Skip to content

Commit

Permalink
Added download_data.sh
Browse files Browse the repository at this point in the history
  • Loading branch information
krrish94 committed Jul 25, 2018
1 parent 1a8b8d9 commit 794f355
Show file tree
Hide file tree
Showing 4 changed files with 84 additions and 5 deletions.
2 changes: 2 additions & 0 deletions .gitignore
@@ -0,0 +1,2 @@
Data/*
*.tar.gz
13 changes: 8 additions & 5 deletions README.md
Expand Up @@ -4,7 +4,7 @@ This repository contains code and data required to reproduce the results in the

## Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking
### Sarthak Sharma<sup>\*</sup>, Junaid Ahmed Ansari<sup>\*</sup>, [J. Krishna Murthy](https://krrish94.github.io), and [K. Madhava Krishna](http://robotics.iiit.ac.in)
> <sup>\*</sup The first two authors contributed equally to the work.
> <sup>\*</sup> The first two authors contributed equally to the work.
### [Project Page](https://junaidcs032.github.io/Geometry_ObjectShape_MOT/)
> The project page has more qualitative results, and links to data.
Expand All @@ -15,7 +15,7 @@ If you find the code/data useful in your experiments, kindly consider citing
@inproceedings{BeyondPixels_ICRA2018,
title={Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking},
author={Sarthak Sharma, Junaid Ahmed Ansari, J. Krishna Murthy, K. Madhava Krishna},
booktitle = {Proceedings of the IEEE Conference on Robotics and Automation (In Press)},
booktitle = {Procedings of the IEEE International Conference on Robotics and Automation},
year={2018}
}
```
Expand All @@ -31,8 +31,11 @@ To run a demo script that shows representative results on short snippets from th
main_script_train.m
main_script_test.m
```
> IMPORTANT: You need to have the `Data` folder initialized, before you can run this demo.
> See below for details.
Before you can run this, however, make sure you download the requisite CNN appearance features and rectified images by running the following script

Before you can run this, however, make sure you download the requisite CNN appearance features and rectified images by running the following script.
```
sh download_data.sh
```
Expand All @@ -47,6 +50,6 @@ To falcilitate comparision, we have also released our results on the KITTI Track
## Misc. Remarks

We release release object detections obtained (and filtering scripts for non-maxima suppression, along with parameters used) for all train and test sequences. We report results obtained by running [RRC-Net](https://arxiv.org/abs/1704.05776) \[[code](https://github.com/xiaohaoChen/rrc_detection)\] on KITTI Tracking data. They can be accessed in the `DATA` directory.
We release release object detections obtained (and filtering scripts for non-maxima suppression, along with parameters used) for all train and test sequences. We report results obtained by running [RRC-Net](https://arxiv.org/abs/1704.05776) \[[code](https://github.com/xiaohaoChen/rrc_detection)\] on KITTI Tracking data. They can be accessed in the `Data` directory.

We also release odometry estimates obtained from ORB-SLAM. Note that, since we used monocular ORB-SLAM, odometry estimates were obtained *to-scale*. To get rid of the scale factor ambiguity, we empirically estimate a scale factor by four-fold cross-validation over the train set. Once this scale factor is estimated, we use the same factor across all train and test sequences in the results reported. These can be found in the `DATA` directory too.
We also release odometry estimates obtained from ORB-SLAM. Note that, since we used monocular ORB-SLAM, odometry estimates were obtained *to-scale*. To get rid of the scale factor ambiguity, we empirically estimate a scale factor by four-fold cross-validation over the train set. Once this scale factor is estimated, we use the same factor across all train and test sequences in the results reported. These can be found in the `Data` directory too.
4 changes: 4 additions & 0 deletions download_data.sh
@@ -0,0 +1,4 @@
#!/bin/bash

./third_party/gdown.pl https://drive.google.com/file/d/1BQrLvvCV3tomtBSdVE_orJxQOhHxcinG/
tar -zxvf gdown.tar.gz
70 changes: 70 additions & 0 deletions third_party/gdown.pl
@@ -0,0 +1,70 @@
#!/usr/bin/env perl
#
# Google Drive direct download of big files
# ./gdown.pl 'gdrive file url' ['desired file name']
#
# v1.0 by circulosmeos 04-2014.
# v1.1 by circulosmeos 01-2017.
# http://circulosmeos.wordpress.com/2014/04/12/google-drive-direct-download-of-big-files
# Distributed under GPL 3 (http://www.gnu.org/licenses/gpl-3.0.html)
#
use strict;

my $TEMP='gdown.cookie.temp';
my $COMMAND;
my $confirm;
my $check;
sub execute_command();

my $URL=shift;
die "\n./gdown.pl 'gdrive file url' [desired file name]\n\n" if $URL eq '';

my $FILENAME=shift;
$FILENAME='gdown' if $FILENAME eq '';

if ($URL=~m#^https?://drive.google.com/file/d/([^/]+)#) {
$URL="https://docs.google.com/uc?id=$1&export=download";
}

execute_command();

while (-s $FILENAME < 100000) { # only if the file isn't the download yet
open fFILENAME, '<', $FILENAME;
$check=0;
foreach (<fFILENAME>) {
if (/href="(\/uc\?export=download[^"]+)/) {
$URL='https://docs.google.com'.$1;
$URL=~s/&amp;/&/g;
$confirm='';
$check=1;
last;
}
if (/confirm=([^;&]+)/) {
$confirm=$1;
$check=1;
last;
}
if (/"downloadUrl":"([^"]+)/) {
$URL=$1;
$URL=~s/\\u003d/=/g;
$URL=~s/\\u0026/&/g;
$confirm='';
$check=1;
last;
}
}
close fFILENAME;
die "Couldn't download the file :-(\n" if ($check==0);
$URL=~s/confirm=([^;&]+)/confirm=$confirm/ if $confirm ne '';

execute_command();
}

unlink $TEMP;

sub execute_command() {
$COMMAND="wget --no-check-certificate --load-cookie $TEMP --save-cookie $TEMP \"$URL\"";
$COMMAND.=" -O \"$FILENAME\"" if $FILENAME ne '';
`$COMMAND`;
return 1;
}

0 comments on commit 794f355

Please sign in to comment.