Geo-trax is a comprehensive pipeline for extracting and analyzing high-accuracy georeferenced vehicle trajectories from quasi-stationary, bird’s-eye view drone footage. Using advanced computer vision and deep learning, it enables detailed urban traffic analysis and supports scalable, precise studies of vehicle dynamics.

🗺️ Create landscape design images in bird's eye view using DALL-E 3.

Spiideo SoccerNet SynLoc - Single Frame World Coordinate Athlete Detection and Localization with Synthetic Data

Talk2BEV: Language-Enhanced Bird's Eye View Maps (ICRA'24)

[ECCV 2024] Official Implementation of "TrajPrompt: Aligning Color Trajectory with Vision-Language Representations"

The code used by the team of the Hanze UAS during the Self Driving Challenge 2024

[IEEE T-PAMI] Awesome BEV perception research and cookbook for all level audience in autonomous diriving

TensorFlow Implementation for Computing a Semantically Segmented Bird's Eye View (BEV) Image Given the Images of Multiple Vehicle-Mounted Cameras.

Transforming multiple vehicle-mounted camera images into a bird’s-eye view (BEV), this project employs deep learning, including a U-Net backbone for semantic segmentation and a spatial transformer module.

[ITSC 23] Official codebase for the paper 'Radar Enlighten the Dark: Enhancing Low-Visibility Perception for Automated Vehicles with Camera-Radar Fusion

Birds-Eye view of a car and its surroundings for park assist.

Top view (bird's eye) 2D video game with WASD and mouse-aim controls where you can enter different rooms, gamble enemy-killing bounty money for ammo and lives, sprint, etc.

PyTorch implementation of ComplexYOLO. This Repository is meant for students to learn object detection and working with LiDAR/RADAR datasets.

This repository is dedicated for 3D detection , sensor fusion and tracking using camera and LIDAR data

[ICCV'21] NEAT: Neural Attention Fields for End-to-End Autonomous Driving

In this project, the aim is denoting danger zones for suspended loads and creating warnings for workers inside these danger zones. Overall pipeline consists of object detection, object tracking and distance estimation by using bird’s eye view transformation.

A ROS package for LiDAR's Bird's Eye View projection.

Perspective transformation (birds eye) tool, for easy experimenting and finding the right transformation values.