Lidar-Obstacle-Detection

Lidar obstacle detection using PCL and C++

Approach

This project is aimed to show basic scenarios for processing point clouds to detect the obstacles, and use it to detect cars and trucks on a narrow street using Lidar data.

The detection pipeline includes the following steps:

Step 1: Load PCD data from file

Step 2: Apply voxel grid filtering

Step 3: Segment the filtered cloud into two parts, road and obstacles

Step 4: Cluster the obstacle cloud

Step 5: Render bounding boxes around the clusters

The segmentation, and clustering methods were created from scratch.

The final result looks like the animation below:

Installation

Ubuntu

$> sudo apt install libpcl-dev
$> cd ~
$> git clone https://github.com/olpotkin/Lidar-Obstacle-Detection.git
$> cd Lidar-Obstacle-Detection
$> mkdir build && cd build
$> cmake ..
$> make
$> ./environment

Windows

http://www.pointclouds.org/downloads/windows.html

MAC

Install via Homebrew

install homebrew
update homebrew
```
$> brew update
```
add homebrew science tap
```
$> brew tap brewsci/science
```
view pcl install options
```
$> brew options pcl
```
install PCL
```
$> brew install pcl
```

Possible issue: 'simulation is required but glew was not found':

check details here

Prebuilt Binaries via Universal Installer

http://www.pointclouds.org/downloads/macosx.html
NOTE: very old version

Build from Source

PCL Source Github

PCL Mac Compilation Docs