自动驾驶
R2026b通过将 Deep Learning Toolbox™ 与 Automated Driving Toolbox™ 结合使用，将深度学习应用于自动驾驶应用。
App
| 真实值标注器 | (To be removed) Label ground truth data for automated driving applications |
主题
- Train a Deep Learning Vehicle Detector (Automated Driving Toolbox)
Train a vision-based vehicle detector using deep learning.
- 使用单目相机和语义分割创建占据栅格
此示例说明如何使用语义分割和深度学习来估计一辆车周围的可用空间和创建占据栅格。然后，您将使用该占据栅格创建车辆代价地图，该代价地图可用于规划路径。
- Automate Ground Truth Labeling for Semantic Segmentation (Automated Driving Toolbox)
Use a pretrained semantic segmentation algorithm to segment an image, and use this algorithm to automate ground truth labeling.
- Train Deep Learning Semantic Segmentation Network Using 3-D Simulation Data
This example shows how to use 3-D simulation data to train a semantic segmentation network and fine-tune it to real-world data using generative adversarial networks (GANs).
- Track Multiple Vehicles Using a Camera (Automated Driving Toolbox)
Detect and track multiple vehicles with a monocular camera mounted in a vehicle.
精选示例
Train Deep Learning Semantic Segmentation Network Using 3-D Simulation Data
Use 3-D simulation data to train a semantic segmentation network and fine-tune it to real-world data using generative adversarial networks (GANs).
使用单目相机和语义分割创建占据栅格
此示例说明如何使用语义分割和深度学习来估计一辆车周围的可用空间和创建占据栅格。然后，您将使用该占据栅格创建车辆代价地图，该代价地图可用于规划路径。
Perception Based Live Parking Spot Detection Using Unreal Engine Simulation
Develop a live parking spot detection system using deep learning and SLAM.
