# US 12,002,221 B2 · Control method and device for mobile platform, and computer readable storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,002,221 B2 - Document ID: US12002221B2 - Status: Granted - Kind: B2 - Application number: 17/648,179 - Filed: 2022-01-17 - Published: 2022-05-05 - Granted: 2024-06-04 - Earliest claimed: 2018-01-23 - Assignees: Sz Dji Technology Co., Ltd. - Applicants: Sz Dji Technology Co., Ltd. - Inventors: Lei Pang; Cong Zhao; Liliang Zhang; Gao Zhu; Sijin Li; Yao Liu - Web page: https://patentgrep.com/patent/US12002221B2 ## CPC - G06T 7/246: using feature-based methods, e.g. the tracking of corners or segments - G06F 18/22: Matching criteria, e.g. proximity measures - G06F 18/253: {of extracted features} - G06T 5/20: using local operators - G06T 5/73: Deblurring; Sharpening - G06T 7/0012: {Biomedical image inspection} - G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51) - G06V 10/757: {Matching configurations of points or features} - G06V 10/806: {of extracted features} - G06V 20/10: Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59) - G06V 20/13: Satellite images - G06V 20/17: taken from planes or by drones - G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands - G06V 40/103: {Static body considered as a whole, e.g. static pedestrian or occupant recognition} - G06T 2207/20028: Bilateral filtering - G06T 2207/20192: Edge enhancement; Edge preservation - G06T 2207/30196: Human being; Person - G06T 2207/30201: Face - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A control method for a mobile platform includes obtaining a captured image, determining a target first characteristic part of a target object from the captured image, determining a second characteristic part of the target object in the captured image, and switching from tracking the second characteristic part to tracking the target first characteristic part in response to a tracking parameter of the target object meeting a preset tracking condition. ## Claims ### Claim 1 A control method for a mobile platform comprising: obtaining a captured image; determining a first characteristic part of a target object from the captured image; determining a second characteristic part of the target object in the captured image; and switching from tracking the second characteristic part to tracking the first characteristic part in response to a tracking parameter of the target object meeting a preset tracking condition, the preset tracking condition including a relationship between a distance between the target object and the mobile platform and a preset distance threshold. ### Claim 2 (depends on 1) The method of claim 1, wherein determining the target first characteristic part includes: identifying one or more candidate characteristics for the first characteristic part from the captured image; determining one or more matching parameters each corresponding to one of the one or more candidate characteristics for the first characteristic part based on the one or more candidate characteristics for the first characteristic part and the second characteristic part; and determining the first characteristic part of the target object from the one or more candidate characteristics for the first characteristic part based on the one or more matching parameters. ### Claim 3 (depends on 2) The method of claim 2, wherein determining the one or more matching parameters each corresponding to one of the one or more candidate characteristics for the first characteristic part includes: for each of the one or more matching parameters, determining the matching parameter between the second characteristic part and the corresponding candidate characteristic for the first characteristic part based on the second characteristic part and the corresponding candidate characteristic for the first characteristic part. ### Claim 4 (depends on 2) The method of claim 2, wherein determining the one or more matching parameters each corresponding to one of the one or more candidate characteristics for the first characteristic part includes: estimating a third characteristic part of the target object based on the second characteristic part; and determining one or more matching parameters between the third characteristic part and the one or more candidate characteristics for the first characteristic part as the one or more matching parameters corresponding to the one or more candidate characteristics for the first characteristic part. ### Claim 5 (depends on 4) The method of claim 4, wherein estimating the third characteristic part includes estimating the third characteristic part based on the second characteristic part and a proportional relationship between the second characteristic part and the third characteristic part. ### Claim 6 (depends on 4) The method of claim 4, wherein estimating the third characteristic part includes: determining joint point information of the target object according to the second characteristic part; and estimating the third characteristic part based on the joint point information. ### Claim 7 (depends on 2) The method of claim 2, wherein determining the first characteristic part further includes: determining a largest matching parameter among the one or more matching parameters; and determining one of the one or more candidate characteristics for the first characteristic part corresponding to the largest matching parameter as the first characteristic part. ### Claim 8 (depends on 7) The method of claim 7, wherein the distance between the target object and the mobile platform is a first distance, and the preset distance threshold is a first preset distance threshold, the method further comprising: determining a second distance between a top edge of a tracking frame of the one of the one or more candidate characteristics for the first characteristic part corresponding to the largest matching parameter and a top edge of a tracking frame of the second characteristic part; and determining the one of the one or more candidate characteristics for the first characteristic part corresponding to the largest matching parameter as the first characteristic part includes determining the one of the one or more candidate characteristics for the first characteristic part corresponding to the largest matching parameter as the first characteristic part in response to the second distance being less than or equal to a second preset distance threshold. ### Claim 9 (depends on 2) The method of claim 2, wherein the one or more matching parameters include at least one of a coincidence degree, an image similarity degree, or a geometric similarity degree. ### Claim 10 (depends on 1) The method of claim 1, wherein: the first characteristic part includes a target human body and the second characteristic part includes a preset part of the target human body; and switching from tracking the second characteristic part to tracking the first characteristic part includes switching from tracking the preset part of the target human body to tracking the target human body. ### Claim 11 (depends on 10) The method of claim 10, wherein the preset tracking condition further includes: a size proportion of a tracking frame of the target object in the captured image being smaller than or equal to a preset proportion threshold, wherein the tracking parameter of the target object meets the preset condition in response to the relationship between the distance and the preset distance threshold is satisfied and the size proportion of the tracking frame is smaller than or equal to the preset proportion threshold. ### Claim 12 (depends on 1) The method of claim 1, wherein: the first characteristic part includes a preset part of a target human body and the second characteristic part includes the target human body; and switching from tracking the second characteristic part to tracking the first characteristic part includes switching from tracking the target human body to tracking the preset part of the target human body. ### Claim 13 (depends on 12) The method of claim 12, wherein the preset tracking condition further includes: a size proportion of a tracking frame of the target object in the captured image being greater than or equal to a preset proportion threshold, wherein the tracking parameter of the target object meets the preset condition in response to the relationship between the distance and the preset distance threshold is satisfied and the size proportion of the tracking frame is greater than or equal to the preset proportion threshold. ### Claim 14 (depends on 12) The method of claim 12, wherein the preset part includes a head or a head-shoulder part. ### Claim 15 A mobile platform comprising: at least one processor; and at least one memory including computer program code, wherein the at least one memory and the computer program code are configured, with the at least one processor, to cause the mobile platform to at least: obtain a captured image; determine a first characteristic part of a target object from the captured image; determine a second characteristic part of the target object in the captured image; and switch from tracking the second characteristic part to tracking the first characteristic part in response to a tracking parameter of the target object meeting a preset tracking condition, the preset tracking condition including a relationship between a distance between the target object and the mobile platform and a preset distance threshold. ### Claim 16 (depends on 15) The mobile platform of claim 15, wherein the at least one memory and the computer program code are further configured, with the at least one processor, to cause the mobile platform to at least: identify one or more candidate characteristics for the first characteristic part from the captured image; determine one or more matching parameters each corresponding to one of the one or more candidate characteristics for the first characteristic part based on the one or more candidate characteristics for the first characteristic part and the second characteristic part; and determine the first characteristic part of the target object from the one or more candidate characteristics for the first characteristic part based on the one or more matching parameters. ### Claim 17 (depends on 16) The mobile platform of claim 16, wherein the at least one memory and the computer program code are further configured, with the at least one processor, to cause the mobile platform to at least: determine a largest matching parameter among the one or more matching parameters; and determine one of the one or more candidate characteristics for the first characteristic part corresponding to the largest matching parameter as the first characteristic part. ### Claim 18 (depends on 17) The mobile platform of claim 17, wherein: the distance between the target object and the mobile platform is a first distance, and the preset distance threshold is a first preset distance threshold; and the at least one memory and the computer program code are further configured, with the at least one processor, to cause the mobile platform to at least: determine a second distance between a top edge of a tracking frame of the one of the one or more candidate characteristics for the first characteristic part corresponding to the largest matching parameter and a top edge of a tracking frame of the second characteristic part; and determine the one of the one or more candidate characteristics for the first characteristic part corresponding to the largest matching parameter as the first characteristic part in response to the second distance being less than or equal to a second preset distance threshold. ### Claim 19 A control method for a mobile platform comprising: obtaining a captured image; determining a first characteristic part of a target object from the captured image; determining a second characteristic part of the target object in the captured image; and switching from tracking the second characteristic part to tracking the first characteristic part in response to the tracking parameter of the target object meeting a preset tracking condition, including: in response to the first characteristic part including a target human body and the second characteristic part including a preset part of the target human body, switching from tracking the preset part of the target human body to tracking the target human body in response to a distance between the target object and the mobile platform being larger than or equal to a preset distance threshold. ### Claim 20 A control method for a mobile platform comprising: obtaining a captured image; determining a first characteristic part of a target object from the captured image; determining a second characteristic part of the target object in the captured image; and switching from tracking the second characteristic part to tracking the first characteristic part in response to the tracking parameter of the target object meeting a preset tracking condition, including: in response to the first characteristic part including a preset part of the target human body and the second characteristic part including a target human body, switching from tracking the target human body to tracking the preset part of the target human body in response to a distance between the target object and the mobile platform being less than or equal to a preset distance threshold.