Skip to content

Instantly share code, notes, and snippets.


Tejus Gupta tejus-gupta

View GitHub Profile
View figure.tex
tejus-gupta /
Last active Oct 10, 2018
Download dataset and training code for tensorpad
mkdir train_set
cd train_set
unzip -qq
unzip -qq
cd ..
git clone
cd Segmentation
git checkout modelD
tejus-gupta / median_filter_multilevel.jl
Created Oct 9, 2018
Code for median filter based on 'A coarse-to-fine algorithm for fast median filtering of image data with a huge number of levels' by Alparone et al.
View median_filter_multilevel.jl
using Images, TestImages, Statistics, BenchmarkTools, Test
img = testimage("lena_gray")
function median_filter_multilevel(img::Array{Gray{Normed{T,f}}, 2}, window_size::Tuple{Int64,Int64}) where {T,f}
nlevels = 2^f
course_nlevels = 2^(f>>1)
bin_bits = f>>1
import requests
def download_file_from_google_drive(id, destination):
def get_confirm_token(response):
for key, value in response.cookies.items():
if key.startswith('download_warning'):
return value
return None
tejus-gupta / median_filter.jl
Last active Oct 4, 2018
Code for median filter based on 'A Fast Two-Dimensional Median Filtering Algorithm' by Huang, Yang and Tang.
View median_filter.jl
using Images, TestImages, Statistics, BenchmarkTools, Test
img = testimage("lena_gray")
high_resolution_img = convert(Array{Gray{Normed{UInt16,16}}, 2}, img)
function median_filter(img::Array{Gray{Normed{T,f}}, 2}, window_size::Tuple{Int64,Int64}) where {T,f}
function update_median(median_val, n_pixels_below_median, hist, half_pixels)
if n_pixels_below_median <= half_pixels
for val in median_val:2^f

📋 Project overview: Parallelizing Apollo

Status Just starting 🌱 / In progress 🔨 / Ready to go 🚀
Team Start with you and add others with @mentions
Description What do you have in mind?
Deadline When do you want to finish?


  • What are the key dates?
View vis_example.cpp
#include <pcl/visualization/cloud_viewer.h>
boost::shared_ptr<pcl::visualization::PCLVisualizer> cloudVis (pcl::PointCloud<pcl::PointXYZ>::ConstPtr cloud)
boost::shared_ptr<pcl::visualization::PCLVisualizer> viewer (new pcl::visualization::PCLVisualizer ("3D Viewer"));
viewer->setBackgroundColor (0, 0, 0);
viewer->addPointCloud<pcl::PointXYZ> (cloud, "sample cloud");
viewer->setPointCloudRenderingProperties (pcl::visualization::PCL_VISUALIZER_POINT_SIZE, 1, "sample cloud");
viewer->addCoordinateSystem (1.0);
viewer->initCameraParameters ();
tejus-gupta /
Last active Sep 21, 2017
ImageSegmentation Blog


Over the last three months, we've been working on ImageSegmentation.jl - a collection of image segmentation algorithms written in Julia. Under the mentorship of Tim Holy, we have implemented several popular image segmentation algorithms and designed a consistent interface for using these algorithms. This blog post describes image segmentation, why it's useful and how to use the tools in this package.

Image Segmentation is the process of partitioning the image into regions that have similar attributes. Image segmentation has various applications e.g, medical image segmentation, image compression and is used as a preprocessing step in higher level vision tasks like object detection and optical flow.

Image segmentation is not a mathematically well-defined problem: for example, the only lossless representation of the input image would be to say that each pixel is its own segment. Yet this does not correspond to our own intuitive notion that