diff --git a/main.py b/main.py index 58db2a9..c81c531 100755 --- a/main.py +++ b/main.py @@ -60,42 +60,27 @@ def main(): msg = robot_control_cmd_lcmt() print('2') try: - # TEST - # print('yuyin') - # cv_image = Ctrl.image_processor.get_current_image('ai') - # print('111') - # cv2.imwrite(f"saved_images/firstai.jpg", cv_image) - # print('try out') - # speak('nihao') - - # TEST - # go_straight_with_enhanced_calibration(Ctrl, msg, distance = 5, speed=0.5, observe=False, mode=11, gait_id=3, step_height=[0.21, 0.21]) - # pass_up_down(Ctrl, msg) - # pass_bar(Ctrl, msg) - # run_task_2(Ctrl, msg) - # INFO Real Task # TAG task - 0 info("Recovery stand", "info") Ctrl.base_msg.stand_up() Ctrl.base_msg.stop() # BUG 垃圾指令 for eat # INFO 但是正式比赛或许也有用 - # image = Ctrl.image_processor.get_current_image('ai') - # timestamp = datetime.now().strftime("%Y%m%d_%H%M%S_%f") - # filename = f"saved_images/rgb_{timestamp}.jpg" - # cv2.imwrite(filename, image) - if TASK == TaskType.PASS_BAR: from task_4.pass_bar import pass_bar # TEST #1: pass-bar pass_bar(Ctrl, msg) elif TASK == TaskType.YELLOW_LIGHT: # TODO image from task_3.task_3 import go_until_yellow_area +<<<<<<< HEAD # turn_degree_v2(Ctrl, msg, degree=-90, absolute=True) go_until_yellow_area(Ctrl, msg, yellow_ratio_threshold=0.012, speed=0.3, max_time=30, observe=True) +======= + go_until_yellow_area(Ctrl, msg, yellow_ratio_threshold=0.05) +>>>>>>> 00b77fe2476f74be45267ef52a45138e41114e7b elif TASK == TaskType.RED_BAR: from task_4.task_4 import go_straight_until_red_bar - go_straight_until_red_bar(Ctrl, msg) + go_straight_until_red_bar(Ctrl, msg, red_ratio_threshold=0.18, step_distance=0.3) elif TASK == TaskType.UP_AND_DOWN: from task_3.task_3 import go_straight_with_enhanced_calibration go_straight_with_enhanced_calibration(Ctrl, msg, distance = 5, speed=0.5, observe=False, mode=11, gait_id=3, step_height=[0.21, 0.21]) @@ -108,16 +93,18 @@ def main(): elif TASK == TaskType.CENTER_ON_DUAL_TRACKS: from base_move.center_on_dual_tracks import center_on_dual_tracks center_on_dual_tracks(Ctrl, msg, max_deviation=10.0, observe=False, detect_height=0.3) +<<<<<<< HEAD else: pass +======= +>>>>>>> 00b77fe2476f74be45267ef52a45138e41114e7b if TASK != TaskType.TASK: # 如果不是 task 类型，直接返回 pass # TAG task - 1 # run_task_1(Ctrl, msg, time_sleep=TIME_SLEEP) - # TAG task - 2 # arrow_direction='left' @@ -126,8 +113,12 @@ def main(): # arrow_direction='left' # print('🏹 arrow_direction: ', arrow_direction) +<<<<<<< HEAD # arrow_direction = 'right' +======= + +>>>>>>> 00b77fe2476f74be45267ef52a45138e41114e7b # if(arrow_direction=='left'): speak("左侧路线") # else: speak("右侧路线") diff --git a/task_3/task_3.py b/task_3/task_3.py index 3f3341f..cd8fe88 100755 --- a/task_3/task_3.py +++ b/task_3/task_3.py @@ -27,7 +27,7 @@ from utils.speech_demo import speak logger = get_logger("任务3") observe = False -YELLOW_RATIO_THRESHOLD = 0.03 # TODO 黄色区域比例阈值 +YELLOW_RATIO_THRESHOLD = 0.04 # TODO 黄色区域比例阈值 def run_task_3(ctrl, msg, time_sleep=5000): section('任务3：上下坡', "启动") diff --git a/task_4/task_4.py b/task_4/task_4.py index c79ca96..fc937aa 100755 --- a/task_4/task_4.py +++ b/task_4/task_4.py @@ -87,7 +87,7 @@ def run_task_4_back(ctrl, msg): def go_straight_until_red_bar(ctrl, msg, red_ratio_threshold=0.2, - step_distance=0.5, + step_distance=0.3, max_distance=5, speed=0.3 ): diff --git a/test/text-image/README.md b/test/text-image/README.md new file mode 100644 index 0000000..9858614 --- /dev/null +++ b/test/text-image/README.md @@ -0,0 +1,49 @@ +# 数字识别程序 + +这是一个使用OpenCV识别图片中数字1和2的Python程序。 + +## 功能特点 + +- 使用OpenCV进行图像预处理和特征提取 +- 基于轮廓检测和特征分析的数字分类 +- 能够区分数字1和2的形态特征 +- 自动保存识别结果图片 + +## 安装依赖 + +```bash +pip install -r requirements.txt +``` + +## 使用方法 + +1. 将需要识别的图片放在`imgs/`文件夹中 +2. 运行程序： + ```bash + python text_image.py + ``` + +## 程序流程 + +1. **图像预处理**：转换为灰度图、高斯模糊去噪、自适应阈值二值化、形态学操作 +2. **轮廓检测**：查找图像中的轮廓，筛选可能的数字区域 +3. **特征提取**：提取ROI的像素密度、水平和垂直投影等特征 +4. **数字分类**：基于特征分析判断是数字1还是2 +5. **结果输出**：在原图上标注识别结果并保存 + +## 识别原理 + +- **数字1**：通常较细，垂直投影集中在中间，方差较小 +- **数字2**：通常较宽，有弯曲部分，垂直投影方差较大 + +## 输出文件 + +程序会在`imgs/`文件夹中生成： +- `result_1.jpg`：第一张图片的识别结果 +- `result_2.jpg`：第二张图片的识别结果 + +## 注意事项 + +- 确保图片清晰，数字对比度足够 +- 程序会自动过滤太小的轮廓 +- 识别结果包含位置信息和置信度 diff --git a/test/text-image/imgs/1.jpg b/test/text-image/imgs/1.jpg new file mode 100644 index 0000000..526afb9 Binary files /dev/null and b/test/text-image/imgs/1.jpg differ diff --git a/test/text-image/imgs/2.jpg b/test/text-image/imgs/2.jpg new file mode 100644 index 0000000..476f45a Binary files /dev/null and b/test/text-image/imgs/2.jpg differ diff --git a/test/text-image/imgs/result_1.jpg b/test/text-image/imgs/result_1.jpg new file mode 100644 index 0000000..cd7a969 Binary files /dev/null and b/test/text-image/imgs/result_1.jpg differ diff --git a/test/text-image/imgs/result_2.jpg b/test/text-image/imgs/result_2.jpg new file mode 100644 index 0000000..a7fa18e Binary files /dev/null and b/test/text-image/imgs/result_2.jpg differ diff --git a/test/text-image/requirements.txt b/test/text-image/requirements.txt new file mode 100644 index 0000000..8739c64 --- /dev/null +++ b/test/text-image/requirements.txt @@ -0,0 +1,3 @@ +opencv-python>=4.5.0 +numpy>=1.19.0 +pathlib diff --git a/test/text-image/text_image.py b/test/text-image/text_image.py new file mode 100644 index 0000000..89d2764 --- /dev/null +++ b/test/text-image/text_image.py @@ -0,0 +1,180 @@ +import cv2 +import numpy as np +import os +from pathlib import Path + +def preprocess_image(image): + """ + 预处理图像：转换为HSV色彩空间，检测白色区域 + """ + # 转换为HSV色彩空间 + hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV) + + # 定义白色的HSV范围 - 放宽范围 + # 白色在HSV中：饱和度低，明度高 + # 原来的范围：lower_white = np.array([0, 0, 200]), upper_white = np.array([180, 30, 255]) + # 放宽后的范围： + lower_white = np.array([0, 0, 150]) # 降低明度下限，从200降到150 + upper_white = np.array([180, 60, 255]) # 提高饱和度上限，从30提高到60 + + # 创建白色掩码 + white_mask = cv2.inRange(hsv, lower_white, upper_white) + + # 形态学操作：开运算去除小噪点，闭运算填充小孔 + kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5)) + cleaned = cv2.morphologyEx(white_mask, cv2.MORPH_OPEN, kernel) + cleaned = cv2.morphologyEx(cleaned, cv2.MORPH_CLOSE, kernel) + + return cleaned + +def find_white_rectangles(binary_image): + """ + 查找白色矩形区域 + """ + contours, _ = cv2.findContours( + binary_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE + ) + + # 筛选合适的矩形轮廓 + valid_rectangles = [] + for contour in contours: + area = cv2.contourArea(contour) + if area > 200: # 过滤太小的区域，从500降低到200 + # 计算轮廓的边界矩形 + x, y, w, h = cv2.boundingRect(contour) + + # 计算轮廓的近似多边形 + epsilon = 0.02 * cv2.arcLength(contour, True) + approx = cv2.approxPolyDP(contour, epsilon, True) + + # 检查是否为四边形（矩形） + if len(approx) == 4: + # 计算宽高比 + aspect_ratio = w / h + # 矩形应该有合理的宽高比（不是太细长） + if 0.3 < aspect_ratio < 3.0: + valid_rectangles.append((contour, (x, y, w, h), approx)) + + return valid_rectangles + +def analyze_white_region(roi, original_roi): + """ + 分析白色区域的特征 + """ + # 计算白色像素比例 + total_pixels = roi.shape[0] * roi.shape[1] + white_pixels = np.sum(roi == 255) + white_ratio = white_pixels / total_pixels + + # 计算区域的形状特征 + height, width = roi.shape + aspect_ratio = width / height + + # 计算边缘强度（白色区域应该有清晰的边缘） + edges = cv2.Canny(original_roi, 50, 150) + edge_density = np.sum(edges > 0) / total_pixels + + return { + 'white_ratio': white_ratio, + 'aspect_ratio': aspect_ratio, + 'edge_density': edge_density, + 'area': total_pixels + } + +def detect_white_rectangles_in_image(image_path): + """ + 检测图片中的白色矩形区域 + """ + # 读取图像 + image = cv2.imread(image_path) + if image is None: + print(f"无法读取图像: {image_path}") + return [] + + # 预处理 + white_mask = preprocess_image(image) + + # 查找白色矩形 + valid_rectangles = find_white_rectangles(white_mask) + + results = [] + + for contour, (x, y, w, h), approx in valid_rectangles: + # 提取ROI + roi_mask = white_mask[y:y+h, x:x+w] + roi_original = image[y:y+h, x:x+w] + + # 分析特征 + features = analyze_white_region(roi_mask, roi_original) + + # 判断是否为有效的白色矩形 + is_valid_white_rectangle = ( + features['white_ratio'] > 0.4 and # 白色像素比例要求降低，从0.6降到0.4 + features['edge_density'] > 0.005 # 边缘密度要求降低，从0.01降到0.005 + ) + + if is_valid_white_rectangle: + results.append({ + 'type': 'white_rectangle', + 'position': (x, y, w, h), + 'features': features, + 'confidence': 'high' if features['white_ratio'] > 0.8 else 'medium' + }) + + # 在图像上绘制结果 + cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2) + cv2.putText(image, f"白色矩形", (x, y - 10), + cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2) + + # 绘制轮廓点 + cv2.drawContours(image, [approx], -1, (255, 0, 0), 2) + + return image, results + +def main(): + """ + 主函数：测试白色矩形检测 + """ + # 图片路径 + img_dir = Path("imgs") + img1_path = img_dir / "1.jpg" + img2_path = img_dir / "2.jpg" + + print("开始检测图片中的白色矩形区域...") + + # 检测第一张图片 + if img1_path.exists(): + print(f"\n检测图片: {img1_path}") + result_img1, results1 = detect_white_rectangles_in_image(str(img1_path)) + + print("检测结果:") + for result in results1: + print(f" 类型: {result['type']}, 位置: {result['position']}, 置信度: {result['confidence']}") + print(f" 特征: 白色比例={result['features']['white_ratio']:.2f}, " + f"宽高比={result['features']['aspect_ratio']:.2f}") + + # 保存结果图片 + output_path1 = img_dir / "result_1.jpg" + cv2.imwrite(str(output_path1), result_img1) + print(f"结果图片已保存到: {output_path1}") + + # 检测第二张图片 + if img2_path.exists(): + print(f"\n检测图片: {img2_path}") + result_img2, results2 = detect_white_rectangles_in_image(str(img2_path)) + + print("检测结果:") + for result in results2: + print(f" 类型: {result['type']}, 位置: {result['position']}, 置信度: {result['confidence']}") + print(f" 特征: 白色比例={result['features']['white_ratio']:.2f}, " + f"宽高比={result['features']['aspect_ratio']:.2f}") + + # 保存结果图片 + output_path2 = img_dir / "result_2.jpg" + cv2.imwrite(str(output_path2), result_img2) + print(f"结果图片已保存到: {output_path2}") + + print("\n检测完成！") + +if __name__ == "__main__": + main() diff --git a/test/text_image.py b/test/text_image.py new file mode 100644 index 0000000..b28b04f --- /dev/null +++ b/test/text_image.py @@ -0,0 +1,3 @@ + + + diff --git a/utils/shoushi_demo.py b/utils/shoushi_demo.py index 1075cbb..2ab8ffe 100755 --- a/utils/shoushi_demo.py +++ b/utils/shoushi_demo.py @@ -118,58 +118,6 @@ class GestureControlNode(Node): elif msg.id == 7: # 停止手势 self.get_logger().info("检测到停止手势") - def complete_loading(self): - """完成配货操作""" - self.get_logger().info("配货完成，开始运输") - - # 调用开始运输服务 - if self.start_transport_cli.wait_for_service(timeout_sec=1.0): - req = Trigger.Request() - future = self.start_transport_cli.call_async(req) - future.add_done_callback(self.transport_start_callback) - else: - self.get_logger().warn("开始运输服务不可用") - - # 更新状态 - self.current_state = "transporting" - - def transport_start_callback(self, future): - """运输开始服务回调""" - try: - response = future.result() - if response.success: - self.get_logger().info("运输已开始") - else: - self.get_logger().warn("运输启动失败") - except Exception as e: - self.get_logger().error(f"运输服务调用失败: {e}") - - def complete_unloading(self): - """完成卸货操作""" - self.get_logger().info("卸货完成，准备新的配货") - - # 调用完成卸货服务 - if self.complete_unloading_cli.wait_for_service(timeout_sec=1.0): - req = Trigger.Request() - future = self.complete_unloading_cli.call_async(req) - future.add_done_callback(self.unloading_complete_callback) - else: - self.get_logger().warn("完成卸货服务不可用") - - # 更新状态 - self.current_state = "waiting_for_loading" - - def unloading_complete_callback(self, future): - """卸货完成服务回调""" - try: - response = future.result() - if response.success: - self.get_logger().info("卸货已完成确认") - else: - self.get_logger().warn("卸货完成确认失败") - except Exception as e: - self.get_logger().error(f"卸货完成服务调用失败: {e}") - def timer_callback(self): """定时器回调，用于状态检查和超时处理""" # 检查手势识别是否激活且超时 @@ -181,7 +129,6 @@ class GestureControlNode(Node): # 这里可以添加状态机逻辑，根据实际需求更新current_state # 例如，当机器狗到达配货区域时，设置self.current_state = "loading" # 当机器狗到达卸货区域时，设置self.current_state = "unloading" - def update_state(self, new_state): """更新机器狗状态""" old_state = self.current_state