Your Browser is Out of Date

Nytro.ai uses technology that works best in other browsers.
For a full experience use one of the browsers below
Computer Vision 3D Flow and Function AI with LiDAR
Introduction Solution overview Partner overview Architecture overview Sizing and scaling Use case validation
Use case validation
Smart Places
Multiple LiDAR sensors at an intersection Object detection LiDAR images and maps integration
Security
Create events for intrusion detection Capture person height and location Showcase tag and follow capabilities Third-party integration
Conclusions References

Smart Places

Home > Workload Solutions > Computer Vision > White Papers > Computer Vision 3D Flow and Function AI with LiDAR > Smart Places

Smart Places

  • Object detection

    The SENSR application also performs object detection on the incoming LiDAR streams during processing. The goal of this test was to assess what objects could be detected along with what level of object detail can be extracted.

    Results

    We found it useful to sometimes simplify the viewing of objects by hiding the raw LiDAR point cloud and show the objects that were detected in the scene. An example of this is below:

    Figure 3. Object detection example
    Object Detection example

    Findings

    • Fine grained analysis of all objects in a scene is available.
    • Counts of the different object types (such as a car, person, or cyclist) are available for convenience.
    • A detailed description of the point data used to identify the objects is available. See the "Object Point Shape" in the left window that shows the points that were used to detect a pedestrian from the scene above.