# US 12,601,145 B2 · Exclusion zone or inclusion zone generation for object detection > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,601,145 B2 - Document ID: US12601145B2 - Status: Granted - Kind: B2 - Application number: 18/799,725 - Filed: 2024-08-09 - Published: 2026-02-12 - Granted: 2026-04-14 - Earliest claimed: 2024-08-09 - Assignees: Caterpillar Inc. - Applicants: Caterpillar Inc. - Inventors: Duane Myklejord - Web page: https://patentgrep.com/patent/US12601145B2 ## CPC - E02F 9/2033: {Limiting the movement of frames or implements, e.g. to avoid collision between implements and the cabin (sub-groups of E02F3/431 of E02F3/435 take precedence; for turntables E02F9/123)} - B60R 1/23: with a predetermined field of view - B60R 1/26: to the rear of the vehicle - E02F 9/265: {with follow-up actions (e.g. control signals sent to actuate the work tool)} - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads - G01S 2013/93272: {in the back of the vehicles} - G06T 2207/20036: Morphological image processing - E02F: DREDGING; SOIL-SHIFTING (winning peat E21C49/00) - B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A controller may obtain, from a camera, a first image and a second image depicting a work machine in an environment, where an implement of the work machine has moved, or the work machine has moved in the environment, in a depiction of the second image relative to the first image. The controller may generate a difference image that depicts a region of difference between the first image and the second image. The controller may perform object detection on image data from the camera based on the difference image, where the region of difference depicted in the difference image is an exclusion zone or an inclusion zone used for the object detection. ## Claims ### Claim 1 An object detection calibration system, comprising: a camera configured to mount on a work machine and to capture images relating to an environment of the work machine; and a controller configured to: obtain, from the camera, based on movement of an implement of the work machine into a first calibration position, a first image depicting the work machine in the environment, and obtain, from the camera, based on movement of the implement of the work machine into a second calibration position, a second image depicting the work machine in the environment, wherein the implement of the work machine has moved in a depiction of the second image relative to the first image; generate a difference image that depicts a region of difference between the first image and the second image; and perform object detection on image data from the camera based on the difference image, wherein the region of difference depicted in the difference image is an exclusion zone for the object detection. ### Claim 2 (depends on 1) The object detection calibration system of claim 1, wherein the controller is further configured to: process the difference image using one or more morphological operations to transform the region of difference into a solid geometry. ### Claim 3 (depends on 2) The object detection calibration system of claim 2, wherein the one or more morphological operations include a sequence of one or more foreground erosion operations and one or more foreground dilation operations. ### Claim 4 (depends on 1) The object detection calibration system of claim 1, wherein the first image depicts the implement in the first calibration position, and the second image depicts the implement in the second calibration position different from the first calibration position. ### Claim 5 (depends on 1) The object detection calibration system of claim 1, wherein the first image depicts the implement in the first calibration position in which the implement occupies a greater area of the first image than any other position of the implement would occupy, and the second image depicts the implement in the second calibration position different from the first calibration position. ### Claim 6 (depends on 1) The object detection calibration system of claim 1, wherein the controller, to obtain the first image and the second image, is configured to: cause presentation, in a user interface, of a first prompt that requests movement of the implement into the first calibration position; receive, via the user interface, a first indication that the implement is moved into the first calibration position; cause presentation, in the user interface, of a second prompt that requests movement of the implement into the second calibration position; and receive, via the user interface, a second indication that the implement is moved into the second calibration position. ### Claim 7 (depends on 1) The object detection calibration system of claim 1, wherein the controller, to obtain the first image and the second image, is configured to: cause the implement to move into the first calibration position; and cause the implement to move into the second calibration position. ### Claim 8 (depends on 1) The object detection calibration system of claim 1, wherein the controller, to obtain the first image and the second image, is configured to: detect that the implement is in the first calibration position; and detect that the implement is in the second calibration position. ### Claim 9 (depends on 1) The object detection calibration system of claim 1, wherein the controller, to generate the difference image, is configured to: process the first image and the second image using a foreground detection image processing technique, a background subtraction image processing technique, or an optical flow image processing technique. ### Claim 10 (depends on 1) The object detection calibration system of claim 1, wherein the implement is a ripper, and wherein the first image depicts the ripper in a fully-raised position, and the second image depicts the ripper in a non-fully-raised position. ### Claim 11 A method, comprising: obtaining, from a camera, based on movement of an implement of a work machine into a first position or movement of the work machine to a first location, a first image depicting the work machine in an environment, and obtaining, from the camera, based on movement of the implement of the work machine into a second position or movement of the work machine to a second location, a second image depicting the work machine in the environment, wherein the implement of the work machine has moved, or the work machine has moved in the environment, in a depiction of the second image relative to the first image; generating a difference image that depicts a region of difference between the first image and the second image; and performing object detection on image data from the camera based on the difference image, wherein the region of difference depicted in the difference image is an exclusion zone or an inclusion zone used for the object detection. ### Claim 12 (depends on 11) The method of claim 11, further comprising: processing the difference image using one or more morphological operations to transform the region of difference into a solid geometry. ### Claim 13 (depends on 11) The method of claim 11, wherein performing the object detection comprises: detecting an object in an image frame of the image data; identifying a location of the object in the image frame; comparing the location of the object to the region of difference in the difference image; and selectively discarding or outputting object detection data associated with the object based on whether the location of the object is within the region of difference. ### Claim 14 (depends on 11) The method of claim 11, wherein the difference image is a binary image. ### Claim 15 (depends on 11) The method of claim 11, wherein the first image depicts the implement in the first position in which the implement is in a farthest position of the implement from the camera, and the second image depicts the implement in the second position in which the implement is in a closest position of the implement to the camera. ### Claim 16 A work machine, comprising: a frame; an implement connected to the frame; a camera configured to capture images relating to an environment of the work machine; and a controller configured to: obtain, from the camera, based on movement of the implement of the work machine into a first position or movement of the work machine to a first location, a first image depicting the work machine in the environment, and obtain, from the camera, based on movement of the implement of the work machine into a second position or movement of the work machine to a second location, a second image depicting the work machine in the environment, wherein the second image differs from the first image by a depiction of the work machine or the environment; generate a difference image that depicts a region of difference between the first image and the second image; and perform object detection on image data from the camera based on the difference image, wherein the region of difference depicted in the difference image is an exclusion zone or an inclusion zone used for the object detection. ### Claim 17 (depends on 16) The work machine of claim 16, wherein the controller is further configured to: process the difference image using one or more morphological operations to transform the region of difference into a solid geometry. ### Claim 18 (depends on 16) The work machine of claim 16, wherein the camera is positioned in a rear-facing configuration with respect to the work machine. ### Claim 19 (depends on 16) The work machine of claim 16, wherein the implement is a ripper, and wherein the first image depicts the ripper in a fully-raised position, and the second image depicts the ripper in a non-fully-raised position. ### Claim 20 (depends on 16) The work machine of claim 16, wherein the first image depicts the implement in the first position in which the implement occupies a greater area of the first image than any other position of the implement would occupy, and the second image depicts the implement in the second position different from the first position.