diff --git a/src/Smart_car/overload.py b/src/Smart_car/overload.py index 1018554ae2..74076f98a4 100644 --- a/src/Smart_car/overload.py +++ b/src/Smart_car/overload.py @@ -2,39 +2,57 @@ import random class UnmannedVehicleOverloadWarningSystem: - """无人车超载预警系统""" + """无人车超载预警系统 + 功能:实时监测无人车载重状态,根据载重占比划分预警等级,输出可视化预警信息,严重超载时紧急停止系统 + """ def __init__(self, max_load=1000): - # 初始化系统参数 - self.max_load = max_load # 车辆最大载重(单位:kg,可自定义) - self.current_load = 0 # 当前载重 + # 初始化系统核心参数 + self.max_load = max_load # 车辆最大载重(单位:kg,可根据实际车型自定义配置) + self.current_load = 0 # 当前实时载重,初始值为0 self.warning_level = 0 # 预警等级:0-正常,1-轻度过载,2-中度过载,3-严重超载 def simulate_weight_collection(self): - """模拟无人车重量采集(模拟传感器数据,可替换为真实硬件接口)""" - # 模拟载重变化:每次在当前基础上小幅波动(模拟乘客/货物上下车) + """模拟无人车重量采集(模拟传感器数据,可替换为真实硬件接口) + 逻辑:在当前载重基础上随机小幅波动,模拟乘客上下车或货物装卸的载重变化 + 返回:更新后的当前载重值 + """ + # 模拟载重变化:每次波动范围为-50kg(卸载)到100kg(加载) weight_change = random.randint(-50, 100) - self.current_load = max(0, self.current_load + weight_change) # 载重不能为负数 + # 更新当前载重,确保载重不会为负数(最低为0) + self.current_load = max(0, self.current_load + weight_change) return self.current_load def judge_overload(self): - """超载判断逻辑,划分预警等级""" - load_ratio = self.current_load / self.max_load # 载重占比 + """超载判断逻辑,根据载重占比划分预警等级 + 计算规则:载重占比 = 当前载重 / 最大载重 + 返回值:(预警状态名称, 预警颜色标识, 处理建议描述) + """ + load_ratio = self.current_load / self.max_load # 计算载重占比,用于等级判定 + # 正常状态:载重≤80%最大载重,无需干预 if load_ratio <= 0.8: - self.warning_level = 0 # 正常:载重≤80%最大载重 + self.warning_level = 0 return "正常", "绿色", "当前载重未超出安全范围,无需处理" + # 轻度过载预警:80%<载重≤95%,接近上限需停止加载 elif 0.8 < load_ratio <= 0.95: - self.warning_level = 1 # 轻度过载:80%<载重≤95% + self.warning_level = 1 return "轻度过载预警", "黄色", "当前载重接近上限,建议停止加载" + # 中度过载警告:95%<载重≤110%,超出上限需卸载并停止运行 elif 0.95 < load_ratio <= 1.1: - self.warning_level = 2 # 中度过载:95%<载重≤110% + self.warning_level = 2 return "中度过载警告", "橙色", "当前载重已超出安全上限,立即停止运行并卸载部分货物" + # 严重超载警报:载重>110%,极度危险需紧急制动并联系工作人员 else: - self.warning_level = 3 # 严重超载:载重>110% + self.warning_level = 3 return "严重超载警报", "红色", "极度危险!立即紧急制动,联系工作人员处理" def display_warning(self, status, color, desc): - """可视化输出预警信息(模拟车载终端显示)""" + """可视化输出预警信息(模拟车载终端显示界面) + 参数: + status: 预警状态名称(如"正常"、"严重超载警报") + color: 预警颜色标识(如"绿色"、"红色") + desc: 具体处理建议描述 + """ print("=" * 50) print(f"【无人车超载预警系统 - 实时监测】") print(f"当前时间:{time.strftime('%Y-%m-%d %H:%M:%S')}") @@ -47,26 +65,31 @@ def display_warning(self, status, color, desc): print() def run(self, monitor_times=10): - """运行系统,持续监测载重并输出预警""" + """运行系统,持续循环监测载重并输出预警信息 + 参数: + monitor_times: 预设监测次数,默认10次,可根据需求修改 + 流程:采集载重→判断等级→显示预警→异常停止(严重超载)→间隔等待 + """ print("无人车超载预警系统已启动...") print(f"开始持续监测(共监测{monitor_times}次,每次间隔2秒)\n") + # 循环执行监测流程,达到预设次数或检测到严重超载时终止 for i in range(monitor_times): - # 1. 采集当前载重(模拟) + # 1. 采集当前载重(模拟传感器数据更新) self.simulate_weight_collection() - # 2. 判断超载等级 + # 2. 判断超载等级,获取预警相关信息 status, color, desc = self.judge_overload() - # 3. 显示预警信息 + # 3. 可视化输出预警详情(模拟车载终端展示) self.display_warning(status, color, desc) - # 4. 严重超载时紧急停止 + # 4. 严重超载(等级3)时,紧急停止系统运行 if self.warning_level == 3: print("❗❗❗ 检测到严重超载,系统紧急停止运行! ❗❗") break - # 5. 间隔2秒进行下一次监测 + # 5. 间隔2秒进行下一次监测,模拟实时周期性检测 time.sleep(2) if __name__ == "__main__": - # 初始化系统:设置无人车最大载重为1000kg(可根据需求修改) + # 初始化系统:设置无人车最大载重为1000kg(可根据车型/场景需求修改该参数) overload_system = UnmannedVehicleOverloadWarningSystem(max_load=1000) - # 运行系统,持续监测10次(可修改监测次数) + # 运行系统,持续监测10次(可修改monitor_times参数调整监测次数) overload_system.run(monitor_times=10) \ No newline at end of file diff --git a/src/Smart_car/traffic.py b/src/Smart_car/traffic.py new file mode 100644 index 0000000000..49ab35aa92 --- /dev/null +++ b/src/Smart_car/traffic.py @@ -0,0 +1,153 @@ +import cv2 +import numpy as np +import os +import time + + +def traffic_light_real_time_detection(): + """ + 摄像头实时交通信号灯三色识别函数 + """ + # 1. 初始化摄像头(0为默认内置摄像头,1为外接摄像头,可根据实际调整) + cap = cv2.VideoCapture(0) + if not cap.isOpened(): + print("错误:无法打开摄像头,请检查摄像头是否正常连接或被其他程序占用.") + return "摄像头初始化失败." + + # 设置摄像头分辨率(提升识别效率,可根据摄像头性能调整) + cap.set(cv2.CAP_PROP_FRAME_WIDTH, 640) + cap.set(cv2.CAP_PROP_FRAME_HEIGHT, 480) + + # 创建保存目录(用于保存抓拍结果) + save_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "real_time_detection_results") + if not os.path.exists(save_dir): + os.makedirs(save_dir) + red_lower1 = np.array([0, 100, 80]) + red_upper1 = np.array([10, 255, 255]) + red_lower2 = np.array([160, 100, 80]) + red_upper2 = np.array([180, 255, 255]) + + # 黄色 + yellow_lower = np.array([15, 120, 80]) + yellow_upper = np.array([35, 255, 255]) + + # 绿色 + green_lower = np.array([40, 80, 80]) + green_upper = np.array([80, 255, 255]) + + # 形态学操作核 + kernel = np.ones((3, 3), np.uint8) + # 轮廓检测参数 + contour_params = (cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) + # 自适应最小面积(基于摄像头分辨率) + min_area = (640 * 480) / 1000 + + print("摄像头已启动,实时交通信号灯检测中...") + print("操作提示:") + print(" 1. 按下 's' 键保存当前检测结果图像") + print(" 2. 按下 'ESC' 键退出程序") + + def filter_valid_contours(contours, min_area_val): + """筛选有效轮廓(面积+圆度,适配信号灯圆形特征)""" + valid = [] + for cnt in contours: + area = cv2.contourArea(cnt) + if area < min_area_val: + continue + perimeter = cv2.arcLength(cnt, True) + if perimeter == 0: + continue + circularity = (4 * np.pi * area) / (perimeter ** 2) + if circularity > 0.6: # 圆度筛选,排除非圆形噪声 + valid.append(cnt) + return valid + + while True: + # 3. 读取摄像头帧 + ret, frame = cap.read() + if not ret: + print("警告:无法读取摄像头帧,可能是摄像头断开连接") + break + + # 复制帧用于绘制结果 + frame_result = frame.copy() + # 转换为HSV色彩空间(抗光照干扰) + hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV) + + # 4. 颜色掩码生成 + red_mask = cv2.inRange(hsv, red_lower1, red_upper1) | cv2.inRange(hsv, red_lower2, red_upper2) + yellow_mask = cv2.inRange(hsv, yellow_lower, yellow_upper) + green_mask = cv2.inRange(hsv, green_lower, green_upper) + + # 5. 形态学操作优化掩码 + red_mask = cv2.morphologyEx(red_mask, cv2.MORPH_OPEN, kernel, iterations=1) + red_mask = cv2.morphologyEx(red_mask, cv2.MORPH_CLOSE, kernel, iterations=2) + yellow_mask = cv2.morphologyEx(yellow_mask, cv2.MORPH_OPEN, kernel, iterations=1) + yellow_mask = cv2.morphologyEx(yellow_mask, cv2.MORPH_CLOSE, kernel, iterations=2) + green_mask = cv2.morphologyEx(green_mask, cv2.MORPH_OPEN, kernel, iterations=1) + green_mask = cv2.morphologyEx(green_mask, cv2.MORPH_CLOSE, kernel, iterations=2) + + # 6. 轮廓检测与筛选 + red_contours, _ = cv2.findContours(red_mask, *contour_params) + yellow_contours, _ = cv2.findContours(yellow_mask, *contour_params) + green_contours, _ = cv2.findContours(green_mask, *contour_params) + + red_valid = filter_valid_contours(red_contours, min_area) + yellow_valid = filter_valid_contours(yellow_contours, min_area) + green_valid = filter_valid_contours(green_contours, min_area) + + # 7. 信号灯判断与可视化绘制 + light_color = "未检测到信号灯" + color_configs = [ + (red_valid, "红色信号灯", "Red", (0, 0, 255)), + (yellow_valid, "黄色信号灯", "Yellow", (0, 255, 255)), + (green_valid, "绿色信号灯", "Green", (0, 255, 0)) + ] + + for valid_contours, color_name, label, bgr_color in color_configs: + if len(valid_contours) > 0: + light_color = color_name + # 绘制轮廓和最小外接圆 + cv2.drawContours(frame_result, valid_contours, -1, bgr_color, 2) + for cnt in valid_contours: + (x, y), radius = cv2.minEnclosingCircle(cnt) + center = (int(x), int(y)) + radius = int(radius) + cv2.circle(frame_result, center, radius, bgr_color, 2) + # 绘制文字标签(避免超出图像边界) + text_y = int(y - radius - 10) if (y - radius - 10) > 10 else int(y + radius + 20) + cv2.putText(frame_result, label, (int(x) - 20, text_y), + cv2.FONT_HERSHEY_SIMPLEX, 0.6, bgr_color, 2) + break # 通常仅一种信号灯点亮,找到后退出循环 + + # 8. 在帧上添加信息提示 + cv2.putText(frame_result, f"Status: {light_color}", (10, 30), + cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2) + cv2.putText(frame_result, "Press 's' to save, 'ESC' to exit", (10, 60), + cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255), 1) + + # 9. 显示实时结果 + cv2.namedWindow("Real-Time Traffic Light Detection", cv2.WINDOW_NORMAL) + cv2.resizeWindow("Real-Time Traffic Light Detection", 640, 480) + cv2.imshow("Real-Time Traffic Light Detection", frame_result) + + # 10. 按键事件处理 + key = cv2.waitKey(1) & 0xFF + if key == 27: # ESC键退出 + print("程序已退出") + break + elif key == ord('s'): # 's'键保存结果 + timestamp = time.strftime("%Y%m%d_%H%M%S", time.localtime()) + save_path = os.path.join(save_dir, f"real_time_result_{timestamp}.jpg") + cv2.imwrite(save_path, frame_result) + print(f"当前检测结果已保存:{save_path}") + + # 释放资源 + cap.release() + cv2.destroyAllWindows() + return "实时检测结束" + + +# 主函数调用 +if __name__ == "__main__": + traffic_light_real_time_detection() \ No newline at end of file