Does LiDAR-based spatial intelligence require machine learning training data?

Not necessarily. Certain LiDAR processing architectures achieve real-time object detection, tracking, and SLAM without any machine learning component, removing the need for annotated training datasets entirely. Outsight's SHIFT platform takes this approach: its spatial intelligence pipeline processes 3D point clouds geometry-first, meaning it can move from sensor installation to actionable output without the weeks-long data-labeling phase that camera-based computer vision systems typically require. This design also means performance does not degrade when encountering object types or environments absent from a training set, which matters for operators managing dynamic, unpredictable physical spaces such as airports, train stations, or factory floors.

What is SLAM and why does it matter for LiDAR spatial intelligence?

SLAM stands for Simultaneous Localisation and Mapping. It allows a LiDAR-equipped system to build a 3D map of a new environment while simultaneously tracking where sensors and moving objects are within that map, without relying on GPS or a pre-loaded floor plan. For infrastructure deployments in enclosed spaces such as terminals or warehouses, where GPS signals are unavailable, SLAM is what allows the system to establish spatial reference and begin tracking immediately after installation. Outsight's Spatial Intelligence platform applies this capability at scale through infrastructure-mounted LiDAR, enabling real-time 3D awareness across complex sites like airports and transit stations without requiring prior mapping or external positioning systems.

Can a single LiDAR edge device handle detection, tracking, and mapping at once?

Compact edge hardware is capable of running SLAM, object detection, and tracking simultaneously on a single chip, delivering structured spatial output without requiring a separate centralised processing server. This embedded approach reduces end-to-end latency and lowers power consumption compared to architectures that stream raw point-cloud data to a remote compute cluster for processing. Outsight's SHIFT platform is built around this principle, processing 3D LiDAR data at the infrastructure edge with a sub-50ms end-to-end pipeline, so that detection, tracking, and spatial mapping are fused locally before results are passed upstream for analytics or operations.

How does LiDAR spatial intelligence apply to autonomous vehicle development?

LiDAR spatial intelligence contributes to autonomous driving by classifying whether nearby objects are static or moving, reading road surface conditions, and interpreting precautionary road signs, all in real time from a compact onboard module. These inputs are relevant to reaching SAE Level 4 and Level 5 autonomy, where the vehicle must handle all driving tasks without human intervention across defined or unrestricted environments. Outsight extends this same spatial intelligence approach beyond the vehicle itself, using infrastructure-based LiDAR to build real-time 3D awareness of how vehicles, people, and robots move through complex physical environments, a capability that complements onboard perception and is formalized in the SHIFT platform.

What sectors besides automotive does infrastructure-based spatial intelligence serve?

Infrastructure-based spatial intelligence serves a broad range of sectors beyond automotive. Airports such as Paris-Charles de Gaulle, Rome Fiumicino, and Dallas Fort Worth use it to track passenger flow, monitor assets like trolleys and escalators, and support safety compliance. Train stations, including SNCF Gares & Connexions facilities in France, apply it for crowd management and operational analytics. Industrial sites such as BMW factories deploy it for worker safety and autonomous mobile robot coordination. Smart-city programs, like the City of Bellevue's Vision Zero intersections, use it for pedestrian and vehicle flow analytics. Security-sensitive facilities, including datacenters, rely on it for perimeter and access monitoring. Outsight's SHIFT platform covers all of these verticals through its Motional Digital Twin, building a real-time, anonymous 3D replica of how people, vehicles, and robots move through a physical site.

Insights

Outsight receives Frost & Sullivan’s 2021 Global Technology Innovation Leadership Award, with a visual of connected mobility and global IoT networks overlaid on a road and ocean.

Outsight recognised by Frost & Sullivan as the Global Leader in Spatial Intelligence

Frost & Sullivan recognises Outsight with the Global Technology Innovation Leadership Award for its Spatial Intelligence software solution based on LiDAR.

LONDON, UK, (FROST), Based on its recent analysis of the global Spatial Intelligence Market, Frost & Sullivan recognises Outsight with the Global Technology Innovation Leadership Award for its Spatial Intelligence solution.

Outsight’s Augmented LiDAR Box can process LiDAR data from any supplier in real-time. It offers full situational awareness from a compact stand-alone device by embedding simultaneous localisation and mapping (SLAM), object detection, and tracking software onto a single chip.

Without requiring Machine Learning, this eliminates the need for training datasets and annotation processes, allowing the solution to deliver actionable information to the decision-making centralised computation module in real time.

Outsight’s spatial intelligence processing technology is bound to power autonomous machines of the future, machines that will enable a smarter world.” said Arjun Mehta, Senior Analyst.

Unlike conventional 3D perception LiDAR solutions that only deliver raw data, Outsight’s state-of-art edge computing module provides a plug-and-play spatial intelligence solution that empowers developers to easily build and scale their 3D-based applications.

In addition to providing spatial intelligence, Outsight’s solution consumes less power, reduces latency, and is more economical than other conventional 3D perception solutions that depend on machine learning-based centralised processing power.

It enables edge-intelligent machines for industries such as automotive, agriculture, aviation, and security and surveillance and can even potentially drive the adoption of autonomous vehicles.

By gathering intelligence from its surroundings and providing critical information for a vehicle in motion, such as whether an object is moving or static, the condition of roads, and the meaning of precautionary road signs, the Augmented LiDAR Box can expedite level 4 and level 5 autonomous vehicle adoption.

The software can also be deployed in public places such as airports and malls to obtain real-time information related to people flow, asset maintenance, security, safety, and compliance issues. Its ability to track crowded areas, trolley and escalator usage, and distance between people further underlines its value in the post-COVID-19 world. The solution has already been deployed at airports across France, including in the busy Paris-Charles de Gaulle Airport, to ensure that travellers observe social distancing.

With the proliferation of the Internet of Things (IoT) and increasing demand for smart machines and smart infrastructure, Outsight’s spatial intelligence software is poised to attract interest from automotive, robotics, and smart city players from around the world, noted Mehta.

Each year, Frost & Sullivan presents this award to the company that has demonstrated uniqueness in developing and leveraging new technologies that deliver significant customer value.

Overall, the success of its disruptive product in attracting strategic investments and helping customers power next-gen vehicles and smart cities is expected to help the company accelerate in the global market.

Frost & Sullivan Best Practices awards recognise companies in a variety of regional and global markets for demonstrating outstanding achievement and superior performance in areas such as leadership, technological innovation, customer service, and strategic product development. Industry analysts compare market participants and measure performance through in-depth interviews, analysis, and extensive secondary research to identify best practices in the industry

About Outsight

Outsight’s Physical AI continuously digitizes the movement, behavior, and interactions of people, vehicles and robots at scale, producing real-time Spatial Intelligence built on 3D LiDAR data and enriched with other available data sources.

Operators of large, complex environments, including transportation hubs such as airports and train stations, sports and entertainment venues, road infrastructure, and industrial sites, rely on this Spatial Intelligence to enhance operations, improve visitor experiences, and strengthen safety and security.

We support customers across five continents from our offices in Paris, San Francisco, Singapore and Hong Kong, driven by the belief that accelerating the global adoption of Spatial Intelligence will lead to a smarter, safer, and more sustainable world.

Let's connect

Send us a Message

Drop your email and we'll get back to you as soon as possible.

Frequently Asked Questions

What is the Frost & Sullivan Global Technology Innovation Leadership Award?
Frost & Sullivan presents this award annually to a company that has demonstrated measurable uniqueness in developing and deploying new technologies that deliver concrete customer value. Selection involves in-depth analyst interviews, primary research, and extensive secondary research benchmarking the winner against global market participants. The award recognizes performance across leadership, technological innovation, customer service, and strategic product development, not just self-reported capability. Outsight received the Global Technology Innovation Leadership Award for its Spatial Intelligence software solution built on LiDAR, a recognition grounded in Frost & Sullivan's independent analysis of the SHIFT platform and its deployments across airports, transit hubs, factories, and smart-city intersections worldwide.
Does LiDAR-based spatial intelligence require machine learning training data?
Not necessarily. Certain LiDAR processing architectures achieve real-time object detection, tracking, and SLAM without any machine learning component, removing the need for annotated training datasets entirely. Outsight's SHIFT platform takes this approach: its spatial intelligence pipeline processes 3D point clouds geometry-first, meaning it can move from sensor installation to actionable output without the weeks-long data-labeling phase that camera-based computer vision systems typically require. This design also means performance does not degrade when encountering object types or environments absent from a training set, which matters for operators managing dynamic, unpredictable physical spaces such as airports, train stations, or factory floors.
What is SLAM and why does it matter for LiDAR spatial intelligence?
SLAM stands for Simultaneous Localisation and Mapping. It allows a LiDAR-equipped system to build a 3D map of a new environment while simultaneously tracking where sensors and moving objects are within that map, without relying on GPS or a pre-loaded floor plan. For infrastructure deployments in enclosed spaces such as terminals or warehouses, where GPS signals are unavailable, SLAM is what allows the system to establish spatial reference and begin tracking immediately after installation. Outsight's Spatial Intelligence platform applies this capability at scale through infrastructure-mounted LiDAR, enabling real-time 3D awareness across complex sites like airports and transit stations without requiring prior mapping or external positioning systems.
Can a single LiDAR edge device handle detection, tracking, and mapping at once?
Compact edge hardware is capable of running SLAM, object detection, and tracking simultaneously on a single chip, delivering structured spatial output without requiring a separate centralised processing server. This embedded approach reduces end-to-end latency and lowers power consumption compared to architectures that stream raw point-cloud data to a remote compute cluster for processing. Outsight's SHIFT platform is built around this principle, processing 3D LiDAR data at the infrastructure edge with a sub-50ms end-to-end pipeline, so that detection, tracking, and spatial mapping are fused locally before results are passed upstream for analytics or operations.
How does LiDAR spatial intelligence apply to autonomous vehicle development?
LiDAR spatial intelligence contributes to autonomous driving by classifying whether nearby objects are static or moving, reading road surface conditions, and interpreting precautionary road signs, all in real time from a compact onboard module. These inputs are relevant to reaching SAE Level 4 and Level 5 autonomy, where the vehicle must handle all driving tasks without human intervention across defined or unrestricted environments. Outsight extends this same spatial intelligence approach beyond the vehicle itself, using infrastructure-based LiDAR to build real-time 3D awareness of how vehicles, people, and robots move through complex physical environments, a capability that complements onboard perception and is formalized in the SHIFT platform.
What sectors besides automotive does infrastructure-based spatial intelligence serve?
Infrastructure-based spatial intelligence serves a broad range of sectors beyond automotive. Airports such as Paris-Charles de Gaulle, Rome Fiumicino, and Dallas Fort Worth use it to track passenger flow, monitor assets like trolleys and escalators, and support safety compliance. Train stations, including SNCF Gares & Connexions facilities in France, apply it for crowd management and operational analytics. Industrial sites such as BMW factories deploy it for worker safety and autonomous mobile robot coordination. Smart-city programs, like the City of Bellevue's Vision Zero intersections, use it for pedestrian and vehicle flow analytics. Security-sensitive facilities, including datacenters, rely on it for perimeter and access monitoring. Outsight's SHIFT platform covers all of these verticals through its Motional Digital Twin, building a real-time, anonymous 3D replica of how people, vehicles, and robots move through a physical site.