The Detector Settings tab enables you to finely adjust and optimize your detectors to meet specific project requirements and use cases. Offering both Basic and Advanced settings, it provides a variety of options to customize detector behavior and enhance performance.
Platform interface
Picterra offers an intuitive platform interface, meticulously crafted for seamless navigation and user-friendly interactions, prioritizing efficiency, speed, and quality in geospatial data analysis.
Designed to facilitate production of scalable customized machine learning models, Picterra streamlines your workflows, empowering you to achieve unparalleled productivity and precision.
Dashboard
Upon logging in to Picterra you are greeted by the Dashboard page. This consists of three sections.
- A tabbed panel showing either Favorites or Detector Activities
- A Notifications panel showing either Activities or Mentions
- Highlights of recently released platform features that you might be interested in learning about
Detector Activities Tab
In the Detectors Activities tab you can see and access recent activities on the platform including:
- The most recently trained detectors
- The most recent detections and annotations
This allows you to quickly get up to speed in the latest developments on your detectors and jump back in where you left off.
Favorites Tab
From here, you can see and access the Projects and Detectors that you have selected as your favorites. This allows you to bookmark specific projects or detectors that you are working on and find them quickly and easily.
Marking Detectors or Projects as Favorites
To mark a project or detector as a favorite, simply click the Star icon on its card. This action will ensure it's conveniently listed on the Favorites tab for quick access. The star outline indicates that the project or detector is not a current favorite, and a solid blue star indicates that the project or detector is a current favorite!
Activities and Mentions
On the right-hand panel you can see a list of the recent Activities and their status within the platform, this list includes:
- Detector training runs
- Detections on a project or raster
- Advanced Tools runs
- Processing of image uploads
On the Mentions tab you can catch up with the most recent marker comments which mentioned your username, and click on View to be taken directly to that Marker in order to respond.
Detectors UI
To streamline detector creation and management in Pictera, access the dedicated Detectors tab via the top bar on your Dashboard.
Here, you can initiate creation of a new detector by clicking the Train New Detector button, or browse through existing detectors you’ve created or those shared with you.
Once you’ve configured the baseline settings for your new detector and are prepared to create and train your model, you’ll discover all the necessary tools within the Detector Training View. Here, you can seamlessly develop and prepare your model for production.
Detector Training View - Training toolbar
The training toolbar is available on the left side of the detector training UI and enable you to create annotations and define training, accuracy and testing areas, used to build and train your your detector.
Detector Training View - Top bar
Detector settings
Train Detector
Training report
Detector settings
Train Detector
Once your detector is prepared for training, simply click the Train button to initiate the training process with just one click.
Training report
The training report is available after each training iteration is complete and can be accessed using the button on the right of the “Train Detector” button as seen above.
The training report is an extremely helpful tool to give you more detailed insights into your detector to help you with improvements and additional experimentation. There are multiple sections in the report that can aid you in this.
View
Selection
Training area
Drawing tool
Magic wand
Accuracy area
Testing area
Import
Markers
View
The View button on the toolbar allows you to control various options which influence how your detections are displayed. You can switch between viewing the detections as shapes and as the center points of those detections. You can also toggle showing or hiding all detections from the image here.
Selection
This default tool allows you to:
- Click and drag to move the map
- Left Click to Select a Single Polygon for Editing
Click and Drag to move the map
If you click and hold, and drag your mouse you can scroll around the image.
Select a Single Polygon for Editing
Selecting a single detection allows you to move and edit the polygon. A number of actions are available to you including:
- Rotating and resizing the shape
- Click and drag the point on the dotted circle to rotate or resize the shape
- You can click the Fix Size Rotation button to lock the current shape size and restrict this to rotation only
- Move the shape
- Click inside the shape and drag it to move it
- Use the shape as a template and clone copies of it
- Click the Clone button. Your cursor will change to an outline of the shape. Left click to place copies.
- Cut holes in your shape
- Click the Cut Inside button, you will now be able to draw another shape inside your shape to cut a hole. Double-click to finish drawing.
- Delete the shape
- Press the
Delete
orBackspace
key to remove the shape
- Press the
At any point you can discard or save your edits with the Discard and Save buttons respectively.
Training area
Training areas are sub-regions that you define in your image that will be given to your detector to learn from. Any image content outside of these training areas is ignored, which is intended because if the detector tried to use your entire image that means you would be forced to annotate your entire image as well, which in the case of geospatial data, can often times be enormous.
Drawing tool
The drawing tools allow you to draw polygon outlines: the examples of object that will be shown to your detector, to learn from. The detector will learn from them, what kind of object you are looking for and how it looks like. Note that any image content in your training areas that does not have an outline will be treated as something you are NOT looking for.
Magic wand
The Magic Wand tool allows you to quickly create outlines of complex objects or regions in just a few clicks. This is leveraging the “Segment Anything” model by Meta/Facebook.
Accuracy area
Accuracy areas allow you to calculate the accuracy of your detector.
Annotating the accuracy areas, you can understand how precise is your detector, and test it, generating results within them, after training.
When you are training a detector you can calculate the accuracy score for your detector as well as accuracy score for each individual Accuracy area you created.
Testing area
Testing Areas, like Accuracy Areas in that they output results within them after training. However the main difference is just that they do not require annotations inside them and also will not output any quantitative measure of the accuracy of your detector.
The only serve as a way to quickly get some output over some regions of your training imagery as a qualitative check of the performance of your detector without having to spend time annotating.
We recommend that you only use this as tool to help you more easily decide where to put more training and accuracy areas because in the end they do not contribute to either the performance of your detector or the representative-ness of the score of your detector.
Import
If you are trying to automate a digitization process that you were doing manually before, it is likely you can import some of your existing data as annotations within a detector.
To do so, you need to have your data in GeoJSON format. If you have it in other formats (KML, Shapefile), you can convert it in GeoJSON first. /!\ The reference coordinate system should be in EPSG:4326 (WGS84 ellipsoid) and not any other projection system.
When creating or improving a detector, use the Upload button in the drawing tools and select a GeoJSON file.
The file should only contain Polygons (no lines).
Find out more about Importing annotations
Markers
Markers allow you to make note of various locations in your imagery.
You can assign markers by mentioning a user as well as add comments.
Markers have do not help in training your model whatsoever, they are simply a tool to help you manage your data.
You can start creating new markers using the Markers button.
Projects UI
Projects tab takes you to the Projects page, where you can efficiently store, organize and manage imagery for various projects, each folder containing relevant imagery for specific projects or geographies.
Once you have created your detector and run it on the image, you can inspect and edit achieved detection results in the related Image View accessible directly from the respective project folder.
Image View - Result management toolbar
The result management toolbar is available on the left side of the Image View UI and enable you to manage detection results and add further annotations to your imagery.
View
Split view
Selection
Drawing tool
Detection area
Magic wand
Markers
View
The View button on the toolbar allows you to control various options which influence how your detections are displayed. You can switch between viewing the detections as shapes and as the center points of those detections. You can also toggle showing or hiding all detections from the image here.
Split view
If your image is multispectral and you have more than one band visualization defined (more info), you can view two band visualizations side-by-side. Detections display and drawing will only be enabled on the primary image (left side), but a duplicate cursor will track your actions on the secondary image (right side).
Selection
This default tool allows you to:
- Click and drag to move the map
- Left Click to Select a Single Polygon for Editing
- Shift-click and drag to draw a selection box to select multiple polygons
Click and Drag to move the map
If you click and hold, and drag your mouse you can scroll around the image.
Select a Single Polygon for Editing
Selecting a single detection allows you to move and edit the polygon. A number of actions are available to you including:
- Rotating and resizing the shape
- Click and drag the point on the dotted circle to rotate or resize the shape
- You can click the Fix Size Rotation button to lock the current shape size and restrict this to rotation only
- Move the shape
- Click inside the shape and drag it to move it
- Use the shape as a template and clone copies of it
- Click the Clone button. Your cursor will change to an outline of the shape. Left click to place copies.
- Cut holes in your shape
- Click the Cut Inside button, you will now be able to draw another shape inside your shape to cut a hole. Double-click to finish drawing.
- Delete the shape
- Press the
Delete
orBackspace
key to remove the shape
- Press the
At any point you can discard or save your edits with the Discard and Save buttons respectively.
Selecting Multiple Polygons
To select multiple polygons, you can hold down your Shift key and click and drag to draw a selection box around the polygons you wish to select.
To delete the polygons you have selected, press Delete or Backspace.
Drawing tool
Select this tool to draw a new polygon outline in your currently selected detections layer. Left click on the image to start drawing, click to place points around the edge of your shape and double click to finish drawing.
Detection area
From the Detection Areas Tool, you can select one of three options
Edit Detection Areas
This tool allows you to select existing detection areas and modify their shape, move them and delete them. See the Selection tool above, for more info on polygon editing.
Draw a new Detection Area
This tool allows you to draw a new shape to create a detection area. Detection areas determine where detections will be made on your image when running your detector. Areas outside of detection areas will not be considered by the detector. Left click on the image to start drawing an area, click again to place points and double-click to finish drawing.
You can upload a geojson file which represents detection areas. You can drag and drop a file onto the dialog, or click to select one from your computer. We currently support geojson Polygon and Multipolygon feature types.
Magic wand
The Magic Wand tool allows you to quickly create outlines out of complex objects or regions in just a few clicks. This is leveraging the “Segment Anything” model by Meta/Facebook.
Markers
The markers tool allows you to leave comments at a specific location on your image. With this tool selected click anywhere on the map to leave a new comment, use the @ symbol to mention colleagues or leave yourself a reminder.