←

Self-driving cars perception notes

Contents

1. 3D Object Detection
   1. Evaluation metrics
   2. Datasets
   3. Approaches
2. Depth Estimation
   1. Evaluation metrics
   2. Datasets
   3. Approaches
3. Segmentation
   1. Evaluation metrics
   2. Datasets
   3. Approaches
4. 2D Object Detection
   1. Evaluation metrics
   2. Datasets
   3. Approaches
5. All about self-driving car
6. Other sources

See this repo from my site: https://maiminh1996.github.io/biblio-self-driving-cars/

Click on which represents the "Reading & Writting" process of each paper to see more details
Synthetic: Loss function, Network problem, Depth limit, Geometry

Data preprocessing

Update: in the process of adding all the articles i've read before 2021 _
Here is time-list paper

Other sources

LiDAR: awesome-LiDAR, awesome-point-cloud-analysis, awesome-point-cloud-deep-learning

Others: Learning-Deep-Learning, Making a Pseudo LiDAR With Cameras and Deep Learning

Andrej Karpathy'talk - AI for Full-Self Driving at Tesla

Andrej Karpathy - AI for Full-Self Driving at Tesla, Tesla autopilotAI

Takeaways's Lei Xin!

1. What is Tesla Autopilot 1:20
2. Tesla's methods are heavily based on computer vision rather than lidar 5:25
3. Neural networks in production 6:55
4. Receive training images for tricky cases from the fleet 8:35 5. For testing, it is not enough to just rely on loss function and mean accuracy of test set 13:00
6. HydraNet contains 48 networks with shared backbone, 1,000 distinct predictions (Number of output tensors) and it takes 70,000 GPU hours to train 14:12
7. Neural networks for full self-driving 16:54
8. Get depth estimation from images directly by using self-supervised techniques 22:54, predict the depth, drive to it and measure the real distance
9. other uses of self-supervised learning 25:24
10. Q&A 26:50

Tutorial

• CVPR 2019 Tutorial, workshops
• CVPR 2020 Tutorial
  • All You Need to Know About Self-Driving
• NeurIPS 2020 Tutorial