 如果mask为空,使用图像尺寸的某个百分比 - diagonal = np.sqrt(H**2 + W**2) - kernel_radius = max(3, int(diagonal * 0.02)) # 图像对角线的2%作为核半径 - - # 创建方形结构元素,边长为 kernel_radius*2+1 - structure = np.ones((kernel_radius * 2 + 1, kernel_radius * 2 + 1), dtype=bool) - - # 对expansion_mask进行形态学膨胀,使其扩大约20% - valid_mask = binary_dilation(expansion_mask.astype(bool), structure=structure) - else: - # 如果没有提供掩码,使用全图 - valid_mask = np.ones((H, W), dtype=bool) - - # 提取FOE坐标 - if foe is None: - # 如果没有提供FOE,返回零深度图 - return np.zeros((H, W), dtype=np.float32) - - if isinstance(foe, (tuple, list, np.ndarray)): - if len(foe) >= 2: - fx, fy = float(foe[0]), float(foe[1]) - else: - raise ValueError(f"FOE coordinates must have at least 2 elements, got {len(foe)}") - else: - raise ValueError(f"FOE must be a tuple, list, or array, got {type(foe)}") - - # 确保FOE坐标在图像范围内 - fx = np.clip(fx, 0, W - 1) - fy = np.clip(fy, 0, H - 1) - - # 创建坐标网格 - yy, xx = np.meshgrid(np.arange(H), np.arange(W), indexing='ij') - - # 计算从FOE到每个点的径向向量 - rx = xx - fx - ry = yy - fy - r = np.sqrt(rx**2 + ry**2) - - # 避免除零:在FOE点附近使用小值 - r_safe = np.maximum(r, 1.0) - - # 计算径向单位向量 - radial_unit_x = rx / r_safe - radial_unit_y = ry / r_safe - - # 计算径向流(光流在径向方向上的投影) - # 正值表示远离FOE,负值表示朝向FOE - radial_flow = u * radial_unit_x + v * radial_unit_y - - # 创建掩码:FOE附近区域(半径内) - foe_radius = 1 # FOE附近的半径(像素) - mask_foe_region = r < foe_radius - - # 处理FOE附近区域:使用邻域的中位数径向流(更稳健) - if np.any(mask_foe_region): - # 创建FOE区域的扩展掩码(用于获取邻域值) - mask_foe_extended = r < (foe_radius + 5) - if np.any(mask_foe_extended & ~mask_foe_region): - # 使用FOE区域外的邻域值的中位数 - neighbor_flow = radial_flow[mask_foe_extended & ~mask_foe_region] - if len(neighbor_flow) > 0: - radial_flow[mask_foe_region] = np.median(neighbor_flow) - else: - radial_flow[mask_foe_region] = 0.0 - else: - # 如果没有邻域值,使用全局中位数 - if np.any(~mask_foe_region): - radial_flow[mask_foe_region] = np.median(radial_flow[~mask_foe_region]) - else: - radial_flow[mask_foe_region] = 0.0 - - # 深度计算:Z = (T_z * r) / radial_flow - # 当径向流为正(远离FOE)时,深度为正 - radial_flow_safe = np.where( - np.abs(radial_flow) < min_radial_flow, - np.sign(radial_flow) * min_radial_flow, - radial_flow - ) - - # 计算相对深度(仅在有效掩码内) - depth = np.zeros((H, W), dtype=np.float32) - - # 只在有效掩码内计算深度 - if np.any(valid_mask): - depth_valid = (T_z * r[valid_mask]) / np.maximum(np.abs(radial_flow_safe[valid_mask]), min_radial_flow) - depth_valid = np.abs(depth_valid) # 使用绝对值 - depth[valid_mask] = depth_valid - - # 对于掩码外的像素,设置为掩码内的最低深度值 - if np.any(valid_mask): - min_depth_in_mask = np.min(depth[valid_mask]) - depth[~valid_mask] = min_depth_in_mask - else: - # 如果没有有效掩码,使用初始深度或0 - depth.fill(init_depth if init_depth is not None and np.isscalar(init_depth) else 0.0) - - # 处理FOE附近区域:使用平滑后的值 - if np.any(mask_foe_region): - depth_smoothed = gaussian_filter(depth, sigma=15) - depth[mask_foe_region] = depth_smoothed[mask_foe_region] - - # 应用高斯滤波平滑整个深度图,减少噪声和伪影 - depth = gaussian_filter(depth, sigma=15) - - - # 缩放深度(如果提供了初始深度,只使用掩码内的值) - if init_depth is not None: - if np.isscalar(init_depth): - # 统一缩放:将深度中位数缩放到init_depth(只使用掩码内的值) - if np.any(valid_mask): - valid_depth = depth[valid_mask & (depth > 0)] - if len(valid_depth) > 0: - median_depth = np.median(valid_depth) - if median_depth > 0: - scale = init_depth / median_depth - depth *= scale - elif isinstance(init_depth, np.ndarray): - # 逐像素参考深度:计算缩放因子并混合(只使用掩码内的值) - if init_depth.shape == depth.shape and np.any(valid_mask): - valid_ref = valid_mask & (init_depth > 0) & (depth > 0) - if np.any(valid_ref): - # 计算缩放因子 - scale = np.median(init_depth[valid_ref] / depth[valid_ref]) - depth *= scale - - # 可选:与参考深度混合 - alpha = 0.3 # 混合因子 - depth = alpha * depth + (1 - alpha) * init_depth - - # 缩放后,确保掩码外的像素保持为掩码内的最低深度值 - if np.any(valid_mask): - min_depth_in_mask = np.min(depth[valid_mask]) - depth[~valid_mask] = min_depth_in_mask - - # 后处理:处理异常值 - depth = np.nan_to_num(depth, nan=0.0, posinf=1000.0, neginf=0.0) - - # 裁剪到合理范围(使用百分位数,但只在掩码内) - if np.any(valid_mask) and np.any(depth[valid_mask] > 0): - p1, p99 = np.percentile(depth[valid_mask & (depth > 0)], [1, 99]) - depth = np.clip(depth, p1, p99) - - # 最终平滑:对FOE附近区域再次应用平滑,确保伪影被消除 - depth_final_smooth = gaussian_filter(depth, sigma=15) - - # 重新计算FOE附近掩码 - rx = xx - fx - ry = yy - fy - r = np.sqrt(rx**2 + ry**2) - mask_foe_region = r < foe_radius - - # 在FOE附近区域使用更平滑的值(但只在有效掩码内) - if np.any(mask_foe_region & valid_mask): - depth[mask_foe_region & valid_mask] = depth_final_smooth[mask_foe_region & valid_mask] - - # 确保掩码外的像素保持为掩码内的最低深度值 - if np.any(valid_mask): - min_depth_in_mask = np.min(depth[valid_mask]) - depth[~valid_mask] = min_depth_in_mask - - return depth.astype(np.float32) - - - -def main(): - - - # 方式1: 从视频文件读取 - # sensor = orisys.Sensor("./s1.mp4", isstitch=True, cuda=True, verbose=True) - - # 方式2: 从摄像头读取(取消注释使用) - sensor = orisys.Sensor(0, isstitch=True, cuda=True, verbose=True) - - print("\n按 'q' 退出程序,按 'r' 重置光流追踪器") - - while True: - # 步骤 2.1: 获取并拼接图像 - sensor.get_img() - - # 步骤 2.2: 计算形变场 - sensor.compute_deformation() - - fps, flow,vnormal, depth = sensor.read_info( - sensor.info.FPS, - sensor.info.VRAW, - sensor.info.VNORMAL, - sensor.info.DEPTH - ) - - # depth = get_depth_improved(vnormal, fps) - - - arrows = orisys.util.draw_arrows( - sensor.img.copy(), # 使用 copy() 避免修改原图 - vnormal, - threshold=5, - grid_spacing=10, - arrow_scale=1.0 - ) - cv2.imshow("形变场 Deformation", arrows) - - # # 绘制深度图(热力图) - # # 深度值缩放:中心值 30,范围 ±10(即 20-40 映射到 0-255) - - - mag_img = orisys.util.draw_magnitude_map( - sensor.img.copy(), - vnormal, - threshold=5, - colormap=cv2.COLORMAP_HOT, - downsample_factor = 1 - ) - cv2.imshow("magnitude map", mag_img) - - # 计算扩张焦点 - # foe_result = orisys.util.compute_foe(vnormal,min_magnitude=1,expansion_threshold=0.01,downsample_factor=1) - foe_result = sensor.get_contact(multiple_foe=False, min_magnitude=1, expansion_threshold=0.01, downsample_factor=1,denoise_sigma=15) - # 在图像上绘制焦点和区域 - image_with_foe = orisys.util.draw_foe(sensor.img.copy(), foe_result) - cv2.imshow("Focus of Expansion", image_with_foe) - - divergence = foe_result['divergence_map'] - divergence = np.where(divergence>0.01, divergence, 0) - - # 计算散度统计信息 - div_min = np.min(divergence) - div_max = np.max(divergence) - div_median = np.median(divergence) - print(f"散度统计: min={div_min:8.4f}, median={div_median:8.4f}, max={div_max:8.4f}") - - # 归一化散度值到0-255范围(使用绝对值,然后归一化) - div_abs = np.abs(divergence) - if div_abs.max() > div_abs.min(): - div_normalized = ((div_abs - div_abs.min()) / (div_abs.max() - div_abs.min()) * 255).astype(np.uint8) - else: - div_normalized = np.zeros_like(div_abs, dtype=np.uint8) - - # 应用颜色映射(使用JET:蓝色=低散度,红色=高散度) - divergence_colored = cv2.applyColorMap(div_normalized, cv2.COLORMAP_JET) - - # 添加颜色条显示散度尺度 - div_display_min = div_abs.min() - div_display_max = div_abs.max() - divergence_with_colorbar = add_colorbar_to_image(divergence_colored, div_display_min, div_display_max, cv2.COLORMAP_JET) - cv2.imshow("divergence map", divergence_with_colorbar) - - # 检查是否找到FOE - if 'foe_point' in foe_result and foe_result.get('is_foe_found', False): - (cx, cy) = foe_result['foe_point'] - # 使用FOE坐标和vnormal估计深度,传入扩张和收缩掩码 - Z_rel = estimate_depth( - foe=(cx, cy), - flow=vnormal, - init_depth=30, - T_z=1.0, - expansion_mask=foe_result.get('expansion_mask'), - contraction_mask=foe_result.get('contraction_mask') - ) - - # 计算深度统计信息(用于颜色映射缩放) - z_min = np.min(Z_rel) - z_max = np.max(Z_rel) - z_median = np.median(Z_rel) - - # 打印深度统计信息 - print(f"FPS: {fps:5.1f}, FOE: ({cx:3d}, {cy:3d})") - print(f" 深度统计 (用于颜色映射缩放): min={z_min:8.2f}, median={z_median:8.2f}, max={z_max:8.2f}") - - # 智能颜色映射缩放:根据统计信息设置合理的显示范围 - # 如果最大值远大于中位数,说明存在异常值,使用百分位数范围 - if z_max > 5 * z_median: - # 存在异常值:使用百分位数范围,以median为中心 - z_p1 = np.percentile(Z_rel, 1) - z_p99 = np.percentile(Z_rel, 99) - z_p5 = np.percentile(Z_rel, 5) - z_p95 = np.percentile(Z_rel, 95) - - # 计算以median为中心的对称范围 - # 使用5%和95%百分位数来确定主要数据范围 - range_low = z_median - z_p5 - range_high = z_p95 - z_median - range_symmetric = max(range_low, range_high) - - # 设置显示范围:median ± 对称范围,但不小于1%和99%百分位数 - z_display_min = max(z_p1, z_median - 2 * range_symmetric) - z_display_max = min(z_p99, z_median + 2 * range_symmetric) - - print(f" 使用百分位数范围 (避免异常值): [{z_display_min:8.2f}, {z_display_max:8.2f}]") - else: - # 正常范围:使用min-max - z_display_min = z_min - z_display_max = z_max - print(f" 使用完整范围: [{z_display_min:8.2f}, {z_display_max:8.2f}]") - - # 裁剪深度值到显示范围并归一化 - depth_clipped = np.clip(Z_rel, z_display_min, z_display_max) - depth_normalized = (depth_clipped - z_display_min) / (z_display_max - z_display_min + 1e-6) - depth_normalized = np.clip(depth_normalized, 0, 1) - - # 使用JET颜色映射显示深度图(蓝色=低深度,红色=高深度) - depth_colored = cv2.applyColorMap((depth_normalized * 255).astype(np.uint8), cv2.COLORMAP_JET) - - # 添加颜色条显示深度尺度 - depth_with_colorbar = add_colorbar_to_image(depth_colored, z_display_min, z_display_max, cv2.COLORMAP_JET) - cv2.imshow("Depth Map", depth_with_colorbar) - else: - # 如果没有找到FOE,显示提示信息 - print("No FOE found, skipping depth estimation") - # 显示一个默认的深度图 - Z_rel = np.full((sensor.img.shape[0], sensor.img.shape[1]), 30.0, dtype=np.float32) - depth_colored = cv2.applyColorMap((Z_rel * 8).astype(np.uint8), cv2.COLORMAP_HOT) - - # 添加颜色条 - depth_with_colorbar = add_colorbar_to_image(depth_colored, 0.0, 30.0, cv2.COLORMAP_HOT) - cv2.imshow("Depth Map", depth_with_colorbar) - - - # ===================================================================== - # 4. 键盘控制 - # ===================================================================== - key = cv2.waitKey(1) & 0xFF - if key == ord("q"): - print("\n退出程序...") - break - if key == ord("r"): - # 重置光流追踪器(当追踪漂移时使用) - sensor.reset() - print("光流追踪器已重置") - - # ========================================================================= - # 5. 清理资源 - # ========================================================================= - sensor.disconnect() # 释放视频源和相关资源 - cv2.destroyAllWindows() - - -if __name__ == '__main__': - main()