IP Library › Granted Patent US 12,731,500
Granted Patent B2
US 12,731,500 · App. 18/660,714 · Granted Sep 8, 2026

Systems and methods for identifying and adapting exciting shot-paths involving a vehicle

Inventor: John-Michael McNew (Ann Arbor, MI)
Assignees: Toyota Motor Engineering & Manufacturing North America, Inc.; Toyota Jidosha Kabushiki Kaisha
G08G7/00G05D1/689G07C5/02G05D2109/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,731,500
App. No.
18/660,714
Granted
Sep 8, 2026
Kind
B2
Abstract

Systems, methods, and other embodiments described herein relate to identifying and adapting exciting shot-paths within a camera mode through acquiring data from a vehicle and an aerial device. In one embodiment, a method includes estimating an activity using context from situational data acquired about a vehicle and an environment surrounding the vehicle. The method also includes identifying shot-paths for the activity from estimated paths and viewing angles of an aerial device. The method also includes calculating excitement factors for the shot-paths using a model and selecting at least one of the shot-paths according to the excitement factors. The method also includes, on a condition that the at least one of the shot-paths satisfies feasibility conditions, adapting the shot-paths for the activity by monitoring the situational data and factoring the excitement factors.

Claims (49)

1 . A tracking system comprising:

a memory storing instructions that, when executed by a processor, cause the processor to:

estimate an activity using context from situational data acquired about a vehicle and an environment surrounding the vehicle;

identify shot-paths for the activity from estimated paths and viewing angles of an aerial device;

calculate excitement factors for the shot-paths using a model and select at least one of the shot-paths according to the excitement factors;

on a condition that the at least one of the shot-paths satisfies feasibility conditions, a decay rate, and a decay duration, adapt the shot-paths for the activity by monitoring the situational data and factoring the excitement factors, and control the aerial device along the shot-paths, where in the decay rate and the decay duration include factoring interest from an occupant of the vehicle about an image from the at least one of the shot-paths; and

assemble a timeline for the vehicle with a sequence of the shot-paths according to the excitement factors, wherein the timeline repeats the at least one of the shot-paths that is an initial shot-path according to a downward slope of the decay rate and the decay duration for another one of the shot-paths.

2 . The tracking system of claim 1 further including instructions to:

optimize the timeline according to the decay rate and reuse factors associated with the shot-paths that maximize the excitement factors for the activity using a threshold level.

3 . The tracking system of claim 2 further including instructions to:

upon the at least one of the shot-paths unsatisfying the feasibility conditions associated with the decay rate, recalculate the excitement factors for the shot-paths using the model and select a different shot-path.

4 . The tracking system of claim 2 , wherein the instructions to calculate the excitement factors for the shot-paths further include instructions to:

rank the excitement factors associated with the shot-paths by learning preferences acquired about occupants of the vehicle, wherein the preferences include one of occupant ratings for viewpoints, the viewing angles, flight plans for the activity, and a manual selection from the shot-paths.

5 . The tracking system of claim 4 , wherein the excitement factors are raw scores formulated with one of flight paths, the viewing angles, degrees of freedom (DoF), vehicle views, shortest path, least cost, and view confidence, and the model is one of an expert-based model and a data-driven model.

6 . The tracking system of claim 1 , wherein the instructions to identify the shot-paths further include instructions to:

compute availability of the shot-paths using the context, wherein the shot-paths are available according to safety, view obstructions, and a relative motion between the vehicle and the aerial device.

7 . The tracking system of claim 1 , wherein the instructions to estimate the activity using the context further include instructions to:

select the activity from a set of activities according to a trajectory and a speed of the vehicle.

8 . The tracking system of claim 1 further including instructions to:

upon the activity for the vehicle ending, search for another activity using the context.

9 . The tracking system of claim 1 , wherein the feasibility conditions include one of safety associated with the aerial device, a relative motion between the vehicle and the aerial device, and view obstructions.

10 . A non-transitory computer-readable medium comprising:

instructions that when executed by a processor cause the processor to:

estimate an activity using context from situational data acquired about a vehicle and an environment surrounding the vehicle;

identify shot-paths for the activity from estimated paths and viewing angles of an aerial device;

calculate excitement factors for the shot-paths using a model and select at least one of the shot-paths according to the excitement factors;

on a condition that the at least one of the shot-paths satisfies feasibility conditions, a decay rate, and a decay duration, adapt the shot-paths for the activity by monitoring the situational data and factoring the excitement factors, and control the aerial device along the shot-paths, wherein the decay rate and the decay duration include factoring interest from an occupant of the vehicle about an image from the at least one of the shot-paths; and

assemble a timeline for the vehicle with a sequence of the shot-paths according to the excitement factors, wherein the timeline repeats the at least one of the shot-paths that is an initial shot-path according to a downward slope of the decay rate and the decay duration for another one of the shot-paths.

11 . A method comprising:

estimating an activity using context from situational data acquired about a vehicle and an environment surrounding the vehicle;

identifying shot-paths for the activity from estimated paths and viewing angles of an aerial device;

calculating excitement factors for the shot-paths using a model and selecting at least one of the shot-paths according to the excitement factors;

on a condition that the at least one of the shot-paths satisfies feasibility conditions, a decay rate, and a decay duration, adapting the shot-paths for the activity by monitoring the situational data and factoring the excitement factors, and controlling the aerial device along the shot-paths, wherein the decay rate and the decay duration include factoring interest from an occupant of the vehicle about an image from the at least one of the shot-paths; and

assembling a timeline for the vehicle with a sequence of the shot-paths according to the excitement factors, wherein the timeline repeats the at least one of the shot-paths that is an initial shot-path according to a downward slope of the decay rate and the decay duration for another one of the shot-paths.

12 . The method of claim 11 further comprising:

optimizing the timeline according to the decay rate and reuse factors associated with the shot-paths that maximize the excitement factors for the activity using a threshold level.

13 . The method of claim 12 further comprising:

upon the at least one of the shot-paths unsatisfying the feasibility conditions associated with the decay rate, recalculating the excitement factors for the shot-paths using the model and selecting a different shot-path.

14 . The method of claim 12 , wherein calculating the excitement factors for the shot-paths further includes:

ranking the excitement factors associated with the shot-paths by learning preferences acquired about occupants of the vehicle, wherein the preferences include one of occupant ratings for viewpoints, the viewing angles, flight plans for the activity, and a manual selection from the shot-paths.

15 . The method of claim 14 , wherein the excitement factors are raw scores formulated with one of flight paths, the viewing angles, degrees of freedom (DoF), vehicle views, shortest path, least cost, and view confidence, and the model is one of an expert-based model and a data-driven model.

16 . The method of claim 11 , wherein identifying the shot-paths further includes:

computing availability of the shot-paths using the context, wherein the shot-paths are available according to safety, view obstructions, and a relative motion between the vehicle and the aerial device.

17 . The method of claim 11 , wherein estimating the activity using the context further includes:

selecting the activity from a set of activities according to a trajectory and a speed of the vehicle.

18 . The method of claim 11 further comprising:

upon the activity for the vehicle ending, searching for another activity using the context.

19 . The method of claim 11 , wherein the feasibility conditions include one of safety associated with the aerial device, a relative motion between the vehicle and the aerial device, and view obstructions.

20 . The method of claim 11 , wherein the situational data includes information acquired from the aerial device about the vehicle and the environment surrounding the vehicle.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 20, 2024
From: MCNEW, JOHN-MICHAEL
To: TOYOTA MOTOR ENGINEERING & MANUFACTURING NORTH AMERICA, INC.; TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 067465/0363 →
Continuity (2)
Provisional Application 63626128 · Jan 29, 2024
Related Publication 20260038380A1 · Feb 5, 2026
References Cited (21)
US 9854165B2 · Wang et al. · 2017 [cited by applicant]
US 10053236B1 · Buchmueller et al. · 2018 [cited by applicant]
US 11334076B2 · Hortner · 2022 [cited by applicant]
US 20140336848A1 · Saund et al. · 2014 [cited by applicant]
US 20190225239A1 · Sasaki · 2019 [cited by examiner]
US 20200137580A1 · Yang et al. · 2020 [cited by applicant]
US 20210256255A1 · Al Qizwini · 2021 [cited by examiner]
US 20220035382A1 · Zhou et al. · 2022 [cited by applicant]
US 20220374013A1 · Bachrach · 2022 [cited by examiner]
US 20230146288A1 · Hershkovitz · 2023 [cited by examiner]
US 20230315093A1 · Vaughn et al. · 2023 [cited by applicant]
CA 2831712A1 · 2012 [cited by examiner]
WO 2016069497A1 · 2016 [cited by applicant]
Gshwindt et al., “Can a Robot Become a Movie Director? Learning Artistic Principles for Aerial Cinematography”, Nov. 8, 2019 , IEEE, 2019 IEEE/RSJ IROS, pp. 1107-1114 (Year: 2019). [cited by examiner]
Huang et al., “ACT: An Autonomous Drone Cinematography System for Action Scenes”, May 25, 2018, IEEE, 2018 IEEE ICRA, pp. 7039-7046 (Year: 2018). [cited by examiner]
Livermore, “Optimal UAV Path Planning for Tracking a Moving Ground Vehicle With a Gimbaled Camera”, Mar. 2014, Air Force Institute of Technology, pp i-106 (Year: 2014). [cited by examiner]
Roberts, “Trajectory Optimization Methods for Drone Cameras”, May 2019, Stanford University, pp i-4 (Year: 2019). [cited by examiner]
Sabetghadam et al., “Optimal Trajectory Planning for Autonomous Drone Cinematography”, 2019, IEEE, pp. 1-7 (Year: 2019). [cited by examiner]
Sochopoulos et al., “Deep Reinforcement Learning with semi-expert distillation for autonomous UAV cinematography”, 2023, IEEE, 2023 IEEE ICME, pp. 1325-1330 (Year: 2023). [cited by examiner]
R. Bonatti et al., “Autonomous Aerial Cinematography in Unstructured Environments With Learned Artistic Decision-Making”, Oct. 15, 2019, arXiv:1910.06988v1, pp. 1-49 (Year: 2019). [cited by examiner]
Galvane et al., “Automated Cinematography with Unmanned Aerial Vehicles,” arXiv: 1712.04353, Dec. 17, 2017, pp. 1-8. [cited by applicant]