TIADALG Release Notes

Version: 00.07.03.00

Contents

  1. Introduction
  2. Licensing
  3. What's New
  4. Documentation
  5. Upgrade and Compatibility Information
  6. Device Support
  7. Validation Information
  8. Fixed Issues
  9. Known Issues
  10. Technical Support
  11. Package Versioning

Introduction

The package consists of the Texas Instruments TIADALG Software package

Licensing

The licensing information of this library, as well as any third-party components included which are made available under a number of other open-source licenses are enumerated as part of the manifest. A complete manifest along with export control information is detailed here [HTML].

Documentation

1 User's Guide [HTML]
3 Data Sheet [HTML]
4 Software Manifest [HTML]

What's New

List of features supported in this release are :

  1. Image pre processsing API targetted for deep learning application, and it is optimized for C66x DSP (tiadalg_image_preprocessing) for 8b and 16b output bit depth
  2. Camera lens distortion correction and insertion for fish eye images, and it is optimized for C66x DSP (tiadalg_fisheye_transformation)
  3. 3 plane seperation/creation from raw output from DOF accelerator, and it is optimized for C66x DSP (tiadalg_dof_plane_seperation)
  4. Feature matching API to select top feature, and it is optimized for C66x DSP (tiadalg_select_top_feature)
  5. Camera Pose estimation API using solve pnp technique, and it is optimized for C66x DSP (tiadalg_solve_pnp)
  6. Visual localization algorithm with external feature and descriptor, and it is optimized for C66x DSP (tiadalg_visual_localization)
  7. Sparse feature descriptor up-sampling and convolution optimized for C66x DSP(tiadalg_sparse_upsampling)
  8. Image color blending on C66x DSP to show different kind of pixel detection computed by some other algorithm (tiadalg_image_color_blending)
  9. Image thresholding followed by Non Maxima Supression optimized for C66x DSP (tiadalg_image_recursive_nms)
  10. Structure from Motion application on C7x (tiadalg_structure_from_motion)
  11. Voxelization preprocessing API for points pillar CNN. Only reference code. (tiadalg_voxelization)

Upgrade and Compatibility Information

  • C7x Build of C66x APIs are supported. No C7x specific optimization is done except for tiadalg_structure_from_motion application.

    • Device Support

    Target SoC Target Plaform Build environment (OS) Target environment (OS)
    PreSi x86_64 Linux PC x86_64 (Linux) x86_64 (Linux)
    PreSi C66x/C7x DSP x86_64 (Linux) C66x/C7x DSP

    Validation Information

    This release has dependency on GCC , C6000 and C7000 compiler. Please refer top level SDK information for exact version of these dependency.

    Fixed Issues

    Known Issues

    Technical Support

    For technical support, please post your questions on TI E2E Forum for Automotive ADAS SoCs.

    For additional assistance, contact local TI Field Application Engineer

    Package Versioning

    Each package version is composed of 4 period-delimited numbers - represented here by the letters M, m, p and b [M.m.p.b]. The table below provides a descriptive reference regarding package version numbering.

    Digit Meaning Description
    1 (M=Major) Major revision Incremented when the new version is substantially different from the previous For example, a new module added or an existing module's algorithm significantly altered.
    2 (m=minor) Minor revision Incremented when the new version has changed but not in a major way. For example, some minor changes in the API or feature set.
    3 (p=patch) Patch number Incremented for all other source code changes. This include any packaging support code.
    4 (b=build) Build number Incremented for each release delivery to CM. Reset for any change to M, m or p
    Copyright 2018, Texas Instruments Incorporated