# US 12,008,773 B2 · Object tracking apparatus and control method thereof using weight map based on motion vectors > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,008,773 B2 - Document ID: US12008773B2 - Status: Granted - Kind: B2 - Application number: 17/549,632 - Filed: 2021-12-13 - Published: 2022-06-23 - Granted: 2024-06-11 - Earliest claimed: 2020-12-22 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Yuta Kawamura - Web page: https://patentgrep.com/patent/US12008773B2 ## CPC - G06T 7/254: involving subtraction of images - G06T 5/40: using histogram techniques - G06T 5/50: using two or more images, e.g. averaging or subtraction - G06T 5/73: Deblurring; Sharpening - G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI] - G06V 10/62: relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking - G06V 10/761: {Proximity, similarity or dissimilarity measures} - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G06T 2207/20201: Motion blur correction - G06T 2207/20224: Image subtraction - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract An object tracking apparatus includes a motion vector calculation unit, a feature amount area determination unit, a reliability evaluation unit, a weight map creation unit, and an object tracking unit. The motion vector calculation unit is configured to calculate a motion vector between images. The feature amount area determination unit is configured to determine an area of an object detected from an image as a feature amount area. The reliability evaluation unit is configured to evaluate a reliability of the motion vector between images and a motion vector in the feature amount area. The weight map creation unit is configured to create a weight map based on the motion vector between images, the reliability, and the motion vector in the feature amount area. The object tracking unit is configured to track the object based on the weight map. ## Claims ### Claim 1 An object tracking apparatus comprising: at least one processor and memory holding a program which, when executed by the processor, causes the processor to function as: a motion vector calculation unit configured to calculate a motion vector between images; a feature amount area determination unit configured to determine an area of an object detected from an image as a feature amount area; a reliability evaluation unit configured to evaluate a reliability of the motion vector between the images and a motion vector in the feature amount area; a weight map creation unit configured to create a weight map, which is a distribution of weights of areas for which motion vectors have been calculated, based on the motion vector between images, the reliability, and the motion vector in the feature amount area; and an object tracking unit configured to track the object based on the weight map. ### Claim 2 (depends on 1) The object tracking apparatus according to claim 1 wherein, based on a difference between the motion vector between images and the motion vector in the feature amount area, the weight map creation unit calculates motion vectors in local areas of the motion vector in the feature amount area and creates a weight map by using the motion vectors in the local areas. ### Claim 3 (depends on 1) The object tracking apparatus according to claim 1, the motion vector in the feature amount area is calculated as a bin having a maximum number of motion vectors by performing histogram processing on the motion vector between images within the feature amount area. ### Claim 4 (depends on 1) The object tracking apparatus according to claim 1, wherein, in a case where a motion vector in a local area indicates a second value larger than a first value, the weight map creation unit sets a low weight for the local area in the weight map. ### Claim 5 (depends on 1) The object tracking apparatus according to claim 1, wherein, in a case where the reliability in an area indicates a second value smaller than a first value, the weight map creation unit sets a low weight for the area in the weight map. ### Claim 6 (depends on 1) An imaging apparatus comprising: an imaging element configured to capture an image of an object formed via an imaging optical system; and the object tracking apparatus according to claim 1. ### Claim 7 (depends on 6) The imaging apparatus according to claim 6 comprising: a circuit configured to refer to the motion vector between images and correct an image blur by driving a lens included in the imaging optical system. ### Claim 8 (depends on 6) The imaging apparatus according to claim 6 comprising: a circuit configured to refer to the motion vector between images and corrects an image blur by controlling a position of the imaging element included in the imaging apparatus. ### Claim 9 A control method for an object tracking apparatus comprising: calculating a motion vector between images; determining an area of an object detected from an image as a feature amount area; evaluating a reliability of the motion vector between images and a motion vector in the feature amount area; creating a weight map, which is a distribution of weights of areas for which the motion vectors have been calculated, based on the motion vector between images, the reliability, and the motion vector in the feature amount area; and tracking the object based on the weight map. ### Claim 10 A non-transitory computer-readable storage medium storing a program for causing a computer to execute a method of controlling an image processing apparatus, comprising: calculating a motion vector between images; determining an area of an object detected from an image as a feature amount area; evaluating a reliability of the motion vector between images and a motion vector in the feature amount area; creating a weight map, which is a distribution of weights of areas for which the motion vectors have been calculated, based on the motion vector between images, the reliability, and the motion vector in the feature amount area; and tracking the object based on the weight map.