# US 12,183,201 B1 · Machine learning parking determination > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,183,201 B1 - Document ID: US12183201B1 - Status: Granted - Kind: B1 - Application number: 18/511,987 - Filed: 2023-11-16 - Granted: 2024-12-31 - Earliest claimed: 2023-11-16 - Applicants: Krish Arora - Inventors: Krish Arora - Web page: https://patentgrep.com/patent/US12183201B1 ## CPC - G08G 1/146: {where the parking area is a limited parking space, e.g. parking garage, restricted space} - G06Q 30/0284: {Time or distance, e.g. usage of parking meters or taximeters} - G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80) - G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88) - G06V 20/17: taken from planes or by drones - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G08G 1/144: {on portable or mobile units, e.g. personal digital assistant [PDA]} - G06T 2200/24: involving graphical user interfaces [GUIs] - G06T 2207/10032: Satellite or aerial image; Remote sensing - G06T 2207/20081: Training; Learning - G06T 2207/20132: Image cropping - G06T 2207/30232: Surveillance - G06T 2207/30252: Vehicle exterior; Vicinity of vehicle - G06V 2201/08: Detecting or categorising vehicles - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Apparatuses, systems, methods, and computer program products for machine learning parking determination. A method includes receiving an image of a parking spot taken by an image sensor. A method includes processing an image of a parking spot using a machine learning model to determine a likelihood that the parking spot is occupied. A method includes communicating to a user, on an electronic display screen of a hardware computing device, whether a parking spot is occupied or available based on a determined likelihood that the parking spot is occupied. ## Claims ### Claim 1 An apparatus, comprising: multiple image sensors disposed at different parking lots, the different parking lots comprise ng multiple parking spots each and each having different distances from a destination; an electronic hardware parking device in communication with the multiple image sensors, the electronic hardware parking device comprising a processor and a memory, the memory storing computer program code executable by the processor to perform operations, the operations comprising: receiving images taken by the image sensors, each of the images comprising multiple parking spots at one of the different parking lots; presenting a graphical user interface to administrators for each of the different parking lots allowing the administrators to graphically define, in the images of the multiple parking spots, locations of the multiple parking spots by selecting at least two diagonal corners for each of the multiple parking spots within the graphical user interface; processing the images of the multiple parking spots using a machine learning model to determine likelihoods that each of the multiple parking spots are occupied; predicting, using a second machine learning model, whether one or more of the parking spots are likely to be occupied or available at a future time based on the likelihoods that the parking spots are occupied and on a plurality of previous determinations of likelihoods that the parking spots are occupied; and communicating to a user, on a hardware computing device, a recommendation of one or more of the different parking lots for an unoccupied parking spot, based on the determined likelihoods that the parking spots are occupied, the predictions of whether one or more of the parking spots are likely to be occupied, and on a distance away from the destination that a user is willing to park. ### Claim 2 (depends on 1) The apparatus of claim 1, the operations further comprising predicting, using a second machine learning model, whether one or more of the parking spots are likely to be occupied or available at a future time based on the likelihoods that the parking spots are occupied and on a plurality of previous determinations of likelihoods that the parking spots are occupied. ### Claim 3 (depends on 1) The apparatus of claim 1, wherein at least one of the image sensors is coupled to the electronic hardware parking device in proximity to one of the different parking lots such that the image sensor is in view of the one of the different parking lots. ### Claim 4 (depends on 1) The apparatus of claim 1, wherein at least one of the image sensors is remote from the electronic hardware parking device and the electronic hardware parking device receives at least some of the images over a data network using an application programming interface of the electronic hardware parking device. ### Claim 5 (depends on 1) The apparatus of claim 1, wherein the operations further comprise: detecting the multiple parking spots in each of the images; processing the images using the machine learning model to determine separate likelihoods that each of the multiple parking spots are occupied; and communicating to the user, on the hardware computing device, whether each of the multiple parking spots are occupied or available based on the determined separate likelihoods that each of the multiple parking spots are occupied. ### Claim 6 (depends on 5) The apparatus of claim 5, the operations further comprising dynamically adjusting a cost of parking based on whether the multiple parking spots are occupied or available. ### Claim 7 (depends on 1) The apparatus of claim 1, wherein at least one of the image sensors comprises a preexisting security camera in proximity to one of the different parking lots. ### Claim 8 (depends on 1) The apparatus of claim 1, wherein at least one of the image sensors comprises an airborne drone flying in proximity to at least one of the different parking lots and in communication with the electronic hardware parking device over a wireless data network. ### Claim 9 (depends on 1) The apparatus of claim 1, the operations further comprising cropping each of the multiple parking spots from the images for processing using the machine learning model. ### Claim 10 (depends on 1) The apparatus of claim 1, the operations further comprising notifying an administrator associated with at least one of the parking lots in response to determining that at least one of the multiple parking spots has been occupied for at least a threshold amount of time. ### Claim 11 (depends on 1) The apparatus of claim 1, the operations further comprising notifying an administrator associated with at least one of the parking lots in response to determining that at least one of the multiple parking spots has been available for at least a threshold amount of time. ### Claim 12 A computer program product comprising a non-transitory computer readable storage medium storing computer program code executable to perform operations, the operations comprising: receiving images taken by the image sensors, each of the images comprising multiple parking spots at one of the different parking lots; presenting a graphical user interface to administrators for each of the different parking lots allowing the administrators to graphically define, in the images of the multiple parking spots, locations of the multiple parking spots by selecting at least two diagonal corners for each of the multiple parking spots within the graphical user interface; processing the images of the multiple parking spots using a machine learning model to determine likelihoods that each of the multiple parking spots are occupied; predicting, using a second machine learning model, whether one or more of the parking spots are likely to be occupied or available at a future time based on the likelihoods that the parking spots are occupied and on a plurality of previous determinations of likelihoods that the parking spots are occupied; and communicating to a user, on a hardware computing device, a recommendation of one or more of the different parking lots for an unoccupied parking spot, based on the determined likelihoods that the parking spots are occupied, the predictions of whether one or more of the parking spots are likely to be occupied, and on a distance away from the destination that a user is willing to park. ### Claim 13 (depends on 12) The computer program product of claim 12, the operations further comprising predicting, using a second machine learning model, whether one or more of the parking spots are likely to be occupied or available at a future time based on the likelihoods that the parking spots are occupied and on a plurality of previous determinations of likelihoods that the parking spots are occupied. ### Claim 14 A method comprising: receiving images taken by the image sensors, each of the images comprising multiple parking spots at one of the different parking lots; presenting a graphical user interface to administrators for each of the different parking lots allowing the administrators to graphically define, in the images of the multiple parking spots, locations of the multiple parking spots by selecting at least two diagonal corners for each of the multiple parking spots within the graphical user interface; processing the images of the multiple parking spots using a machine learning model to determine likelihoods that each of the multiple parking spots are occupied; predicting, using a second machine learning model, whether one or more of the parking spots are likely to be occupied or available at a future time based on the likelihoods that the parking spots are occupied and on a plurality of previous determinations of likelihoods that the parking spots are occupied; and communicating to a user, on a hardware computing device, a recommendation of one or more of the different parking lots for an unoccupied parking spot, based on the determined likelihoods that the parking spots are occupied, the predictions of whether one or more of the parking spots are likely to be occupied, and on a distance away from the destination that a user is willing to park.