Vision-Centric BEV Perception: A Survey

Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline

A basic implementation(not official code) of AVP-SLAM(IROS 2020) in simulation. https://arxiv.org/abs/2007.01813

[T-PAMI] Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving

[CVPRW'24] SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap (CVPR24 - CVSports workshop)

Official version of 'Weakly Supervised 3D object detection from Lidar Point Cloud'(ECCV2020)

Python scripts for performing road segemtnation and car detection using the HybridNets multitask model in ONNX.

[TMLR'24] On the Adversarial Robustness of Camera-based 3D Object Detection

Stitching and fusion of 4 pairs of on-board surround view fisheye image sequences, odometer estimation and output of large pixel maps.

Several tools for visualizing 3D perception result

Bird-eye view map construction for a mobile robot based on RGB and point cloud input

Software pipeline to identify lane boundaries from a video streaming from a front-facing camera on a car using color transform and gradient

Distortion correction of single image without checkerboard calibration.

This ML project helps ensures 6 feet distance between pedestrians.

Notes and key takeaways of the Self-Driving Cars Perception applied Deep Learning Free Course from freeCodeCamp.org

Get undistorted bird eye view images in real time

A classicial computer vision based approach to transform images from multi-camera sensors to a single Bird's Eye View image.

AI Tool for Social Distancing - Master's University Project

Projection of 3D Camera Points onto the 2D images of each camera and finally create a Bird's Eye View (BEV) representation by combining the projected points from all cameras onto a single 2D grid. The BEV provides a top-down view of the scene, which is crucial for tasks like object detection, tracking, and path planning in autonomous driving.

During the COVID-19 pandemic it is necessary, to prevent contagion, to keep a safe distance from other individuals, in particular in public places. This project was created to provide a tool that, through Neural Networks and Artificial Vision, exploits images collected by surveillance video systems, producing useful information for respecting in…