remove depth and fix normal -> vnormal

src/orisys/MultiSensor.py

@@ -75,7 +75,7 @@ def _sensor_worker(sensor_id, config, data_queue, stop_event, use_async=False):
                     'sensor_id': sensor_id,
                     'img': sensor.img.copy() if sensor.img is not None else None,
                     'flow': sensor.flow.copy() if sensor.flow is not None else None,
-                    'normal': sensor.normal.copy() if sensor.normal is not None else None,
+                    'normal': sensor.vnormal.copy() if sensor.vnormal is not None else None,
                     'shear': sensor.shear.copy() if sensor.shear is not None else None,
                     'depth': sensor.depth.copy() if sensor.depth is not None else None,
                     'fps': sensor.fps,

src/orisys/get_depth.py

@@ -1,7 +1,8 @@
 import numpy as np
 import cv2
+from scipy.ndimage import gaussian_filter
 
-def compute_foe(flow_field, min_magnitude=1.0, expansion_threshold=1, downsample_factor=10, return_all_contours=False, kernel_size=(5,5), denoise_sigma=1.5):
+def compute_foe(flow_field, min_magnitude=1.0, expansion_threshold=1, downsample_factor=10, return_all_contours=False, kernel_size=(5,5), denoise_sigma=10):
     """
     计算光流场的扩张焦点(Focus of Expansion)。
     
@@ -87,7 +88,7 @@ def compute_foe(flow_field, min_magnitude=1.0, expansion_threshold=1, downsample
     return result
 
 def compute_multiple_foe(flow_field, min_magnitude=1.0, expansion_threshold=0.001, 
-                         downsample_factor=10, min_contour_area=3000, denoise_sigma=1.5, kernel_size=(5,5)):
+                         downsample_factor=10, min_contour_area=3000, denoise_sigma=10, kernel_size=(5,5)):
     """
     计算光流场的多个扩张焦点(Foci of Expansion)。
     
@@ -141,4 +142,32 @@ def compute_multiple_foe(flow_field, min_magnitude=1.0, expansion_threshold=0.00
                     result['foe_points'].append((cx, cy))
                     result['expansion_regions'].append(contour)
     
-    return result
+    return result
+
+def smooth_magnitude(mag, method='moving_average', window_size=5, downsample_factor=4):
+    """
+    平滑幅度图以减少梯度计算时的伪影。
+    
+    Args:
+        mag: 幅度图，形状为 (H, W) 的 numpy 数组
+        method: 平滑方法，'moving_average' 或 'windowed_interpolation'
+        window_size: 移动平均的窗口大小（默认5）
+        downsample_factor: 窗口插值的下采样因子（默认4）
+        
+    Returns:
+        np.ndarray: 平滑后的幅度图
+    """
+    if method == 'moving_average':
+        # 使用移动平均滤波器（box filter）
+        kernel = np.ones((window_size, window_size), dtype=np.float32) / (window_size * window_size)
+        mag_smooth = cv2.filter2D(mag, -1, kernel)
+    elif method == 'windowed_interpolation':
+        # 使用窗口插值：下采样然后插值回原尺寸
+        h, w = mag.shape
+        mag_downsampled = mag[::downsample_factor, ::downsample_factor]
+        mag_smooth = cv2.resize(mag_downsampled, (w, h), interpolation=cv2.INTER_CUBIC)
+    else:
+        # 默认使用高斯滤波
+        mag_smooth = gaussian_filter(mag, sigma=1.5)
+    
+    return mag_smooth