fixed new sample cannot detect boxes due to filter

Readme.md

@@ -1,7 +1,8 @@
 # OrisysSDK API 文档
 
 本文件提供了 OrisysSDK 的各类方法
-
+## 使用方法
+pip install .
 ---
 ## `Sensor` 类别
 ### 描述
@@ -18,7 +19,7 @@
 
 ```python
 # Example 1：  用相机编号创建
-from xensesdk import Sensor
+from orisys import Sensor
 from src.sensor import Sensor
 sensor = Sensor(0)
 

example_contact.py

@@ -7,10 +7,10 @@ import time
 def main():
     
     # 方式1: 从视频文件读取
-    sensor = orisys.Sensor("./s1.mp4", isstitch=True, cuda=True, verbose=True)
+    # 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)
+    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")
 
@@ -36,34 +36,25 @@ def main():
         )
         cv2.imshow("形变场 Deformation", arrows)
 
-        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)
-
         # 计算触碰点
-        contact_result = sensor.get_contact(min_magnitude=1, expansion_threshold=0.01,denoise_sigma=15)
+        sensor.compute_contact(min_magnitude=0.1,expansion_threshold=0.01,denoise_sigma=15)
         
         # 在图像上触碰点和区域
-        image_with_foe = orisys.util.draw_foe(sensor.img.copy(), contact_result)
+        image_with_foe = orisys.util.draw_contact(sensor.img.copy(), sensor.contour, sensor.centroid)
         cv2.imshow("Contact Centroid", image_with_foe)
 
         # 计算触碰区域
-        divergence = contact_result['divergence_map']
+        depth_map = sensor.depth_map
         
         # 归一化散度值到0-255范围（使用绝对值，然后归一化）
-        div_abs = divergence
+        div_abs = depth_map
         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）
-        cv2.imshow("Divergence Map", cv2.applyColorMap(div_normalized, cv2.COLORMAP_JET))
+        cv2.imshow("Depth Map", cv2.applyColorMap(div_normalized, cv2.COLORMAP_JET))
 
         print(f"fps: {fps}")
         

requirements.txt

@@ -4,6 +4,4 @@ opencv_python>=4.10.0.84
 opencv-contrib-python
 scipy>=1.10.1
 setuptools>=45.2.0
-PyQt5>=5.15.0
+
-pyqtgraph>=0.12.0
-PyInstaller>=5.0

src/orisys/Stitcher.py

@@ -8,9 +8,14 @@ class Stitcher:
 
     def __init__(self,isstitch=False, n=[3,3], index=np.array([1,2,3,6,7,8,11,12,13])):
 
-            # Settings
+        # Settings
         self.isstitch = isstitch
 
+        # Find Boxes Related
+        self.min_area_frac = 0.01
+        self.max_area_frac = 0.05
+        self.max_aspect_ratio = 100
+
         # stitch related
         self.stitch_valid = False
         self.boxes = self.units = None
@@ -21,6 +26,7 @@ class Stitcher:
         self.nominal_ov_pos=100 
         self.margin=10
         self.bound=self.nominal_ov_pos - self.margin
+        
         # for sensor 1
         self.pos_default = [(260, 56), (577, 62), (897, 69), (1214, 75), (1530, 81), (256, 391), (570, 397), (889, 403), (1208, 409), (1523, 416), (248, 724), (563, 730), (882, 738), (1201, 743), (1516, 751)]
  
@@ -542,7 +548,7 @@ class Stitcher:
     
     
     
-    def __filter_boxes_by_size(self, boxes, img_shape, min_area_frac=0.018, max_area_frac=0.035):
+    def __filter_boxes_by_size(self, boxes, img_shape):
         """
         Remove boxes that are too small or too large relative to the image.
         - boxes: list of (x,y,w,h)
@@ -552,12 +558,12 @@ class Stitcher:
         """
         h, w = img_shape
         img_area = h * w
-        min_area = img_area * float(min_area_frac)
+        min_area = img_area * float(self.min_area_frac)
-        max_area = img_area * float(max_area_frac)
+        max_area = img_area * float(self.max_area_frac)
         filtered = []
         for (x,y,ww,hh) in boxes:
             area = ww * hh
-            if area < min_area or area > max_area or (abs(ww - hh) > 20):
+            if area < min_area or area > max_area or (abs(ww - hh) > self.max_aspect_ratio):
                 continue
             filtered.append((x,y,ww,hh))
         return filtered

src/orisys/configs/prototype.json

@@ -9,6 +9,19 @@
       "resolution_stitch": [400, 400],
       "index": [1,2,3,6,7,8,11,12,13],
       "pos_default": [[260, 56], [577, 62], [897, 69], [1214, 75], [1530, 81], [256, 391], [570, 397], [889, 403], [1208, 409], [1523, 416], [248, 724], [563, 730], [882, 738], [1201, 743], [1516, 751]]
+    },
+    "stitcher": {
+      "min_area_frac": 0.018,
+      "max_area_frac": 0.035,
+      "max_aspect_ratio": 20
+    },
+    "contact": {
+      "min_contour_area": 3000,
+      "min_magnitude": 0.02,
+      "expansion_threshold": 0.01,
+      "downsample_factor": 1,
+      "kernel_size": [5,5],
+      "denoise_sigma": 15
     }
 }
 

src/orisys/configs/sample_1.json

@@ -0,0 +1,23 @@
+{
+    "name": "prototype",
+    "version": "1.0",
+    "camera": {
+      "resolution_raw": [1920, 1080],
+      "fps": 60,
+      "units": 15,
+      "units_used": 9, 
+      "resolution_stitch": [400, 400],
+      "index": [1,2,3,6,7,8,11,12,13],
+      "pos_default": [[260, 56], [577, 62], [897, 69], [1214, 75], [1530, 81], [256, 391], [570, 397], [889, 403], [1208, 409], [1523, 416], [248, 724], [563, 730], [882, 738], [1201, 743], [1516, 751]]
+    },
+    "contact": {
+      "min_contour_area": 3000,
+      "min_magnitude": 1.0,
+      "expansion_threshold": 0.01,
+      "downsample_factor": 1,
+      "kernel_size": [5,5],
+      "denoise_sigma": 15
+    }
+}
+
+

src/orisys/get_depth.py

@@ -12,6 +12,41 @@ except ImportError:
 # 缓存形态学操作的核，避免重复创建
 _morphology_kernels = {}
 
+def _create_foe_result(expansion_mask, contraction_mask, divergence_map, 
+                       centroid=None, centroid_found=False, contour=None, 
+                       all_contours=None):
+    """
+    创建标准化的FOE结果字典，统一所有函数的返回格式。
+    
+    Args:
+        expansion_mask: 扩张区域掩码
+        contraction_mask: 收缩区域掩码
+        divergence_map: 散度图
+        centroid: 质心坐标，可以是单个元组 (x, y) 或列表 [(x1, y1), (x2, y2), ...]
+        centroid_found: 是否找到质心
+        contour: 轮廓，可以是单个轮廓或轮廓列表
+        all_contours: 所有轮廓（仅在return_all_contours=True时使用）
+    
+    Returns:
+        dict: 标准化的FOE结果字典
+    """
+    result = {
+        'expansion_mask': expansion_mask,
+        'contraction_mask': contraction_mask,
+        'divergence_map': divergence_map,
+        'centroid': centroid if centroid is not None else [0,0],
+        'centroid_found': centroid_found,
+    }
+    
+    # 可选字段
+    if contour is not None:
+        result['contour'] = contour
+    
+    if all_contours is not None:
+        result['_all_contours'] = all_contours
+    
+    return result
+
 def compute_foe(flow_field, min_magnitude=1.0, expansion_threshold=1, downsample_factor=1, return_all_contours=False, kernel_size=(5,5), denoise_sigma=10):
     """
     计算光流场的扩张焦点(Focus of Expansion)。
@@ -73,20 +108,15 @@ def compute_foe(flow_field, min_magnitude=1.0, expansion_threshold=1, downsample
             divergence = cv2.GaussianBlur(divergence, (0, 0), denoise_sigma)
     
     # 优化：使用原地操作
-    np.where(divergence > 0.02, divergence, 0, out=divergence)
+    np.where(divergence > min_magnitude, divergence, 0, out=divergence)
     
     # 创建掩码（使用原地操作优化）
     valid_mask = magnitude > min_magnitude
     expansion_mask = (valid_mask & (divergence > expansion_threshold))
     contraction_mask = (valid_mask & (divergence < -expansion_threshold))
     
-    result = {
+    # 初始化结果字典
-        'expansion_mask': expansion_mask,
+    result = _create_foe_result(expansion_mask, contraction_mask, divergence)
-        'contraction_mask': contraction_mask,
-        'divergence_map': divergence,
-        'foe_points': [0, 0],
-        'is_foe_found': False
-    }
     
     # 寻找扩张区域轮廓
     # 优化：缓存形态学操作的核
@@ -100,16 +130,16 @@ def compute_foe(flow_field, min_magnitude=1.0, expansion_threshold=1, downsample
         contours, _ = cv2.findContours(expansion_binary_closed, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
         
         if contours:
-            result['is_foe_found'] = True
+            result['centroid_found'] = True
             if return_all_contours:
                 result['_all_contours'] = contours
             
             largest_contour = max(contours, key=cv2.contourArea)
-            result['expansion_region'] = largest_contour
+            result['contour'] = largest_contour
             
             M = cv2.moments(largest_contour)
             if M["m00"] > 0:
-                result['foe_point'] = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
+                result['centroid'] = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
     
     return result
 
@@ -206,7 +236,7 @@ def compute_foe_gpu(flow_field, min_magnitude=1.0, expansion_threshold=1, downsa
     
     # 优化：在GPU上完成掩码操作，减少数据传输
     # CuPy的where不支持out参数，使用赋值代替
-    divergence_gpu = cp.where(divergence_gpu > 0.02, divergence_gpu, 0)
+    divergence_gpu = cp.where(divergence_gpu > min_magnitude, divergence_gpu, 0)
     
     # 在GPU上创建掩码
     valid_mask_gpu = magnitude_gpu > min_magnitude
@@ -219,13 +249,8 @@ def compute_foe_gpu(flow_field, min_magnitude=1.0, expansion_threshold=1, downsa
     expansion_mask = cp.asnumpy(expansion_mask_gpu)
     contraction_mask = cp.asnumpy(contraction_mask_gpu)
     
-    result = {
+    # 初始化结果字典
-        'expansion_mask': expansion_mask,
+    result = _create_foe_result(expansion_mask, contraction_mask, divergence)
-        'contraction_mask': contraction_mask,
-        'divergence_map': divergence,
-        'foe_points': [0, 0],
-        'is_foe_found': False
-    }
     
     # 寻找扩张区域轮廓（在CPU上进行，因为OpenCV的轮廓检测需要CPU）
     # 优化：缓存形态学操作的核
@@ -239,16 +264,16 @@ def compute_foe_gpu(flow_field, min_magnitude=1.0, expansion_threshold=1, downsa
         contours, _ = cv2.findContours(expansion_binary_closed, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
         
         if contours:
-            result['is_foe_found'] = True
+            result['centroid_found'] = True
             if return_all_contours:
                 result['_all_contours'] = contours
             
             largest_contour = max(contours, key=cv2.contourArea)
-            result['expansion_region'] = largest_contour
+            result['contour'] = largest_contour
             
             M = cv2.moments(largest_contour)
             if M["m00"] > 0:
-                result['foe_point'] = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
+                result['centroid'] = (int(M["m10"] / M["m00"]), int(M["m01"] / M["m00"]))
     
     return result
 
@@ -275,7 +300,7 @@ def compute_multiple_foe(flow_field, min_magnitude=1.0, expansion_threshold=0.00
             - 'divergence_map': 散度图
     """
     # 调用 compute_foe 获取基础数据和所有轮廓
-    foe_result = compute_foe(
+    foe_result = compute_foe_gpu(
         flow_field, 
         min_magnitude=min_magnitude,
         expansion_threshold=expansion_threshold,
@@ -286,13 +311,12 @@ def compute_multiple_foe(flow_field, min_magnitude=1.0, expansion_threshold=0.00
     )
     
     # 构建多焦点结果，复用基础数据
-    result = {
+    result = _create_foe_result(
-        'expansion_mask': foe_result['expansion_mask'],
+        expansion_mask=foe_result['expansion_mask'],
-        'contraction_mask': foe_result['contraction_mask'],
+        contraction_mask=foe_result['contraction_mask'],
-        'divergence_map': foe_result['divergence_map'],
+        divergence_map=foe_result['divergence_map'],
-        'foe_points': [],
+        centroid_found=foe_result['centroid_found']
-        'expansion_regions': []
+    )
-    }
     
     # 处理所有轮廓，过滤并计算焦点
     if '_all_contours' in foe_result:
@@ -304,7 +328,9 @@ def compute_multiple_foe(flow_field, min_magnitude=1.0, expansion_threshold=0.00
                 if M["m00"] > 0:
                     cx = int(M["m10"] / M["m00"])
                     cy = int(M["m01"] / M["m00"])
-                    result['foe_points'].append((cx, cy))
+                    result['centroid'].append((cx, cy))
-                    result['expansion_regions'].append(contour)
+                    if 'contour' not in result:
+                        result['contour'] = []
+                    result['contour'].append(contour)
     
     return result

src/orisys/sensor.py

@@ -45,6 +45,8 @@ class Sensor:
         FNORMAL = auto()
         FSHEARX = auto()
         FSHEARY = auto()
+        CENTROID = auto()
+        CONTOUR = auto()
         DEPTH = auto()
 
     # =========================================================================
@@ -91,15 +93,22 @@ class Sensor:
         self.vupdate = False
         self.stitch_calibration = []
         
-        # Data variables
+        # Data Variables
         self.img = None
+        self.img_size_raw = None
         self.img_filtered = None
         self.flow = None
         self.vnormal = None
-        self.shear = None
+        self.vshear = None
-        self.depth = None
+        # self.depth = None
         self.n_boxes = None
         self.fnormal = self.fshearx = self.fsheary = self.ftor = 0.0
+
+        # Contact Data Variables
+        self.centroid = None
+        self.centroid_found = False
+        self.contour = None
+        self.depth_map = None
         
         # Timing
         self.last_log_time = time.perf_counter()
@@ -116,7 +125,11 @@ class Sensor:
         self._stop_event = None
 
         # Load configuration
+        self.config_cam = None
+        self.config_stitcher = None
+        self.config_contact = None
         self._load_config()
+        
 
         # Initialize components
         self._stitcher = Stitcher(isstitch=isstitch, index=self.config_index)
@@ -167,7 +180,8 @@ class Sensor:
         if log_timing: t0 = time.perf_counter()
         img = np.ascontiguousarray(self._stitcher.stitch_rt_optimized())
         if log_timing: timings['stitch'] = (time.perf_counter() - t0) * 1000
-        
+
+        self.img_size_raw = img.shape
         # Resize
         img = cv2.resize(img, tuple(self.config_resolution_stitch), interpolation=cv2.INTER_CUBIC)
         
@@ -222,7 +236,7 @@ class Sensor:
         
         # Get components
         self.vnormal = self.hhd.get_normal()
-        self.shear = self.hhd.get_shear()
+        self.vshear = self.hhd.get_shear()
         
         # # Depth computation
         # if log_timing: t0 = time.perf_counter()
@@ -244,21 +258,31 @@ class Sensor:
 
         return self.flow
 
-    def get_contact(self, multiple_foe=False, min_contour_area=3000, min_magnitude=1.0, expansion_threshold=0.01, downsample_factor=1, kernel_size=(5,5), denoise_sigma=15):
+    def compute_contact(self, multiple_foe=False, min_contour_area=3000, min_magnitude=1.0, expansion_threshold=0.01, downsample_factor=1, kernel_size=(5,5), denoise_sigma=15):
         
         if multiple_foe:
-            return compute_multiple_foe(self.vnormal, min_contour_area=min_contour_area, min_magnitude=min_magnitude, expansion_threshold=expansion_threshold, downsample_factor=downsample_factor, kernel_size=kernel_size, denoise_sigma=denoise_sigma)
+            result = compute_multiple_foe(self.vnormal, min_contour_area=min_contour_area, min_magnitude=min_magnitude, expansion_threshold=expansion_threshold, downsample_factor=downsample_factor, kernel_size=kernel_size, denoise_sigma=denoise_sigma)
-        else:
+
-            if self.cuda:  
+        else:
-                return compute_foe_gpu(self.vnormal, min_magnitude=min_magnitude, expansion_threshold=expansion_threshold, downsample_factor=downsample_factor, kernel_size=kernel_size, denoise_sigma=denoise_sigma)
+            if self.cuda: 
-                
+                result = compute_foe_gpu(self.vnormal, min_magnitude=min_magnitude, expansion_threshold=expansion_threshold, downsample_factor=downsample_factor, kernel_size=kernel_size, denoise_sigma=denoise_sigma)
-            else:
+
-                return compute_foe(self.vnormal, min_magnitude=min_magnitude, expansion_threshold=expansion_threshold, downsample_factor=downsample_factor, kernel_size=kernel_size, denoise_sigma=denoise_sigma)
+            else:
-                
+                result = compute_foe(self.vnormal, min_magnitude=min_magnitude, expansion_threshold=expansion_threshold, downsample_factor=downsample_factor, kernel_size=kernel_size, denoise_sigma=denoise_sigma)
+
+        self.centroid = result['centroid']
+        self.centroid_found = result['centroid_found']
+        if 'contour' in result:
+            self.contour = result['contour']
+        self.depth_map = result['divergence_map']
+
+        return result
+    
+
+    # def get_depth(self, denoise_sigma=15):
+    #     return getFilteredDensity(self.vnormal, use_cuda=self.cuda)
+    #     self.depth = getFilteredDensity(self.vnormal, use_cuda=self.cuda)   
 
-    def get_depth(self, denoise_sigma=15):
-        return getFilteredDensity(self.vnormal, use_cuda=self.cuda)
-        self.depth = getFilteredDensity(self.vnormal, use_cuda=self.cuda)   
     def update(self):
         """
         Convenience method: get_img + compute_deformation in one call.
@@ -270,7 +294,7 @@ class Sensor:
         self.compute_deformation()
         return {
             'img': self.img, 'flow': self.flow,
-            'normal': self.vnormal, 'shear': self.shear, 'depth': self.depth,
+            'normal': self.vnormal, 'shear': self.vshear, 'depth': self.depth,
             'fps': self.fps, 'fnormal': self.fnormal,
             'fshearx': self.fshearx, 'fsheary': self.fsheary, 'ftor': self.ftor,
         }
@@ -291,13 +315,15 @@ class Sensor:
         mapping = {
             self.info.VRAW: lambda: self.flow if self.flow is not None else np.array([]),
             self.info.VNORMAL: lambda: self.vnormal if self.vnormal is not None else np.array([]),
-            self.info.VSHEAR: lambda: self.shear if self.shear is not None else np.array([]),
+            self.info.VSHEAR: lambda: self.vshear if self.vshear is not None else np.array([]),
             self.info.FNORMAL: lambda: self.fnormal,
             self.info.FSHEARX: lambda: self.fshearx,
             self.info.FSHEARY: lambda: self.fsheary,
             self.info.FPS: lambda: self.fps,
             self.info.TIMESTAMP: lambda: time.strftime('%H:%M:%S'),
-            self.info.DEPTH: lambda: self.depth if self.depth is not None else np.array([]),
+            self.info.DEPTH: lambda: self.depth_map if self.depth_map is not None else np.array([]),
+            self.info.CENTROID: lambda: self.centroid if self.centroid is not None else np.array([]),
+            self.info.CONTOUR: lambda: self.contour if self.contour is not None else np.array([]),
         }
         
         return tuple(mapping.get(arg, lambda: None)() for arg in args if isinstance(arg, self.info))
@@ -431,6 +457,12 @@ class Sensor:
         self.config_index = cam["index"]
         self.config_pos_default = cam["pos_default"]
 
+        config_stitcher = self.config["stitcher"]
+
+        config_contact = self.config["contact"]
+
+        
+
         if self.verbose:
             print(f"Config: {self.config_name}")
             print(f"  Resolution: {self.config_resolution_raw} → {self.config_resolution_stitch}")
@@ -579,7 +611,7 @@ class Sensor:
         while not self._stop_event.is_set():
             try:
                 img, flow = self._flow_queue.get(timeout=0.1)
-                contact_result = self.get_contact(flow)
+                contact_result = self.compute_contact(flow)
                 self._queue_put(self._result_queue, contact_result)
             except Empty:
                 continue

src/orisys/util.py

@@ -132,37 +132,35 @@ def draw_fps(image, fps):
     return image
 
 
-def draw_foe(image, foe_result, point_color=(0, 255, 0), region_color=(0, 255, 255)):
+def draw_contact(image, contour, centroid, point_color=(0, 255, 0), region_color=(0, 255, 255)):
     """
     在图像上绘制扩张焦点和扩张区域。
     
     Args:
         image: 背景图像
-        foe_result: compute_foe 函数的返回结果
+        contour: 轮廓
-        point_color: 焦点点的颜色 (BGR)
+        centroid: 触碰点
-        region_color: 扩张区域轮廓的颜色 (BGR)
+        point_color: 触碰点的颜色 (BGR)
+        region_color: 轮廓的颜色 (BGR)
         
     Returns:
-        np.ndarray: 绘制了焦点和区域的图像
+        np.ndarray: 绘制了触碰点和轮廓的图像
     """
     image = image.copy()
     
     # 绘制扩张区域轮廓
-    if 'expansion_region' in foe_result:
+    if contour is not None:
-        cv2.drawContours(image, [foe_result['expansion_region']], -1, region_color, 2)
+        cv2.drawContours(image, [contour], -1, region_color, 2)
     
-    # 绘制焦点点
+    # 绘制触碰点
-    if 'foe_point' in foe_result:
+    if centroid is not None:
-        cx, cy = foe_result['foe_point']
+        cx, cy = centroid
         cv2.circle(image, (cx, cy), 8, point_color, -1)
         cv2.circle(image, (cx, cy), 10, point_color, 2)
-        cv2.putText(image, "FOE", (cx + 15, cy), 
-                   cv2.FONT_HERSHEY_SIMPLEX, 0.6, point_color, 2)
     
     return image
 
 
-
 def draw_multiple_foe(image, foe_result, point_color=(0, 255, 0), 
                        region_color=(0, 255, 255), label_colors=None):
     """