What is your detector's resolution?
Your detector's resolution specifies the spatial resolution that all training images in your detector will be automatically scaled to when both training and detecting. This is to ensure object and texture size consistency (in pixels) in both your data set and project imagery for better results. When the image resolutions are changed they are simply scaled (like in a simple image editing software). It does not add new details or information to your imagery (a blurry object will remaining a blurry object after scaling). Therefore, it is usually recommended that you only train on and run your detector on, resolutions that are very close to its resolution setting.
How do you set your detector's resolution?
When you first create your detector, the resolution will be set the resolution of the first image you add to your detector. It can be then changed in the detector settings under the 'Spatial Resolution" setting later on if necessary.
We recommend that you use training images that have similar spatial resolutions. You can then set your detector spatial resolution to the average resolution of your training images.
It can sometimes be helpful to change the detector resolution further, for example if the objects you are detecting are either:
- too small (only a few pixels) which makes it hard for the detector to pick up
- or too big, and they don't fit into a standard training tile size, which means your detector will never see an entire instance of your object during training
Example
We provide here an example to give an idea of the targetĀ resolution setting effects:
- By increasing theĀ resolutionĀ (i.e 0.15 -> 0.05) the image gets oversampled.
- By decreasing theĀ resolutionĀ (i.e 0.15 -> 0.25) the image getsĀ downsampled.
The detector when observing the images looks at them by dividing each image into smaller tiles, and two undesired scenarios can happen.
Too high-resolutionĀ images
Ideally in a tile, you should be able to see your entire object, plus some of its surroundings. If it's not the case you can use theĀ resolutionĀ detector settings to downscale your images so that your objects fit better.
By downscaling our imagery (so setting a lowerĀ spatialĀ resolutionĀ setting) we see the following, which is much more understandable by the model:
Too low-resolutionĀ images
You may also have the opposite problem where your objects are too small (for example 2px by 2px objects are quite challenging for the detector to pick up). Especially if these small objects are adjacent to each other the problem becomes even more challenging for the detector to separate them. You may want to consider upscaling if that is the case using the detectorĀ resolutionĀ settings. Currently upscaling is limited to 2x.
With the nativeĀ resolution, we get the results on the right:
Now we can scale up theĀ resolutionĀ by 2x to get the following results, much better:
In order to see these kinds of images applied to your case, you can click on the Training Report icon (green icon) to be found in the top bar.
In this way, you can judge if your objects are too big or too small for the detector and consequently adjust the imageĀ resolution.
Anything else you should know?
- Image scaling is limited to a maximum of 4x, because any more than that will start to distort your imagery, it is recommended that you remove any images that result in this maximum being reached.
- The megapixel usage when running your detector is based on the number of pixels you run on and thus will take into account any scaling that occurs as a result of your detector's resolution setting.
- The platform displays your imagery in it's native resolution.