SPRACX1A April   2021  – April 2021 TDA4VM , TDA4VM-Q1

 

  1.   Trademarks
  2. 1Introduction
  3. 2The Visual Localization Problem
    1. 2.1 Key Point Extraction and Descriptor Computation
    2. 2.2 Feature Matching and Pose Estimation
  4. 3Visual Localization on TDA4VM
  5. 4Example Visual Localization Application
    1. 4.1 Optimized Building Blocks for Your Own Visual Localization Pipeline
  6. 5References
  7. 6Revision History

Example Visual Localization Application

A visual localization application that is built on the subtasks described above is included with the SDK that accompanies the TDA4x family of devices. Since this application was designed to run on simulated data, as it allows for comparison with the ground truth, the data does not need to be processed using VPAC. The application instead consumes saved simulated image data. Detailed documentation of this application can be found here.

Figure 4-1 shows an example output from this application. Here, the computed and actual paths are overlaid on a bird-eye view of the scene. The blue markings here show the computed trajectory, and the white shows the ground truth. The utilizations of the different compute cores at this instance are shown on the bottom right corner. Detailed results can be found here.

GUID-20210312-CA0I-5FBX-FNKM-5KCMJ262DRFF-low.jpg Figure 4-1 Example Output From Visual Localization Application