Questions about how individual parts of claim 1 might be changed. A question may describe something different from what the claim language recites, or a version of it; no view is offered on which.
1.3Automatic image annotation
What ifWhat if the system runs without a user interface and selects image regions automatically?
Claim language“an user interface”
An image segmentation model produces pixel masks for debris and standing water in vehicle camera frames. The processor projects each mask onto a road surface model using the camera calibration and vehicle pose, then stores the resulting polygon in a map layer.
1.4Fixed roadside camera imagery
What ifWhat if fixed roadside cameras supply all images of the area around the vehicle?
Claim language“sensor mounted on an automated driving vehicle”
The server uses time-stamped vehicle positions to select frames from a pole-mounted camera whose field of view covers the vehicle location. It displays those frames and converts an operator's mark on the road surface to map coordinates using surveyed control points.
1.4Synthetic map display
What ifWhat if the operator sees a synthetic map view derived from camera frames while the frames remain hidden?
Claim language“display the one or more images”
An image processor extracts lane boundaries and object outlines and converts them into map coordinates. The display renders those features as lines and polygons, and selecting a feature highlights the associated pixel region in stored frame metadata and records its map geometry.
1.4Direct map annotation
What ifWhat if the operator draws directly on the map and uses the images only as visual references?
Claim language“mark a portion in the one or more images”
A dashboard shows camera frames beside a map centered on the vehicle's capture position. The operator draws a point or polygon on the map, and the server stores those coordinates directly.
1.4Annotations indexed by image
What ifWhat if the system stores marked regions in an image review queue without recording them on a map?
Claim language“on map information of the predetermined area”
A database stores each mark as a pixel polygon keyed to the frame identifier, vehicle identifier, and capture time. Reviewers open queued records to see each polygon overlaid on its source image and assign a status.
Section 2 · machine-generated
Variations
Further arrangements of the same subject matter, described here as of the publication date at the foot of this page.
Other field of use
Aisle obstruction mapping in cold storage
An automated pallet carrier carries a side-facing laser scanner that measures the aisle at floor level. A workstation displays an image formed from the scan returns and accepts a polygon drawn around an obstruction. The workstation uses the scan range, beam angle, and recorded carrier pose to project the enclosed returns onto the warehouse floor map. It stores the projected footprint with the aisle identifier and observation time.
Component substitution
Stylus input for marking map features
A pressure-sensitive stylus and digitizer replace the mouse used to mark a region in the displayed vehicle sensor image. The interface records the stroke between pen contact and release, converts digitizer coordinates to image pixels using the current zoom and pan, and closes the stroke into a polygon. The processor looks up the map positions associated with the sensor samples inside the polygon and saves their footprint as a map feature.
Parameter or scale variation
Buffered image review for twelve vehicles
Twelve automated vehicles each transmit a 640 by 480 range image twice per second, together with a timestamp and a map-referenced pose. A server retains the latest 120 seconds of images per vehicle and displays four operator-selected streams at once. When the operator freezes a frame and outlines a region, the interface submits the frame identifier and polygon vertices. The server uses the ranges and pose stored with that frame to project the marked region onto a shared map with 0.25-meter grid cells.
Combination with existing systems
Map annotations linked to maintenance tickets
An area management console connects to a computerized maintenance management system through a service interface. An operator outlines a damaged surface in a vehicle sensor image, and the console saves the corresponding map footprint with a reference to the source frame. The console submits the feature identifier, map position, defect type, and image crop to create a maintenance ticket. It stores the returned ticket identifier with the map feature and displays subsequent ticket status updates.
Map annotations in fleet route planning
An area management console shares registered map annotations with a fleet route planner. An operator marks a temporary closure in a vehicle sensor image and assigns an expiration time, and the console registers the marked footprint on the map. The planner tests the footprint for intersection with route segments and excludes intersecting segments when calculating routes during the closure period. At expiration, it removes that annotation from the active closure set and checks the affected segments against any remaining closures.
Automated or data-driven variant
Tracking a marked region across frames
An operator outlines a region in one image from a vehicle-mounted range sensor. The processor tracks points inside the outline through subsequent images using pyramidal optical flow on the sensor’s intensity images. It pairs tracked pixels with their depth values, projects the resulting points into map coordinates using each frame’s recorded pose, and discards observations whose map positions differ from the median by more than a configured distance. The processor registers a footprint from the retained points and associates it with the original mark.
Specific version of a part
Fanless image processing computer
A fanless computer uses a multicore processor and a hardware video decoder to prepare frames for display. A solid-state drive stores camera calibration parameters, vehicle pose records, and pending annotations.
Touchscreen polygon marking
A capacitive touchscreen displays a paused camera frame and accepts taps that place polygon vertices. The interface converts screen positions to source image pixels using the current zoom and pan settings.
Ground plane map registration
The processor uses camera calibration and the vehicle pose at capture time to cast a ray through each marked vertex on the road surface. It intersects the rays with a local ground plane and stores the resulting vertices as a polygon in a map layer.
Section 3 · quoted from USPTO records
Other work
Passages reproduced word for word from two earlier-published U.S. patent documents, placed beside the language of claim 1. No characterization is offered. Each passage is marked A or B for the document it comes from; ¶ numbers are the paragraph numbers in the USPTO’s published full text of that document.
Display 2 may be the visual output means (typically a screen) of any suitable Web-enabled computerized device comprising, at minimum, a microprocessor coupled to a memory, including, without limitation, any presently known or hereinafter developed stationary or portable computer, personal digital assistant, or smart phone.
A · US 2011/0299724 A1 · ¶ 14
Each node of the plurality of nodes and the operator console node include a microprocessor and a memory device.
B · US 2025/0123612 A1 · abstract
1.3an user interface, wherein
The operator console node 215 is similar to the other nodes 210 except that the operator console node 215 can include a graphical user interface (GUI) or human-machine interface (HMI) to enable the operator to interact with the control system 100.
B · US 2025/0123612 A1 · ¶ 41
1.4the processing circuitry is configured to: acquire one or more images that are acquired by using a sensor mounted on an automated driving vehicle in the predetermined area and that indicate a situation around the automated driving vehicle in the predetermined area; display the one or more images on a display device of the user interface; receive an operation that is input through the user interface to mark a portion in the one or more images; and register the portion marked in the one or more images on map information of the predetermined area.
(c) combining said image indicator with said image; and (d) displaying the combined image indicator and image on a display in communication with said microprocessor and said memory.
A · US 2011/0299724 A1 · claim 1
An empty cell means only that no passage was reproduced there.
Statements in these documents
Presently, social media security systems and methods make no provision to ensure the image attached to the profile is representative, secure, or feature an independent process for secure management.
A · US 2011/0299724 A1 · ¶ 4
A further advantage exists for a system and method that employs a security identifier that may be undetectably embedded in an image using steganographic and/or encryption techniques to monitor, track, and potentially recall the image.
A · US 2011/0299724 A1 · ¶ 7
However, current systems do not provide an ability to switch between control schemes in real time, such as during a live show.
B · US 2025/0123612 A1 · ¶ 2
The automation and motion control system allows real time control of devices summed from a stored control path submodule, a manual control submodule or a reactive control submodule to provide control to at least one device.
B · US 2025/0123612 A1 · ¶ 13
Cite aspatent.fyi, US 2026/0356388 A1, claim 1, first published 2026-11-20T01:05:31-05:00, https://patent.fyi/US20260356388/, SHA-256 02f83cc8e754cef1996a0accbf1034cd4c2422d4338700e81e2d2df0d32e5482