Video Frame Object Localization With Detection-Transformation Switching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing AR applications on portable user devices face challenges in real-time object detection due to computational complexity and power limitations, leading to inaccurate object tracking and failure in handling occlusions or new objects entering the scene.

Innovation Solution

A multi-mode technology that switches between object detection and transformation modes for object location determination, using object detection for accuracy and transformation for efficiency, reducing computational and power requirements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If object location is determined in every frame of a video stream, then object tracking precision is improved, but processing time and computational resources increase

Engineering Contradiction:
Improveobject tracking precisionVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies partial action by determining object locations in only some frames rather than every frame. The system identifies a first object location in a first frame, then determines a second object location in a second frame based on the first location, using this information to generate a third object location in a third frame. This selective processing reduces computational load while maintaining tracking precision.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent uses preliminary action by establishing the first object location in the first frame as a baseline, then using this preliminary information to inform subsequent location determinations. The second object location is determined based on the first location, creating a foundation that guides future tracking decisions and reduces the need for full re-analysis in each frame.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If object location is determined in every frame of a video stream, then object tracking precision is improved, but computational resources increase

Engineering Contradiction:
Improveobject tracking precisionVSAvoidcomputational resources
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system performs object location determination in only necessary frames rather than all frames, reducing computational resource consumption. By using the first and second object locations to generate the third object location, the system achieves tracking precision while minimizing the computational energy required for processing.

Inventive Principle:
Principle #16Partial or excessive action

3Loss of information

If notifications are sent for every object location change, then information completeness is improved, but communication overhead increases

Engineering Contradiction:
Improveinformation completenessVSAvoidcommunication overhead
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent extracts and transmits only the essential object location information (first, second, and third object locations) rather than sending all raw frame data. This selective extraction maintains information completeness for tracking purposes while significantly reducing communication overhead and system complexity.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP3891700B1Object location determination in frames of a video stream
Publication Date: 2026.04.29 TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
  • EP3891700B1 patent drawingFigure 1~2
  • EP3891700B1 patent drawingFigure 3~4
  • EP3891700B1 patent drawingFigure 5

AI summary

An object locating method comprises deciding, for at least one frame of a video stream and based on at least one parameter representative of a change between a scene represented by the at least one frame and a scene represented by a reference frame of the video stream, whether determination of a location of at least one object (11, 13, 15, 17, 19) in the at least one frame is based on object detection applied to the at least one frame, or is based on a transformation of a location of the at least one object (11, 13, 15, 17, 19) detected in the reference frame.