xwspace

Car_Opencv

Final project with multiple modules

cv-notebooks

📚 Some notebooks implementing compute vision algorithms

darknet

Windows and Linux version of Darknet Yolo v3 & v2 Neural Networks for object detection (Tensor Cores are used)

deep_learning_object_detection

A paper list of object detection using deep learning.

detectron2

Detectron2 is FAIR's next-generation research platform for object detection and segmentation.

dm-vio

Source code for the paper DM-VIO: Delayed Marginalization Visual-Inertial Odometry

facenet

Face recognition using Tensorflow

FairMOT

A simple baseline for one-shot multi-object tracking

fast-style-transfer

TensorFlow CNN for fast style transfer ⚡🖥🎨🖼

hfnet_ros

A cpp or ROS Warpper of HF-NET inference part (https://github.com/ethz-asl/hfnet)

kuafu

This is a tool library that includes log, fsm, state machine...

libfacedetection

An open source library for face detection in images. The face detection speed can reach 1500FPS.

mmdetection

OpenMMLab Detection Toolbox and Benchmark

OpenCat

A programmable and highly maneuverable robotic cat for STEM education and AI-enhanced services.

openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

openvslam-comments

openvslam的注释版代码

orbslam-map-saving-extension

pl-slam

This code contains an algorithm to compute stereo visual SLAM by using both point and line segment features.

PL-VIO

monocular visual inertial system with point and line features

SexyYolo

An implementation of Yolov3 with Tensorflow1.x, which could detect COCO and sexy or porn person simultaneously.

Shading-removal-of-images

SIFTGPUBF

适配目前最新CUDA环境的SIFTGPU代码

slambook

SLATracker

Spatial-Attention Location-Aware Multi-Object Tracking

stargan

StarGAN - Official PyTorch Implementation

TensorFlow-Examples

TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)

tensorflow-serving-yolov3

主要对原tensorflow版本算法进行了网络修改，显示调整，数据处理等细节优化，详细说明了 从本地训练到serving端部署yolov3的整个流程,训练了Visdrone2019无人机数据集, 准确率 较高, 训练工业检测数据集（非80类中的一类），mAP为97.51，FPS在1080上测试15-20帧！

tensorflow-yolov3

🔥 pure tensorflow Implement of YOLOv3 with support to train your own dataset

tesseract

Tesseract Open Source OCR Engine (main repository)

VO-SLAM-Review

SLAM is mainly divided into two parts: the front end and the back end. The front end is the visual odometer (VO), which roughly estimates the motion of the camera based on the information of adjacent images and provides a good initial value for the back end.The implementation methods of VO can be divided into two categories according to whether features are extracted or not: feature point-based methods, and direct methods without feature points. VO based on feature points is stable and insensitive to illumination and dynamic objects