Video images that ultimately make it to your display or used for computer vision are typically process through a lens and sensor. These raw images could have noise from the environment, un-wanted artifacts, poor color, limited lighting, and many other issues that impact the quality. An ISP (Image Signal Processor) is used to perform operations on the video images and convert them to digital streams that are easier to handle for downstream systems. ISPs often have many settings that help enable features like gamma correction, auto exposure, white balance, black level, and gain adjustments. ISPs can have from 20 up to over a hundred different parameters to adjust. Setting up these parameters to match the required application requires tuning. Tuning involves testing the camera and ISP with different setting top achieve the best image quality. Due to the high number of parameters this tuning can take several months of trial and error to achieve an optimized tuning. Also, if the camera is used for computer vision (helping machines see the environment) then it is extremely difficult for a person to determine what settings produce the optimum images for computers to analyze.
Altas is a software application that uses a solver algorithm to automate the manual task of tuning camera and ISPs. Altas uses a methodology that uses metrics or KPI (Key Performance Indicators) to achieve certain objectives, then the solver adjust the ISP parameters over thousands of iterations to achieve the KPI metrics that are set. This approach minimizes the use of subjective and manual adjustments and has been shown to produce much better results. Atlas tuned image quality for visual applications, like a vehicle rear view camera, can have improved color, more smoothness, and fewer unwanted artifacts. Altas tuned quality for computer vision also has been shown to produce characteristics that improves accuracy when identifying and tracking objects. Altas can iterate thousands of settings over days that could take a person many months to achieve a similar result. The Atlas application and methodology can prevent time and resources wasted on trial and error, and it can achieve better quality for visual and computer vision applications.
Atlas Set Up
The Atlas methodology and application requires setting up a camera and ISP within a testing environment. Below is typical setup for Atlas:
Atlas setup includes a number of components within your lab environment:
- Display Machine with 4k Display- Mini PC
- ISP board with camera
- Control machine – runs camera system and connects to camera hardware
- Compute machine- mini PC or Notebook that runs Atlas
- Additional equipment may be required for HDR, Auto White Balance, or Computer Vision optimization.
The ISP board and camera are setup and oriented towards the 4k display. The 4k display is powered by a mini PC that shows a tuning chart. A control machine is used to run the camera system and connect to the camera hardware. Finally, a compute machine is used to run the Atlas software and determine the optimized parameters.
Atlas Workflow Methodology
After the Atlas testing environment is set up, the Atlas workflow methodology can be used to tune the ISP and camera sensor. If the ISP is new there is an integration step required to integrate it to use the Atlas SDK, but many ISPs are currently integrated with Atlas. The lab and KPI (Key Performance Indicators) targets are set to achieve the desired objectives. Then, the solver can be used to achieve the KPI targets. Results can be analyzed and optimal parameters identified while the optimization is running or after it is completed.
- Lab environment setup
- ISP integration (if needed)
- Set KPI targets
- Solver optimizes by iterating towards the KPI targets
- Results analysis
- Optimal ISP settings
When the optimal ISP settings are found they can be used for the camera and ISP combination. If the camera use case changes or if a new camera sensor is needed then the tuning set up can be re-used to optimize the settings again.