fangchaohu1211 Goto Github PK

kitti_native_evaluation

Evaluation of 3D object detection performance on the KITTI dataset.

limo

Lidar-Monocular Visual Odometry

midas-journal-720

Graph Cuts Based Super Pixel Segmentation for VTK

mobilenetv2-ssdlite

Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.

mono-vo

An OpenCV based implementation of Monocular Visual Odometry

mv-lm-icp

Multiview Levenberg-Marquardt ICP

mx-maskrcnn

An MXNet implementation of Mask R-CNN

object-detection-and-tracking

YOLO & RCNN Object Detection and Tracking

optical-flow-filter

A real time optical flow algorithm implemented on GPU

planarreconstruction

[CVPR'19] Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding

pyfeaturetrack

Feature point tracking in Python 2 or 3, using the KLT method.

pytorch-yolov4

PyTorch ,ONNX and TensorRT implementation of YOLOv4

realtime-neural-3d-pose-estimation

Neural 3D Pose Estimation and Object Detection

rodrigob-doppia

simtrack

Exploring Simple 3D Multi-Object Tracking for Autonomous Driving (ICCV 2021)

sparse-scene-flow

This repo contains C++ code for sparse scene flow method.

stereo-visual-odometry-plotting-an-objects-trajectory-using-a-sequence-of-images

Computer Vision Final Project - Plotting the trajectory of a vehicle using a sequence of images captured by a camera on top of the vehicle.

stereovision

separate road using v-disparity. test occupancy grid, stixels

stereovisionforadas

Stereo vision based object detection for ADAS, autonomous vehicle

structured-edge-detection

superpoint_graph

Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

tf-faster-rcnn

Tensorflow Faster RCNN for Object Detection

trackr-cnn

TrackR-CNN baseline method for Multi-Object Tracking and Segmentation (MOTS)

vdo_slam

VDO-SLAM: A Visual Dynamic Object-aware SLAM System

visual-odometry

Visual Odometry is a crucial concept in Robotics Perception for estimating the trajectory of the Robot (camera to be precise). The concepts involved in Visual Odometry are quite the same for SLAM which needless to say is an integral part of Perception.

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

voxelnet-tensorflow

A 3D object detection system for autonomous driving.

yolof

zed-tensorflow

3D Object detection using the ZED and Tensorflow