diff --git a/config/compound_eye.png b/config/compound_eye.png index 452a7d4..499308c 100644 Binary files a/config/compound_eye.png and b/config/compound_eye.png differ diff --git a/example1_basic.py b/example1_basic.py deleted file mode 100644 index e15e0c0..0000000 --- a/example1_basic.py +++ /dev/null @@ -1,112 +0,0 @@ -""" -示例 1: 基础用法 - 单传感器同步处理 - -本示例演示 OrisysSensor 的基本使用流程： -1. 初始化传感器（视频文件或摄像头） -2. 循环获取图像并计算形变 -3. 读取各类传感器数据 -4. 可视化显示 - -适用场景：单传感器、简单应用、学习入门 -""" - -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 - - -def main(): - # ========================================================================= - # 1. 初始化传感器 - # ========================================================================= - # 参数说明： - # vid_src: 视频源，可以是文件路径（如 "./s1.mp4"）或摄像头索引（如 0） - # isstitch: 是否启用复眼拼接模式（多单元传感器需要开启） - # cuda: 是否使用 CUDA GPU 加速（需要 CuPy 和 CUDA 支持） - # verbose: 是否打印详细初始化日志 - - # 方式1: 从视频文件读取 - sensor = orisys.Sensor("./s1.mp4", isstitch=True, cuda=True, verbose=True,config_name="prototype") - - # 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") - - # ========================================================================= - # 2. 主循环：获取图像 → 计算形变 → 读取数据 → 显示 - # ========================================================================= - 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() - - # 步骤 2.3: 读取传感器数据 - # read_info() 支持以下数据类型： - # 向量场数据： - # - VRAW: 原始光流场 (H, W, 2) 的 numpy 数组 - # - VNORMAL: 法向分量场 - # - VSHEAR: 切向分量场 - # 标量数据： - # - FNORMAL: 法向力总和（正压力） - # - FSHEARX: X方向切向力 - # - FSHEARY: Y方向切向力 - # 其他： - # - FPS: 当前帧率 - # - TIMESTAMP: 时间戳字符串 - fps, fn, fx, fy, flow = sensor.read_info( - sensor.info.FPS, - sensor.info.FNORMAL, - sensor.info.FSHEARX, - sensor.info.FSHEARY, - sensor.info.VRAW - ) - - # 打印力的数值 - print(f"FPS: {fps:5.1f}, 法向力: {fn:8.2f}, 切向力X: {fx:8.2f}, 切向力Y: {fy:8.2f}") - - # ===================================================================== - # 3. 可视化显示 - # ===================================================================== - # 绘制光流箭头图 - # 参数说明： - # img: 背景图像 - # flow: 光流场 - # threshold: 显示阈值（小于此值的箭头不显示） - # grid_spacing: 箭头网格间距（像素） - # arrow_scale: 箭头缩放比例 - arrows = orisys.util.draw_arrows( - sensor.img.copy(), # 使用 copy() 避免修改原图 - flow, - threshold=5, - grid_spacing=40, - arrow_scale=1.0 - ) - cv2.imshow("形变场 Deformation", arrows) - - - # ===================================================================== - # 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/example_contact.py b/example1_basic_pipeline.py similarity index 64% rename from example_contact.py rename to example1_basic_pipeline.py index a011dc7..de5452f 100644 --- a/example_contact.py +++ b/example1_basic_pipeline.py @@ -1,30 +1,42 @@ +""" +示例 1: 基础用法 - 单传感器同步处理 + +本示例演示 OrisysSensor 的基本使用流程： +1. 初始化传感器（视频文件或摄像头） +2. 循环获取图像并计算形变 +3. 读取各类传感器数据 + +适用场景：单传感器、简单应用、学习入门 +""" 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 +os.environ["OPENCV_VIDEOIO_MSMF_ENABLE_HW_TRANSFORMS"] = "0" import cv2 import orisys import numpy as np -import time def main(): + # 步骤1：创建传感器对象 (必要步骤)，config_name为配置文件名（内置配置文件名）或路径（自定义配置文件路径） + # 方式1: 从视频文件读取 # sensor = orisys.Sensor("./s1.mp4", isstitch=True, cuda=True, verbose=True,config_name="prototype") - # 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,config_name="prototype") + # 方式2: 从摄像头读取（取消注释使用） + sensor = orisys.Sensor(0, cuda=True, verbose=True, config_name="prototype") 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：信息提取 + # 步骤 2.1: 获取并拼接图像 (必要步骤) + sensor.get_img() - # 步骤 2.2: 计算形变场 + # 步骤 2.2: 计算形变场 (必要步骤) sensor.compute_deformation() - # 计算触碰点 - # sensor.compute_contact(min_magnitude=0.1,expansion_threshold=0.01,denoise_sigma=15) + # 步骤 2.3: 计算触碰点 sensor.compute_contact() - #计算后读取信息 + #步骤 2.4: 读取信息 fps, flow, vnormal, img, contour, centroid, depth_map = sensor.read_info( sensor.info.FPS, sensor.info.VRAW, @@ -34,20 +46,23 @@ def main(): sensor.info.CENTROID, sensor.info.DEPTH ) - + + #步骤 3: 可视化显示 + # 步骤 3.1: 绘制形变场 arrows = orisys.util.draw_arrows( - img, # 使用 copy() 避免修改原图 - vnormal, + img, + flow, threshold=5, grid_spacing=10, arrow_scale=1.0 ) cv2.imshow("形变场 Deformation", arrows) - # 在图像上触碰点和区域 + # 步骤 3.2: 在图像上触碰点和区域 image_with_foe = orisys.util.draw_contact(img, contour, centroid) cv2.imshow("Contact Centroid", image_with_foe) - + + # 步骤 3.3: 绘制深度图 # 归一化散度值到0-255范围（使用绝对值，然后归一化） div_abs = depth_map if div_abs.max() > div_abs.min(): @@ -58,12 +73,10 @@ def main(): # 应用颜色映射（使用JET：蓝色=低散度，红色=高散度） cv2.imshow("Depth Map", cv2.applyColorMap(div_normalized, cv2.COLORMAP_JET)) + #步骤 3.4: 打印资料 print(f"fps: {fps}") - - # ===================================================================== - # 4. 键盘控制 - # ===================================================================== + #步骤 3.5: 键盘控制 key = cv2.waitKey(1) & 0xFF if key == ord("q"): print("\n退出程序...") @@ -74,10 +87,9 @@ def main(): print("光流追踪器已重置") # ========================================================================= - # 5. 清理资源 + # 4. 清理资源 # ========================================================================= sensor.disconnect() # 释放视频源和相关资源 - cv2.destroyAllWindows() if __name__ == '__main__': diff --git a/example3_manual_box.py b/example3_manual_box.py deleted file mode 100644 index 3a46e1a..0000000 --- a/example3_manual_box.py +++ /dev/null @@ -1,45 +0,0 @@ -import os -os.environ["OPENCV_VIDEOIO_MSMF_ENABLE_HW_TRANSFORMS"] = "0" -import cv2 -import orisys - -def main(): - global start_time - - box = [] - dx = 90 - dy = -95 - for i in range(15): - box.append((410+dx, 900+dy, 620+dx, 1110+dy)) - # 打开视频，手动设置box 的坐标 - sensor1 = orisys.Sensor("./s1.mp4",isstitch=False,cuda = True,verbose = True, override=True, box=box) - # sensor1 = orisys.Sensor("./uv_2.mp4",isstitch=True,cuda = True,verbose = True, override=True, box=box) - # 打开摄像头 - # sensor1 = Sensor(0,isstitch=True,cuda = True,verbose = True) - - - while True: - sensor1.get_img() # 提取并拼接复眼图像 - sensor1.compute_deformation() # 计算形变和分解 - # 提取信息： - # 向量场: VRAW, VNORMAL, VSHEAR: 原始，法向，切向 - # 帧率，时间戳: FPS, TIMESTAMP - # 变形量总和: FNORMAL , FSHEARX, FSHEARY : 法向，切向（X)，切向（Y) - fps, fn, fx, fy, flow = sensor1.read_info(sensor1.info.FPS, sensor1.info.FNORMAL, sensor1.info.FSHEARX, sensor1.info.FSHEARY, sensor1.info.VRAW) - print(fps,fn,fx,fy) - # 显示向量场 - arrows = orisys.util.draw_arrows(sensor1.img, flow, threshold=5, grid_spacing=40, arrow_scale=1.0) - cv2.imshow("Deformation", arrows) - - key = cv2.waitKey(1) - if key & 0xFF == ord("q"): - print("\n 停止程序") - break - if key & 0xFF == ord("r"): - sensor1.reset() - - sensor1.disconnect() # 断开传感器连接 - - -if __name__ == '__main__': - main() diff --git a/src/orisys/Stitcher.py b/src/orisys/Stitcher.py index 55545a4..9aa6fa1 100644 --- a/src/orisys/Stitcher.py +++ b/src/orisys/Stitcher.py @@ -27,9 +27,9 @@ class Stitcher: self.nominal_ov_pos=config_stitcher["nominal_ov_pos"] self.margin=config_stitcher["margin"] self.bound=self.nominal_ov_pos - self.margin - - # for sensor 1 - self.pos_default = config_stitcher["pos_default"] + + if self.verbose: + print(f"Stitcher initialized with config: {self.config_stitcher}") def stitch_rt_optimized(self, change_sv=False, s_mean=28., v_mean=180.): tile_list = self.tile_list diff --git a/src/orisys/configs/prototype.json b/src/orisys/configs/prototype.json index 9b79c55..5330393 100644 --- a/src/orisys/configs/prototype.json +++ b/src/orisys/configs/prototype.json @@ -11,19 +11,24 @@ "stitcher": { "min_area_frac": 0.018, "max_area_frac": 0.035, - "max_aspect_ratio": 20, + "max_aspect_ratio": 100, "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]], "margin": 10, "nominal_ov_pos": 100, "n": [3,3] }, + "tracker": { + "adaptive": true, + "lower_threshold": 12.0, + "upper_threshold": 18.0, + "loop_closure_interval": 1, + "dis_preset": "medium" + }, "contact": { "min_contour_area": 3000, "flow_threshold":1, "div_threshold":0.02, "expansion_threshold": 0.01, - "downsample_factor": 1, "kernel_size": [5,5], "denoise_sigma": 15 } diff --git a/src/orisys/configs/sample_1.json b/src/orisys/configs/sample_1.json index 89b7f96..25f07bb 100644 --- a/src/orisys/configs/sample_1.json +++ b/src/orisys/configs/sample_1.json @@ -19,7 +19,7 @@ "min_contour_area": 3000, "min_magnitude": 1.0, "expansion_threshold": 0.01, - "downsample_factor": 1, + "contact_ds_factor": 10, "kernel_size": [5,5], "denoise_sigma": 15 } diff --git a/src/orisys/get_depth.py b/src/orisys/get_depth.py index dfdd0d6..3902337 100644 --- a/src/orisys/get_depth.py +++ b/src/orisys/get_depth.py @@ -19,7 +19,7 @@ class Contact3D: self.config_contact = config_contact self.flow_threshold = config_contact["flow_threshold"] self.expansion_threshold = config_contact["expansion_threshold"] - self.downsample_factor = config_contact["downsample_factor"] + self.downsample_factor = 1 self.kernel_size = config_contact["kernel_size"] self.denoise_sigma = config_contact["denoise_sigma"] self.min_contour_area = config_contact["min_contour_area"] @@ -75,7 +75,6 @@ class Contact3D: return result def compute_foe(self, flow_field, return_all_contours=False): - # def compute_foe(self, 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)。 diff --git a/src/orisys/sensor.py b/src/orisys/sensor.py index 96cd443..0ffcae8 100644 --- a/src/orisys/sensor.py +++ b/src/orisys/sensor.py @@ -53,16 +53,16 @@ class Sensor: # Initialization # ========================================================================= - def __init__(self, vid_src, isstitch=False, verbose=True, cuda=True, - config_name="prototype", cal_path=None, override=False, box=None,mirror=True): + def __init__(self, vid_src, cuda=True, isstitch=True, verbose=True, + config_name="prototype", cal_path=None, override=False, box=None, mirror=True): """ Initialize Sensor with video source and configuration. Args: vid_src: Video source (int for camera ID, str for file path) + cuda: Enable CUDA acceleration (default: True) isstitch: Enable stitching mode for multi-tile sensor (default: False) verbose: Print initialization logs (default: True) - cuda: Enable CUDA acceleration (default: True) config_name: Configuration name (default: "prototype") cal_path: Path to calibration file (default: None) override: Skip auto-detection, use provided box (default: False) @@ -89,9 +89,9 @@ class Sensor: # State variables self.stitch_valid = False - self.imgupdate = False - self.vupdate = False self.stitch_calibration = [] + self.compute_deformation_valid = False + self.compute_contact_valid = False # Data Variables self.__img = None @@ -193,7 +193,6 @@ class Sensor: self.__img_filtered = alpha * img + (1 - alpha) * self.__img_filtered self.__img = self.__img_filtered.astype(np.uint8) - self.__imgupdate = True if log_timing: timings['total'] = (time.perf_counter() - t_start) * 1000 @@ -210,6 +209,8 @@ class Sensor: Returns: np.ndarray: Optical flow field """ + if self.__img is None: + raise Exception("Warning: Get image first") if log_timing: timings = {} t_start = time.perf_counter() @@ -245,9 +246,7 @@ class Sensor: # Update state self.__flow = flow - self.imgupdate = False - self.vupdate = True - + self.compute_deformation_valid = True # FPS calculation self._fps = 1.0 / (time.perf_counter() - self.last_log_time) self.last_log_time = time.perf_counter() @@ -258,8 +257,13 @@ class Sensor: return True - 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): + def compute_contact(self): + multiple_foe=False + + if not self.compute_deformation_valid: + raise Exception("Warning: Compute deformation first") + if multiple_foe: result = self.__contact3d.compute_multiple_foe(self.__vnormal) else: @@ -274,6 +278,7 @@ class Sensor: self.__contour = result['contour'] self.__depth_map = result['divergence_map'] + self.compute_contact_valid = True return True @@ -307,9 +312,18 @@ class Sensor: Returns: Tuple: Requested data in order """ - if not self.vupdate: - print("Warning: Call compute_deformation() first.") - + if any(arg in [self.info.IMG] for arg in args): + if self.__img is None: + raise Exception("Warning: Get image first") + + if any(arg in [self.info.VRAW, self.info.VNORMAL, self.info.VSHEAR, self.info.FNORMAL, self.info.FSHEARX, self.info.FSHEARY] for arg in args): + if not self.compute_deformation_valid: + raise Exception("Warning: Compute deformation first") + + if any(arg in [self.info.CENTROID, self.info.CONTOUR, self.info.DEPTH] for arg in args): + if not self.compute_contact_valid: + raise Exception("Warning: Compute contact first") + mapping = { # Return copies of arrays to prevent external modification of internal state self.info.VRAW: lambda: self.__flow.copy() if self.__flow is not None else np.array([]), diff --git a/src/orisys/util.py b/src/orisys/util.py index 7be998c..9df36d4 100644 --- a/src/orisys/util.py +++ b/src/orisys/util.py @@ -75,62 +75,6 @@ def draw_arrows(image, optical_flow,fps=True, threshold=5, grid_spacing=40, arro cv2.arrowedLine(image, (x_axis[i], y_axis[i]), (end_x[i], end_y[i]), color, thickness=thickness, tipLength=0.3) return image -def draw_magnitude_map(image, flow_field, threshold=3.0, colormap=cv2.COLORMAP_JET,downsample_factor=10): - """ - Draw color map of pointwise magnitude of velocity field. - - Args: - info_type: Type of flow field to visualize (VRAW, VNORMAL, VSHEAR, or None for total) - threshold: Minimum magnitude to display (below threshold shows as zero/blue) - colormap: OpenCV colormap to use (default: COLORMAP_JET) - - Returns: - np.ndarray: 400x400 BGR image with colored magnitude map - """ - - # Compute magnitude at each point - magnitude = np.sqrt(flow_field[:, :, 0]**2 + flow_field[:, :, 1]**2) - - # Smooth by downsampling and interpolating back - h, w = magnitude.shape - magnitude_downsampled = magnitude[::downsample_factor, ::downsample_factor] - magnitude_smoothed = cv2.resize(magnitude_downsampled, (w, h), interpolation=cv2.INTER_CUBIC) - - # Apply threshold - set below-threshold values to zero - magnitude_thresholded = magnitude_smoothed.copy() - magnitude_thresholded[magnitude_smoothed < threshold] = 0 - - # Normalize to 0-255 range - mag_min, mag_max = magnitude_thresholded.min(), magnitude_thresholded.max() - if mag_max > mag_min: - magnitude_norm = ((magnitude_thresholded - mag_min) / (mag_max - mag_min) * 255).astype(np.uint8) - else: - magnitude_norm = np.zeros_like(magnitude_thresholded, dtype=np.uint8) - - # Apply colormap - magnitude_colored = cv2.applyColorMap(magnitude_norm, colormap) - - return magnitude_colored - -def draw_fps(image, fps): - """ - Draw FPS counter on the top left corner of the image. - """ - font_scale=0.5 - thickness=2 - color=(0, 255, 0) - image = image.copy() - - # Draw FPS text - fps_text = f"FPS: {fps:.1f}" - position = (10, 30) # Top left corner with margin - font = cv2.FONT_HERSHEY_SIMPLEX - - # Draw FPS text - cv2.putText(image, fps_text, position, font, font_scale, color, thickness, cv2.LINE_AA) - - return image - def draw_contact(image, contour, centroid, point_color=(0, 255, 0), region_color=(0, 255, 255)): """ @@ -159,60 +103,3 @@ def draw_contact(image, contour, centroid, point_color=(0, 255, 0), region_color cv2.circle(image, (cx, cy), 10, 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): - """ - 在图像上绘制多个扩张焦点和扩张区域。 - - Args: - image: 背景图像 - foe_result: compute_multiple_foe 函数的返回结果 - point_color: 默认焦点点的颜色 (BGR) - region_color: 扩张区域轮廓的颜色 (BGR) - label_colors: 可选的颜色列表，用于不同焦点的标签颜色 - - Returns: - np.ndarray: 绘制了多个焦点和区域的图像 - """ - image = image.copy() - - # 默认标签颜色（彩虹色系） - if label_colors is None: - label_colors = [ - (255, 0, 0), # 蓝色 - (0, 255, 0), # 绿色 - (0, 0, 255), # 红色 - (255, 255, 0), # 青色 - (255, 0, 255), # 洋红色 - (0, 255, 255), # 黄色 - (255, 128, 0), # 橙色 - (128, 0, 255) # 紫色 - ] - - # 绘制扩张区域轮廓 - if 'expansion_regions' in foe_result and foe_result['expansion_regions']: - cv2.drawContours(image, foe_result['expansion_regions'], -1, region_color, 2) - - # 绘制焦点点并添加标签 - if 'foe_points' in foe_result: - for i, (cx, cy) in enumerate(foe_result['foe_points']): - # 选择颜色（循环使用颜色列表） - color = label_colors[i % len(label_colors)] - - # 绘制焦点点 - cv2.circle(image, (cx, cy), 8, color, -1) - cv2.circle(image, (cx, cy), 10, color, 2) - - # 添加标签 - label = f"FOE{i+1}" - cv2.putText(image, label, (cx + 15, cy), - cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2) - - # 显示检测到的焦点数量 - foe_count = len(foe_result.get('foe_points', [])) - cv2.putText(image, f"FOE Count: {foe_count}", (10, 60), - cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2) - - return image \ No newline at end of file