What Is Lidar?

3 things you need to know

Lidar sensors (acronym for “light detection and ranging”) are range-measuring sensors like radar and sonar. The sensors emit laser pulses that reflect off objects, allowing them to perceive the structure of their surroundings. The sensors record the reflected light energy to determine the distances to objects to create a 2D or 3D representation of the surroundings. Lidars are becoming one of the primary sensors for developing perception systems across multiple industries. They enable 3D perception workflows such as object detection, semantic segmentation, and navigation workflows such as mapping, simultaneous localization and mapping (SLAM), and path planning.

Why Lidar Matters

Autonomous systems use multiple sensors such as camera, IMU, and radar in their sensor suite for environmental perception. Lidars can overcome some of the drawbacks of other sensors by providing highly accurate, structural, and 3D information of the surroundings. This advantage contributed to the introduction of lidar sensors into the mainstream perception market.

Point cloud data of a driving scenario with a few cars. — Lidar point cloud of a road scene.

This market adoption of lidars is driven by three key reasons:

Low-cost lidars. The introduction of low-cost lidars, with enhancement in characteristics such as range, size, and robustness, have increased the availability of the technology for comparatively low-revenue industrial applications.
Accurate 3D data. Lidars gather high-density 3D information of the surroundings as point clouds with a higher accuracy than other range sensors such as radars and sonars. This, in turn, improves the accuracy of the 3D reconstruction.
Lidar processing algorithms. The recent developments in lidar processing workflows such as semantic segmentation, object detection and tracking, lidar camera data fusion, and lidar SLAM has enabled the industry to add lidars into their development workflows. You can use tools such as MATLAB to develop and apply lidar processing algorithms.

Lidar Applications

Lidars are used across a wide range of industries from automated driving to geoscience. We can broadly classify these applications into three groups based on the platform they are mounted on:

Aerial lidars
Ground lidars
Indoor lidars

Aerial Lidars

Aerial lidars are lidar sensors mounted on unmanned aerial vehicles (UAV) or aircrafts. Aerial lidars capture 3D point cloud data of a large terrain that can be used for lidar mapping, feature extraction, terrain classification, and other use cases.

Image of a drone flying with a Lidar mounted on top of it. — Aerial lidar sensor.

Aerial point cloud data with buildings and trees. — Aerial lidar data.

Examples of aerial lidar applications include:

Agriculture: Lidar technology is extensively used in agriculture for mapping vegetation area and identifying the exact terrain of the farm and the water catchment area.
Urban planning: Lidars are used in creating digital surface models (DSMs) or even digital city models (DCMs) of an area, which can help design a city or build new infrastructures in an existing city.
Geological mapping: Lidars can be used to create 3D maps of the Earth’s surface, which can be further used in applications such as mining, precision forestry, and oil and gas exploration.
Aerial navigation and path planning: Lidars are now being used in UAVs to gather live 3D data to navigate autonomously through the surroundings.

See examples of using MATLAB^® for aerial lidar processing:

Ground Lidars

There are two types of ground lidars: stationary terrestrial lidars and mobile lidars:

Stationary terrestrial lidars are lidars mounted on a stationary platform. They are commonly used for land surveys, road surveys, topological mapping, creating digital elevation maps (DEMs), agriculture, and other applications. These are more suited for applications where detailed and closer data capturing is needed.
Mobile lidars are ground lidars attached on a mobile platform such as a car or a truck. The most important mobile lidar application is autonomous driving. Lidars mounted on the vehicles capture 3D point cloud data of the surroundings and they are further used in perception and navigation workflows. These workflows will be described in detail in the next section.

Multiple lidars mounted on top of a car. — Mobile lidar sensor.

Point cloud data of a road scenario with car and tree. — Mobile lidar data.

See examples of using MATLAB for ground lidar processing:

Indoor Lidars

Lidars are widely used in indoor robotics applications by mounting them on mobile robots. Apart from 3D lidars, 2D lidars or laser scanners are also used in indoor robotics applications like lidar scanning and mapping. They collect depth information of the surroundings and the depth information is further processed based on the use cases.

A screenshot of indoor lidar data. — Indoor lidar data.

Common uses of indoor lidars include:

Lidar mapping and SLAM: You can use 2D or 3D lidars to create 2D or 3D SLAM and mapping, respectively.
Obstacle detection, collision warning, and avoidance: 2D lidars are widely used to detect obstacles. This data can be further used to create collision warnings or to avoid obstacles.

See examples of using MATLAB for ground lidar processing:

Lidar Processing in MATLAB

MATLAB and Lidar Toolbox™ simplify lidar processing tasks. With dedicated tools and functions, MATLAB helps you overcome common challenges in processing lidar data like 3D data types, sparsity of data, invalid points in the data, and high noises.

You can import live and recorded lidar data into MATLAB, implement lidar processing workflows, and create C/C++ and CUDA^® code to deploy into production.

Some of the important capabilities MATLAB provides in processing lidar point clouds are described in the following sections.

Streaming, Reading, and Writing Lidar Data

The first step in processing any sensor data in MATLAB is to get the data into the MATLAB workspace. You can:

Stream live data from Velodyne sensors using the Velodyne Lidar Hardware Support Package and from Ouster sensors using the Ouster Lidar Hardware Support Package.
Read stored point clouds in different file formats such as PCD, PLY, PCAP (Velodyne, Ouster, and Hesai Pandar), Ibeo data container, LAS, and LAZ.
Write point clouds in different file formats such as PCD, PLY, LAS, and LAZ.
Simulate lidar data, allowing you to test your algorithms and workflows before deploying to a real-world system. In MATLAB, you can synthesize 3D or 2D lidar data in simulation environments by defining sensor parameters for testing your processing algorithms. Lidar Toolbox, UAV Toolbox, and Automated Driving Toolbox provide lidar sensor models to simulate lidar point clouds.

Lidar sensor model. — Stream live lidar data from Velodyne^® Lidar sensors.

Simulation of 3D lidar data.

Lidar Data Processing

You can preprocess lidar data to improve the quality of data and extract basic information from it. Lidar Toolbox™ provides functionality for downsampling, median filtering, aligning, transforming, and extracting features from point clouds.

Lidar Camera Calibration

MATLAB enables lidar camera calibration to estimate lidar-camera transforms for fusing camera and lidar data. You can further fuse color information in lidar point clouds and estimate 3D bounding boxes in lidar using 2D bounding boxes from a co-located camera.

Screenshot of the Lidar Camera Calibrator app. — Lidar Camera Calibrator app.

Deep Learning for Lidar

With MATLAB, you can apply deep learning algorithms for object detection and semantic segmentation on lidar data.

With just a few lines of code in MATLAB, you can import pretrained semantic segmentation models, including PointSeg and SqueezeSegV2 on lidar data. You can also train, evaluate, and deploy your own deep learning models.
MATLAB enables designing, training, and evaluating robust detectors such as PointPillars and ComplexYolo-V4 networks. You can detect and fit oriented bounding boxes around objects in lidar point clouds.
The Lidar Labeler app in Lidar Toolbox simplifies point cloud labeling tasks. You can manually label point clouds for object detection and semantic segmentation, apply built-in or custom algorithms to automate lidar point cloud labeling, and evaluate automation algorithm performance.

Ego view of a point cloud with a truck and car labeled. — Semantic segmentation of point clouds.

Object Tracking on Point Clouds

MATLAB can unify multiple domains that feed into an end-to-end object tracking workflow. This enables you to read lidar data, preprocess it, apply deep learning to detect objects, track these objects using a predefined tracker, and deploy this on target hardware.

Screenshot of vehicles being tracked from sequential point cloud data. — Object detection and tracking.

Point Cloud Registration and SLAM

MATLAB provides functions to register lidar point clouds and build 3D maps from ground and aerial lidar data using SLAM algorithms. This includes:

Simulation of 3D lidar data.

For more information about lidar processing, see Lidar Toolbox and Computer Vision Toolbox™.

Lidar FAQs

Lidar (light detection and ranging) is a range-measuring sensor that emits laser pulses that reflect off objects, allowing it to perceive the structure of its surroundings and create 2D or 3D representations by recording the reflected light energy.

While radar and sonar are also range-measuring sensors, lidar uses laser pulses and reflected light energy to determine distances, providing highly accurate, structural, and 3D information with higher accuracy than other range sensors.

A point cloud is a collection of data points captured by lidar sensors that represents the 3D structure of the surroundings, which can be processed for applications like object detection, semantic segmentation, and mapping.

Lidar systems are classified into three groups based on their platform: aerial lidars (mounted on UAVs or aircraft), ground lidars (stationary terrestrial or mobile), and indoor lidars (used in robotics applications).

Lidar is used in automated driving, agriculture mapping, urban planning, geological mapping, UAV navigation, land surveys, topological mapping, and indoor robotics for SLAM, obstacle detection, and collision avoidance.

The market adoption is driven by the introduction of low-cost lidars with enhanced characteristics and their ability to gather accurate high-density 3D data as point clouds enables application of complex algorithms like semantic segmentation and SLAM.

Lidar camera calibration is the process of finding the transformation between images captured from camera and point cloud captured from lidars. This allows you to fuse color information into lidar point clouds and estimate 3D bounding boxes using 2D bounding boxes from co-located cameras.

MATLAB enables streaming and reading lidar data, preprocessing and filtering, lidar camera calibration, deep learning for object detection and semantic segmentation, object tracking, and point cloud registration and SLAM.

Resources

Expand your knowledge through documentation, examples, videos, and more.

Lidar