diff --git a/README.md b/README.md deleted file mode 100644 index d362f30b07..0000000000 --- a/README.md +++ /dev/null @@ -1,54 +0,0 @@ -# 神经网络实现代理 - -利用神经网络/ROS 实现 Carla(车辆、行人的感知、规划、控制)、AirSim、Mujoco 中人和载具的代理。 - -## 环境配置 - -* 平台:Windows 10/11,Ubuntu 20.04/22.04 -* 软件:Python 3.7-3.12(需支持3.7)、Pytorch(尽量不使用Tensorflow) -* 相关软件下载 [链接](https://pan.baidu.com/s/1IFhCd8X9lI24oeYQm5-Edw?pwd=hutb) - -## 功能模块表 -| 模块类别 | 模块名 | 链接 | 其他 | -|-------------------|------------|-------------------------------------------------------------------------------|---------------------------------------------------------------------| -| 规划 | 车辆全局路径规划 | [carla_slam_gmapping](https://github.com/OpenHUTB/nn/tree/main/src/carla_slam_gmapping) | - | - - -## 贡献指南 - -准备提交代码之前,请阅读 [贡献指南](https://github.com/OpenHUTB/.github/blob/master/CONTRIBUTING.md) 。 -代码的优化包括:注释、[PEP 8 风格调整](https://peps.pythonlang.cn/pep-0008/) 、将神经网络应用到Carla模拟器中、撰写对应 [文档](https://openhutb.github.io/nn/) 、添加 [源代码对应的自动化测试](https://docs.github.com/zh/actions/use-cases-and-examples/building-and-testing/building-and-testing-python) 等(从Carla场景中获取神经网络所需数据或将神经网络的结果输出到场景中)。 - -### 约定 - -* 每个模块位于`src/{模块名}`目录下,`模块名`需要用2-3个单词表示,首字母不需要大写,下划线`_`分隔,不能宽泛,越具体越好 -* 每个模块的入口须为`main.`开头,比如:main.py、main.cpp、main.bat、main.sh等,提供的ROS功能以`main.launch`文件作为启动配置文件 -* 每次pull request都需要保证能够通过main脚本直接运行整个模块,在提交信息中提供运行动图或截图;Pull Request的标题不能随意,需要概括具体的修改内容;README.md文档中提供运行环境和运行步骤的说明 -* 仓库尽量保存文本文件,二进制文件需要慎重,如运行需要示例数据,可以保存少量数据,大量数据可以通过提供网盘链接并说明下载链接和运行说明 - - -### 文档生成 - -测试生成的文档: -1. 安装python 3.11,并使用以下命令安装`mkdocs`和相关依赖: -```shell -pip install mkdocs -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com -pip install -r requirements.txt -``` -(可选)安装完成后使用`mkdocs --version`查看是否安装成功。 - -2. 在命令行中进入`nn`目录下,运行: -```shell -mkdocs build -mkdocs serve -``` -然后使用浏览器打开 [http://127.0.0.1:8000](http://127.0.0.1:8000),查看文档页面能否正常显示。 - -## 参考 - -* [代理模拟器文档](https://openhutb.github.io) -* 已有相关 [无人车](https://openhutb.github.io/doc/used_by/) 、[无人机](https://openhutb.github.io/air_doc/third/used_by/) 、[具身人](https://openhutb.github.io/doc/pedestrian/humanoid/) 的实现 -* [神经网络原理](https://github.com/OpenHUTB/neuro) - -通过网盘分享的文件:supercombo.h5 -链接: https://pan.baidu.com/s/1yYc4aPBLnXRuWXEb0hyKMA?pwd=1234 提取码: 1234 \ No newline at end of file diff --git a/main.py b/main.py deleted file mode 100644 index 8ac2a835e6..0000000000 --- a/main.py +++ /dev/null @@ -1,118 +0,0 @@ -#!/usr/bin/env python3 -# -*- coding: utf-8 -*- -""" -Lane Line Detection (精简版) -核心功能:Canny边缘检测 + 霍夫变换实现车道线检测,单视频处理+结果保存 -适用环境:Ubuntu (Python 3.10 + OpenCV + numpy) -""" - -import cv2 -import numpy as np -import argparse -import os -from pathlib import Path - -# ===================== 核心参数(仅保留必要的) ===================== -# 车道线检测核心参数 -CANNY_LOW_THRESH = 50 # Canny边缘检测低阈值 -CANNY_HIGH_THRESH = 150 # Canny边缘检测高阈值 -HOUGH_RHO = 1 # 霍夫变换rho步长 -HOUGH_THETA = np.pi / 180 # 霍夫变换theta步长 -HOUGH_THRESHOLD = 20 # 霍夫变换阈值 -HOUGH_MIN_LINE_LEN = 40 # 最小线段长度 -HOUGH_MAX_LINE_GAP = 20 # 最大线段间隙 - -# ===================== 核心函数:车道线检测 ===================== -def detect_lane_lines(frame): - """核心:检测并绘制车道线(Canny + 霍夫变换)""" - # 1. 灰度化 + 高斯模糊 - gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) - blur = cv2.GaussianBlur(gray, (5, 5), 0) - - # 2. Canny边缘检测 - edges = cv2.Canny(blur, CANNY_LOW_THRESH, CANNY_HIGH_THRESH) - - # 3. 区域掩码(仅检测图像下半部分,聚焦车道) - h, w = frame.shape[:2] - mask = np.zeros_like(edges) - polygon = np.array([[(0, h), (w//2, h//2), (w, h)]], np.int32) - cv2.fillPoly(mask, polygon, 255) - masked_edges = cv2.bitwise_and(edges, mask) - - # 4. 霍夫变换检测直线 - lines = cv2.HoughLinesP( - masked_edges, HOUGH_RHO, HOUGH_THETA, HOUGH_THRESHOLD, - minLineLength=HOUGH_MIN_LINE_LEN, maxLineGap=HOUGH_MAX_LINE_GAP - ) - - # 5. 绘制车道线 - frame_with_lane = frame.copy() - if lines is not None: - for line in lines: - x1, y1, x2, y2 = line[0] - cv2.line(frame_with_lane, (x1, y1), (x2, y2), (0, 255, 0), 3) - - return frame_with_lane - -# ===================== 核心函数:视频处理 ===================== -def process_video(video_path, max_frames=10): - """处理单视频:读取帧→检测车道线→保存结果""" - # 校验视频文件 - if not os.path.exists(video_path): - print(f"错误:视频文件不存在 → {video_path}") - return - - # 打开视频流 - cap = cv2.VideoCapture(video_path) - if not cap.isOpened(): - print(f"错误:无法打开视频 → {video_path}") - return - - # 获取视频基础信息 - width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH)) - height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) - fps = int(cap.get(cv2.CAP_PROP_FPS)) or 25 - - # 初始化结果视频写入器 - video_name = Path(video_path).stem - result_path = f"{video_name}_lane_detected.mp4" - fourcc = cv2.VideoWriter_fourcc(*'mp4v') - writer = cv2.VideoWriter(result_path, fourcc, fps, (width, height)) - - # 逐帧处理 - count = 0 - print(f"开始处理视频(最大{max_frames}帧)...") - while cap.isOpened() and count < max_frames: - ret, frame = cap.read() - if not ret: - break - - # 核心:检测车道线 - frame_with_lane = detect_lane_lines(frame) - - # 写入结果视频 - writer.write(frame_with_lane) - - # 实时显示(可选,按Q退出) - cv2.imshow("Lane Detection", frame_with_lane) - if cv2.waitKey(10) & 0xFF == ord('q'): - break - - count += 1 - - # 释放资源 - cap.release() - writer.release() - cv2.destroyAllWindows() - print(f"处理完成!结果保存至 → {result_path}") - -# ===================== 主函数(精简参数) ===================== -if __name__ == "__main__": - # 简化命令行参数:仅保留输入视频、最大帧数 - parser = argparse.ArgumentParser(description="车道线检测(精简版)") - parser.add_argument("video_path", type=str, help="输入视频文件路径") - parser.add_argument("--max-frames", type=int, default=10, help="最大处理帧数(默认10)") - args = parser.parse_args() - - # 执行核心逻辑 - process_video(args.video_path, args.max_frames) diff --git a/requirements.txt b/requirements.txt deleted file mode 100644 index 2d3d95d455..0000000000 --- a/requirements.txt +++ /dev/null @@ -1,5 +0,0 @@ -python-markdown-math -imageio -numpy -matplotlib -tensorflow \ No newline at end of file diff --git a/yolo_det.py b/yolo_det.py new file mode 100644 index 0000000000..1d9a794176 --- /dev/null +++ b/yolo_det.py @@ -0,0 +1,34 @@ +from ultralytics import YOLO +import cv2 +import numpy as np + +class ObjectDetector: + def __init__(self, model_name='yolov8n.pt'): + self.model = YOLO(model_name) + # 目标: 2=Car, 3=Motor, 5=Bus, 7=Truck + self.target_classes = [2, 3, 5, 7] + + def detect(self, frame): + """ + 返回: (original_frame, detections_list) + """ + results = self.model(frame, stream=True, verbose=False) + detections = [] + + for result in results: + boxes = result.boxes + for box in boxes: + cls_id = int(box.cls[0]) + if cls_id in self.target_classes: + x1, y1, x2, y2 = map(int, box.xyxy[0]) + conf = float(box.conf[0]) + if conf < 0.4: continue + + detections.append({ + 'box': [x1, y1, x2, y2], + 'class': self.model.names[cls_id], + 'conf': conf, + 'width': x2 - x1, + 'center': ((x1+x2)//2, (y1+y2)//2) + }) + return frame, detections \ No newline at end of file