百度迁徙爬虫

ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

Zotero extension to retrieve and validate DOIs and shortDOIs

MTCNN face detection implementation for TensorFlow, as a PIP package.

Accurate routing for OpenStreetMap/OSMnx

SSD-based head detector for Keras

A Labelme to Data Augmentation to Mask R-CNN or YOLO v3 pipeline for small dataset.

Random walk to calculate the tortuosity tensor of images

Comparing Different Clustering Methods and Similarity Metrics on Trajectory Datasets

[ICCV'21] Learning Spatio-Temporal Transformer for Visual Tracking

地理坐标系转换工具

CityWander，城市漫游街景项目

Mask RCNN implementation on a custom dataset! All incorporated in a single python notebook!

京东抢购助手：包含登录，查询商品库存/价格，添加/清空购物车，抢购商品(下单)，查询订单等功能

Mask R-CNN modified to run on TensorFlow 2

提供百度坐标系(bd-09)、火星坐标系(国测局坐标系、gcj02)、WGS84坐标系直接的坐标互转，也提供了解析高德地址的方法的python版本

Explore how well deep neural networks perform at predicting vehicle speed given just visual data (dashcam video) containing highway and suburban driving.

Inferring transportation modes from GPS trajectories using a Convolutional Neural Network

Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.

Monocular odometry using OpenCV

pySLAM is a visual SLAM pipeline in Python for monocular, stereo and RGBD cameras. It supports many modern local and global features, different loop-closing methods, a volumetric reconstruction pip…

Compute Natural Breaks in Python (Fisher-Jenks algorithm)

Structure from motion (SFM) pipeline for highway driving scenes, based on OpenSFM

Open source Structure-from-Motion pipeline

Automatic License Plate Recognition (ALPR) or Automatic Number Plate Recognition (ANPR) software that works with any camera.

**ARCHIVED** An anonymizer to obfuscate faces and license plates.

The course notes for Stanford's CS231A course on computer vision