SPRAD86 March   2023 AM62A3 , AM62A3-Q1 , AM62A7 , AM62A7-Q1 , AM68A , AM69A

 

  1.   Abstract
  2.   Trademarks
  3. 1Introduction
  4. 2Tuning Overview
  5. 3Hardware Requirement
  6. 4Software Requirement
    1. 4.1 Processor SDK Linux
    2. 4.2 TI's Reference Imaging Software
    3. 4.3 ISP Tuning Tool
  7. 5Sensor Software Development and Integration
    1. 5.1 Adding Sensor Driver to SDK
    2. 5.2 Updating GStreamer Plugins to Support the Sensor
      1. 5.2.1 Update TIOVX Modules
        1. 5.2.1.1 Source Code Change
        2. 5.2.1.2 Rebuild Modules
      2. 5.2.2 Update GStreamer Plugins
        1. 5.2.2.1 Source Code Change
        2. 5.2.2.2 Rebuild Plugins
        3. 5.2.2.3 Verify New Sensor in GStreamer Plugin
  8. 6Tuning Procedure
    1. 6.1 Verify Functional Operation of Camera Capturing
    2. 6.2 Enable Camera Streaming with Initial VPAC Configuration
      1. 6.2.1 Generate Configuration Files
      2. 6.2.2 Generate DCC Binary Files
      3. 6.2.3 Stream Video with the Initial Configuration
    3. 6.3 Adjust Camera Mounting
    4. 6.4 Capture Raw Images and Perform Basic Tuning
      1. 6.4.1 Launch the Tuning Tool and Create a Project
      2. 6.4.2 Tuning Order
      3. 6.4.3 Black Level Subtraction
      4. 6.4.4 Hardware 3A (H3A)
      5. 6.4.5 Auto White Balance (AWB)
        1. 6.4.5.1 Capture Raw Images for Different Lighting Conditions
        2. 6.4.5.2 Tuning AWB
      6. 6.4.6 Color Correction
    5. 6.5 Perform Fine Tuning
  9. 7Summary

1 Introduction

The AM6xA vision processors have a hardware accelerated Image Signal Processor (ISP) which is also referred as the Vision Pre-processing Accelerator (VPAC). With configurable image processing parameters, VPAC is designed to support a wide variety of raw camera modules (a typical raw camera module includes a lens, a filter, a raw image sensor, and sometimes a serializer). To obtain optimal image quality for a specific raw camera module at run-time, the parameters of VPAC needs to be computed and then applied to process the raw sensor images frame by frame. In order to achieve that, optimal VPAC parameters are typically prepared by engineers in an imaging lab under various controlled lighting conditions. Then at run-time, the prepared parameters are referenced and interpolated to fit the run-time lighting environment with the help of software imaging algorithms of Auto Exposure (AE), Auto White Balance (AWB), and dynamic ISP parameter control. The procedure of preparing the optimal VPAC parameters in an imaging lab is referred as ISP tuning in this application report.

The ISP tuning procedure described in this report applies to all SoCs in the AM6xA vision processor family, including AM62A, AM68A, and AM69A. Examples using the AM62A Starter Kit EVM are provided in the report.

For technical details of the ISP (VPAC) on a specific system-on-chip (SoC), see the Technical Reference Manual (TRM) of that SoC.