cmitash Goto Github PK

aigame

Implementing MCTS and MINMAX based AI for a game similar to checkers and go

amazon-sagemaker-examples

Example notebooks that show how to apply machine learning, deep learning and reinforcement learning in Amazon SageMaker

awesome-semantic-segmentation

awesome-semantic-segmentation

bin_packing_simulation

calibrateviewspcl

calibrate multiple views for merging point cloud

cmitash.github.io

cob

Convolutional Oriented Boundaries

deep_object_pose

Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)

emdobjectpose

computing earth movers distance between two point clouds

forward-backward-adaptive-astar

A-star searches in grid world

icp_calibration

perform camera calibration for kinect using ICP registration with robot base model

label6dpose

label 6d pose of objects in images by manually aligning object models to the pointcloud obtained from depth and color image

model_matching

Robust 6D Object Pose Estimation with Stochastic Congruent Sets

multi-instance-pose-estimation

nerc-poster

Poster Latex files for ICCV 3D Workshop

optical_character_recognition

performing Optical Character Recognition (OCR) with kNN-classification using different methods of thresholding (manual, otsu, li, yen, adaptive), morphological operations and feature extraction (hu moments, euler number, convex density, orientation, etc)

orkrenderer

generate synthetic image of objects from multiple views

perception

Deliberative Perception for RGB-D Object Instance Localization

physim-dataset-generator

generate physically realistic synthetic dataset of cluttered scenes using 3D CAD models to train CNN based object detectors

physim_6dpose

Matlab based toolbox for computing 6DoF pose for objects

physimglobalpose

C++ implementation for search based 6d pose estimation of objects in clutter.

pose_selection

robotlearning

object recognition and learning to grasp for the robot learning course

shelfdetection

estimate position and orientation of shelf using the shelf geometry, and RANSAC-based techniques

super4pcs

trafficsignrecognition

traffic sign recognition using CNN (VGG16) in Keras-Tensorflow

train-faster-rcnn

visualize_se3