|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/autonomous-car-deep-learning-computer-vision-for-beginners/
课程评论：没有评论
**课程名称：** 自动驾驶汽车：面向初学者的深度学习与计算机视觉 **课程概述：** 本课程将全面介绍构建定制自动驾驶汽车所需的软硬件知识。 **硬件部分：** * 树莓派（Raspberry Pi）设置与 Raspbian 系统安装 * 树莓派与笔记本电脑的 VNC 连接设置 * 树莓派 GPIO 编程基础，包括使用 Python 控制 LED 和电机 * 摄像头接口的连接与配置 **软件部分：** * 视频处理流水线设置 * 使用计算机视觉技术进行车道线检测 * 利用深度神经网络进行交通标志识别 * 使用光流法进行交通标志跟踪 * 控制模块（自动驾驶开发阶段） **项目流程：** 1. **基础搭建：** 利用提供的 3D 模型和推荐的汽车零件，快速搭建一台可在树莓派上运行的汽车。 2. **硬件接口：** 将树莓派与电机和摄像头连接，为后续编程做好准备。 3. **概念学习：** 理解自动驾驶的概念及其在交通运输和环境领域的未来发展。 4. **案例研究：** 深入分析知名自动驾驶品牌（如特斯拉）的案例。 5. **项目规划：** 确定我们想要构建的自动驾驶汽车的级别。 6. **核心开发（两大部分）：** * **检测模块：** 学习如何从环境中提取关键信息，并通过将大问题分解为小问题的方法，例如将检测任务细分为（a）分割，（b）估计，（c）清理，（d）数据提取。 * **控制模块：** 基于检测模块提供的信息执行相应动作，学习目标设定和实现，例如（a）车道保持，（b）遵守限速。 7. **整合与测试：** 将所有独立组件整合，打造“迷你特斯拉”自动驾驶汽车，并进行最终赛道测试，分析其表现和不足。 8. **未来展望：** 总结改进方向和未来版本可能的新特性。 **硬件要求：** * 树莓派 3B 或更高版本 * 阿克曼转向汽车（Ackerman Drive car） * 12V 锂聚合物电池 * 舵机（Servo Motor） **软件要求：** * Python 3.6 * OpenCV 4.2 * TensorFlow * 充满动力和学习热情的心态！ **重要提示：** * 本课程仅支持树莓派 3B 和 3B+。对于其他型号的树莓派，不提供 TensorFlow 的安装指导。 * 在购买硬件前，建议先查看课程 GitHub 仓库或联系讲师（即使不购买硬件，也可以获取代码进行学习）。
This is course is involves both the hardware and the software part for building your custom car Topics Which Will be Covered in the Course are Hardware Part:Raspberry Pi Setup with RaspbianRaspberry pi and Laptop VNC SetupHardware GPIO ProgrammingLed Controlling with Python CodeMotor Control Camera Interfacing Video FeedSoftware Part:Video Processing Pipeline setupLane Detection with Computer Vision TechniquesSign Detection using Artificial Deep Neural NetworkSign Tracking using Optical FlowControl Course Flow (Self-Driving [Development Stage])We will quickly get our car running on Raspberry Pi by utilizing 3D models ( provided in the repository) and car parts bought from links provided by instructors. After that, we will interface raspberry Pi with Motors and the camera to get started with Serious programming.Then by understanding the concept of self-drive and how it will transform our near future in the field of transportation and the environment. Then we will perform a case study of a renowned brand in self-driving (Tesla) ;).After that, we will put forward our proposal of which (autonomous driving level) self-driving vehicle do we want to build.The core development portion of the course will be divide into two parts. In each of this portion and their subsection, we will look into different approaches. program them and perform an analysis. In the case of multiple approaches for each section, we will do a comparative analysis to sort out which approach best suits our project requirements.1) Detection: responsible for extracting the most information about the environment around the SDV Here we will understand how to tackle a large problem by breaking it down into smaller more manageable problems e.g in the case of Detection. we will divide it into 4 targets a) Segmentation b) Estimation c) Cleaning d) Data extraction2) Control: actions will be performed based on the information provided by the detection module. Starting by defining the targets of this module and then implementation of these targets such as a) Lane Following b) Obeying Road Speed LimitsIn the end, we will combine all the individual components to bring our Self Driving (Mini - Tesla) to life. Then a Final Track run along with analysis will be performed to understand its achievement and shortcoming.We will conclude by describing areas of improvement and possible features in the future version of the Self-driving (Mini-Tesla)Hardware RequirementsRaspberrypi 3b or greaterAckerman Drive car12V lipo Battery Servo MotorSoftware Requirements Python 3.6Opencv 4.2TensorFlowMotivated mind for a huge programming Project- This course is only supported for Raspberry pi 3B and 3B+ , for other version of raspberry pi we do not guide how to install Tensorflow.- Before buying take a look into this course Github repository or message ( if you do not want to buy get the code at least and learn from it:) )
