TrackEgo-Resources
This repository contains resources for the TrackEgo project. This includes the learning resources for computer vision, machine learning, and deep learning. It also contains our literature review for vehicles tracking and motion prediction.
Learning Resources
Deep Learning
- PyTorch Tutorials by Aladdin Persson
Computer Vision
- Convolutional Neural Networks for Visual Recognition (Spring 2017) by Stanford University
- Deep Learning for Computer Vision by Michigan State University
- CV3DST - computer Vision 3: Detection, Segmentation, and Tracking by Technical University of Munich
Perception for Autonomous Driving
- Self-Driving Cars — Andreas Geiger by Tubingen University
Vehicle Tracking
- Object Tracking: Introduction
- Object Tracking: Filtering
- Object Tracking: Association
- CV3DST - Object tracking
- CV3DST - Multi-object tracking
Literature Review
Vehicle Tracking
- EagerMOT: 3D Multi-Object Tracking via Sensor Fusion
- 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
- SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking
- Center-based 3D Object Detection and Tracking
- How To Train Your Deep Multi-Object Tracker
- TrackFormer: Multi-Object Tracking with Transformers
- TransTrack: Multiple Object Tracking with Transformer
- Strong-TransCenter: Improved Multi-Object Tracking based on Transformers with Dense Representations
- GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning
- BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
Motion Prediction
- Deep Learning-based Vehicle Behaviour Prediction for Autonomous Driving Applications: a Review
- Multimodal Motion Prediction with Stacked Transformers
- Wayformer: Motion Forecasting via Simple & Efficient Attention Networks
- TNT: Target-driveN Trajectory Prediction
- TPNet: Trajectory Proposal Network for Motion Prediction
- HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction
- MULTIPATH++: EFFICIENT INFORMATION FUSION AND TRAJECTORY AGGREGATION FOR BEHAVIOR PREDICTION
- GRIP: Graph-based Interaction-aware Trajectory Prediction
- GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving