Innoviz’s advanced perception software, a tool for extracting additional data from the point cloud, is designed to be the perfect complement to the company’s hardware offerings and provides vehicles with a deep understanding of any 3D driving scene. Innoviz was one of the first LiDAR companies to develop perception software to accompany its LiDAR products.
The perception software leverages the rich data derived from Innoviz’s LiDAR sensors, coupled with proprietary state-of-the-art AI algorithms, to provide leading objection detection, classification and tracking features, as well as collision classification, localization and calibration capabilities.
When deployed alongside and in combination with other sensors’ perception algorithms, Innoviz’s software complements them to enhance performance and safety. The perception software is very resource-efficient and requires low compute power, making it compatible with various automotive-grade compute platforms. This achievement is a key differentiator against hardware-only LiDAR providers.
Detection, Classification and Tracking
Detects objects with high precision. Boasts two independent detectors for identifying objects (i.e. cars, trucks, motorcycles, pedestrians, bicycles) as they appear through their shape and other attributes, and due to their movement. Delivers both high-quality object detection as well as more advanced object tracking (the ability to designate the same object as such in consecutive frames).
Pixel Collision Classification
Accurately identifies the driveable area for autonomous and semi-autonomous vehicles by classifying each object in the 3D environment as collision-relevant or non-collision relevant with pixel-level data accuracy. Collision relevant subclasses are broken down into “objects” (i.e. car, truck, bicycle) or “obstacles”, the latter consisting of anything not classified as an object (i.e. tire, debris).
Continuous Calibration
Calibrates between the sensor’s coordinate system and the vehicle’s coordinate system following vehicle mounting in the assembly line. Also fixes pixels’ spatial displacement, which can occur while driving on bumps and potholes, and due to acceleration and deacceleration.
LiDAR is essential to enabling full autonomy (level 5). It is the only way for a car to truly “see” everything around it and make fast, accurate decisions based on its surroundings. However, today’s LiDAR solutions come at a prohibitive cost, and yet they still don’t have the performance required to get us to the necessary levels of autonomous driving.
Both InnovizOne and InnovizPro offer high-performance solid-state sensing to provide an accurate and reliable scan of a vehicle’s surroundings.
It primarily provide two LiDAR products and supporting perception software: InnovizPro is a solid-state LiDAR that offers outstanding performance and value for automotive and other applications. InnovizOne is a cutting-edge, automotive-grade LiDAR sensor that provides superior 3D sensing for Level 3-Level 5 autonomous driving. Innoviz offers perception software along with its LiDAR solutions. The holistic combination of hardware and an integrated perception software stack turns LiDAR data into an indispensable input for the vehicle’s decision-making.