Camera Exposure and Computer Vision
What is Camera Exposure?
Exposure can be thought of as a DC bias in the overall brightness of an image.
Exposure can be measured by the Exposure Value using a series of grey patches.
Exposure is not the "brightest bright" relative to the "darkest dark" of an image: that's dynamic range.
What is Exposure?
Correct exposure is important to all computer vision tasks as any over-exposure or under-exposure results in degradation of contrast and in extreme cases, a complete los of information. Here is a picture of a simulated vehicle under various exposure values.
Even to the human observer, it is difficult to see details in over or under-exposed images.
Blasinski & Farrell, "Optimizing Image Acquisition Systems for Autonomous Driving"
Exposure Has a Major Impact on Computer Vision and Machine Vision
Blasinski et al demonstrated how the mean average precision of detection networks SSD-Mobilenet and Resnet drop significantly with incorrect exposure. Even after training the networks using multiple exposure values, the mean average precision dropped by 25% when over-exposed by 4 exposure values.
References and Related Links
Blasinski & Farrell, "Optimizing Image Acquisition Systems for Autonomous Driving"
Trying to Determine Your Camera Requirements?
Use our free web-based AoV Calculator to determine your system's Field of View Requirements. Then, use the M12 Lens calculator to match your requirements with the available lenses. Our Depth of Field Calculator also provides the hyperfocal distance and depth of field for every sensor and lens combination.
We also have a couple of other calculators that many engineers find interesting.
