Lidar sensor and data processing: free, 49 minutes
One recorded workshop of about 49 minutes, presented over slides in August 2021, followed by a short live demo. It goes from what a lidar is and how it compares with other sensors to lidar types, the automotive market, autonomous driving levels and processing methods, and ends with a ROS demo on the KITTI dataset.
24 chapters · published 16 Aug 2021 · 1,817 views as of 21 Nov 2026 · by Skill-Lync
Free. We ask for your name and phone once before it plays here · or watch on YouTube ↗
Who is this course for?
Engineering students and early-career engineers interested in perception, sensor fusion or autonomous vehicles who want a first overview of lidar and how its data is processed.
What will you learn?
- Explain what lidar stands for and why it is called an active, time-of-flight sensor
- Compare camera, radar, ultrasonic and lidar on dimensions, weather, resolution, range and frequency, as the speaker presents them
- Tell airborne, static terrestrial and mobile terrestrial lidar apart, and mechanical from solid-state
- Describe how lidar and camera or radar data complement each other in sensor fusion
- Name the main lidar processing tasks: 3D object detection, semantic segmentation, SLAM, calibration and motion compensation
- Recognise what a lidar point cloud, a SLAM map and a downsampled cloud look like in a ROS demo
What does each part of the course cover?
8 sections, in watching order. Click a timestamp to jump the player there. The video description has no chapter list, so these chapters and timestamps were written from the video itself.
- 0:003 min · 2 chapters
What a lidar is and what the session covers
The agenda runs from lidar basics and types to the automotive market, autonomous vehicles, processing methods, jobs and a demo. The speaker then defines lidar as light detection and ranging, an active time-of-flight sensor that emits its own waves and reads the reflections in the near infrared.
- 3:077 min · 4 chapters
Lidar compared with camera, radar and ultrasonic
A table-style comparison of the four sensors: dimensionality, active or passive, lateral and longitudinal strength, cost, weather, precision, resolution, range and frequency. In this 2021 talk the speaker puts lidar between camera and radar on range, at around 100 to 150 m, and says mechanical lidars typically run at 10 Hz.
- 10:258 min · 4 chapters
Lidar basics and the main types
Covers the laser and detector, multiple returns and intensity, which hints at the surface type. Then airborne lidar (terrain, clouds, forests, ocean-floor bathymetry), static terrestrial lidar (construction, city maps for games, mining) and mobile terrestrial lidar, which is rugged, compact and works in real time.
- 18:125 min · 3 chapters
Industry growth, solid-state lidar and competitors
The speaker describes lidar moving into vehicles and robots, solid-state lidar with no moving parts, and faster computers that can process around 100,000 points. A 2019 to 2025 market chart is shown, followed by lidar makers such as Velodyne, Ouster and Robosense, named as the speaker sees the 2021 market.
- 23:389 min · 3 chapters
Lidar in autonomous vehicles and the driving levels
Gives reasons lidar suits autonomous driving: resolution, easy low-level fusion, reuse of 3D camera networks and complementary use with camera and radar. It then walks through driving levels 0 to 5 and why, in the speaker's view, carmakers stay at level 2 or 2 plus.
- 32:135 min · 2 chapters
State of the art: detection, SLAM, segmentation, calibration
Lists object detection, SLAM, segmentation, low-level fusion, online calibration and motion compensation for a lidar rotating at 10 Hz on a moving car. The speaker pairs lidar with an IMU for localization and notes that bumpy roads break a flat-ground assumption.
- 36:524 min · 2 chapters
Voxel networks, semantic segmentation and LOAM
Introduces voxels as volumetric pixels that make 3D point clouds easier to process in real time, uses lidar intensity for semantic segmentation, and names the KITTI benchmark. LOAM, laser odometry and mapping, finds edges and corners in point clouds across frames to estimate a trajectory; M-LOAM extends it to several lidars.
- 40:508 min · 4 chapters
Jobs, then a ROS demo on the KITTI dataset
A short note on sensor fusion and perception roles, then a demo on the KITTI dataset in ROS. It shows the 360 degree lidar view, camera, IMU and GPS data, a SLAM map against odometry-only drift, and filtering a dense point cloud by quantising it and raising the leaf size.
Is the Lidar Sensor and Data Processing Workshop course really free?
Yes. All 49 min of it is free on Skill-Lync's YouTube channel, with no payment. To watch it on this page with the chapter guide, leave your name and phone number once; you can also watch it directly on YouTube. It was published on 16 Aug 2021 and had 1,817 views as of 21 Nov 2026. This page adds the chapter guide, a study plan and what to learn next.
How long does the Lidar Sensor and Data Processing Workshop course take to finish?
The video runs 49 min across 24 chapters. That fits in one sitting of under an hour; plan roughly twice that if you practise each exercise as you go. The longest section is "Lidar in autonomous vehicles and the driving levels" (9 min), so give it your full attention.
Does the free lidar course come with a certificate?
The video description has a "claim your certificate" link, which now opens this page. To ask about a certificate for this course, leave your name and phone number in the form below and a Skill-Lync counsellor will call you back. The paid Skill-Lync courses linked here include a certificate along with mentor-reviewed projects.
What should I learn after this course?
The next step is Localization, Mapping, and SLAM using Python (₹40,000), then Introduction to the Future of Vehicle Validation-ADAS (₹40,000). The free course teaches the concepts; the paid Skill-Lync courses add graded projects, mentor feedback and, in the PG programs, placement support.
How does lidar compare with radar and cameras?
The speaker compares them in a table. Lidar is a 3D active sensor with clean, high-resolution data and is good both laterally and longitudinally, but it costs more and struggles in heavy fog. Radar has the longest range and works in all weather. Cameras are cheap and precise laterally but give weak depth. These are the speaker's 2021 views.
What does the lidar demo in this workshop show?
The last ten minutes or so use the KITTI dataset in ROS. The speaker shows the 360 degree lidar view with a car, camera, IMU and GPS data, then a SLAM map built from a start point against odometry alone, which visibly drifts. The final part filters a dense point cloud by quantising it with a larger leaf size.
Do I need any software or background to follow it?
No software is needed to watch. The talk is slide-based and explains terms as it goes. The demo uses ROS and the public KITTI dataset, and the speaker shows it but does not give set-up steps, so installing ROS is not covered. Basic awareness of sensors and autonomous driving helps.
Last updated 21 Nov 2026 · Course length, chapters, views and dates from the YouTube video on 21 Nov 2026 · Grow by Skill-Lync: free lessons from every course