diff --git a/backend/Log/OrbbecSDK.log.txt b/backend/Log/OrbbecSDK.log.txt
index aca2d1d0..156de2b6 100644
Binary files a/backend/Log/OrbbecSDK.log.txt and b/backend/Log/OrbbecSDK.log.txt differ
diff --git a/backend/devices/femtobolt_manager.py b/backend/devices/femtobolt_manager.py
index 771bf449..0715abe2 100644
--- a/backend/devices/femtobolt_manager.py
+++ b/backend/devices/femtobolt_manager.py
@@ -249,21 +249,20 @@ class FemtoBoltManager(BaseDevice):
        
         try:
             # 设置图形背景色和边距
-            self.fig.patch.set_facecolor((50/255, 50/255, 50/255))  # 设置深灰色背景 rgb(50, 50, 50)
+            self.fig.patch.set_facecolor((38/255, 48/255, 64/255))
             self.fig.tight_layout(pad=0)  # 移除所有边距
             
             # 清除之前的绘图
             self.ax.clear()
-            self.ax.set_facecolor((50/255, 50/255, 50/255))  # 设置坐标区域背景色为黑色
+            self.ax.set_facecolor((38/255, 48/255, 64/255))
             
             # 深度数据过滤（与display_x.py完全一致）
             depth[depth > self.depth_range_max] = 0
             depth[depth < self.depth_range_min] = 0
             
-            # 背景图（深灰色背景）
-            # 创建RGB格式的背景图，确保颜色准确性
-            background_gray_value = 50  # RGB(50, 50, 50)
-            background = np.full((*depth.shape, 3), background_gray_value, dtype=np.uint8)
+            # 背景图（#263040）
+            background = np.zeros((*depth.shape, 3), dtype=np.uint8)
+            background[:] = (38, 48, 64)
             
             # 使用 np.ma.masked_equal() 来屏蔽深度图中的零值
             depth = np.ma.masked_equal(depth, 0)
diff --git a/backend/devices/pressure_manager.py b/backend/devices/pressure_manager.py
index 11a9465d..d11138b2 100644
--- a/backend/devices/pressure_manager.py
+++ b/backend/devices/pressure_manager.py
@@ -570,18 +570,25 @@ class MockPressureDevice:
 
     def _generate_heatmap_image(self, raw_data: np.ndarray) -> str:
         try:
+            # 底值阈值（小于等于该值的区域作为背景）
             vmin = 10
+            # 归一化到 [0,255]，避免 dmax==dmin 时除零
             dmin, dmax = np.min(raw_data), np.max(raw_data)
             norm = np.clip((raw_data - dmin) / max(dmax - dmin, 1) * 255, 0, 255).astype(np.uint8)
+            # 应用伪彩色（JET）以增强对比
             heatmap = cv2.applyColorMap(norm, cv2.COLORMAP_JET)
-            heatmap[raw_data <= vmin] = (0, 0, 0)
+            # 将低值区域设置为背景色 #263040；OpenCV 使用 BGR 通道顺序 -> (64, 48, 38)
+            heatmap[raw_data <= vmin] = (64, 48, 38)
+            # 放大显示，保持像素边界清晰
             rows, cols = raw_data.shape
             heatmap = cv2.resize(heatmap, (cols * 4, rows * 4), interpolation=cv2.INTER_NEAREST)
+            # 转换为 RGB 交给 PIL 编码
             heatmap_rgb = cv2.cvtColor(heatmap, cv2.COLOR_BGR2RGB)
             from PIL import Image
             buffer = BytesIO()
             Image.fromarray(heatmap_rgb).save(buffer, format="PNG")
             buffer.seek(0)
+            # 输出 data URL 便于前端直接显示
             image_base64 = base64.b64encode(buffer.getvalue()).decode("utf-8")
             return f"data:image/png;base64,{image_base64}"
         except Exception: