Camera System Target Tracking Stationary State Handling

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current camera systems for motor vehicles cannot track target objects when both the vehicle and the object are stationary, as optical flow vectors cannot be determined in this state, leading to the object being 'lost' and potentially not detected as a hazard.

Innovation Solution

A method that detects a stationary state and stores the target object's relative position, using an object validation counter to resume tracking when movement criteria are met, allowing continued monitoring even when optical flow vectors cannot be calculated.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If optical flow vectors are used to track target objects, then tracking precision is improved during movement, but tracking reliability deteriorates when both vehicle and object are stationary

Engineering Contradiction:
Improvetracking precisionVSAvoidtracking reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The system stores the last known position and state information of the target object before entering a stationary state. This preliminary storage of tracking data allows the system to maintain continuous tracking awareness even when optical flow vectors cannot be calculated during stationary periods, preventing complete loss of target information.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

An intermediary tracking state is introduced that operates differently based on movement conditions. During movement, optical flow vectors are used for precise tracking. During stationary states, the system switches to an intermediary mode that relies on stored position data and detects when movement resumes, thereby bridging the gap between movement-based and stationary-based tracking requirements.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If the system waits for movement to detect target objects, then detection accuracy is improved during movement, but detection reliability deteriorates during stationary periods

Engineering Contradiction:
Improvedetection accuracyVSAvoiddetection reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The system performs preliminary detection and stores target object information before movement occurs or during the transition to stationary state. This ensures that even if no movement is detected during a stationary period, the target object has already been identified and tracked, maintaining continuous detection coverage.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The detection mechanism dynamically adapts its operation mode based on the movement state of the vehicle and target object. During movement, optical flow-based detection is active. During stationary states, the system transitions to a different detection mode that relies on stored information and monitors for movement resumption, thereby maintaining detection reliability across varying operational conditions.

Inventive Principle:
Principle #15Dynamics

3Reliability

If continuous tracking is implemented, then tracking reliability is improved, but computational complexity increases during stationary states

Engineering Contradiction:
Improvetracking reliabilityVSAvoidcomputational complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The computational complexity of the tracking system is dynamically adjusted based on the movement state. During movement, the system performs full optical flow calculations for continuous tracking. During stationary states, the system reduces computational load by switching to a simpler mode that monitors stored position data and detects movement resumption, thereby maintaining tracking reliability while avoiding unnecessary computational complexity during stationary periods.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

Instead of continuous heavy computational processing during stationary states, the system employs periodic checking of movement conditions and uses stored tracking information during intervals when no movement is detected. This periodic approach maintains tracking reliability by periodically updating based on movement detection while reducing computational complexity during extended stationary periods.

Inventive Principle:
Principle #19Periodic action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables more reliable and precise tracking of target objects, ensuring the driver is warned of potential obstacles even when the vehicle and object are stationary, by maintaining tracking and resuming it when movement resumes.

Implementation Method 1

a camera (3) disposed on the motor vehicle (1) and capturing an environmental region (6) of the motor vehicle (1)

Methodology Applied
Scientific EffectLight reflection: Reflection

Implementation Method 2

namely by determining optical flow vectors to the target object (5) based on the sequence of images during a relative movement between the motor vehicle (1) and the target object (5)

Methodology Applied
Scientific EffectOptical flow:

Data Source

PatentEP2936385B1Method for tracking a target object based on a stationary state, camera system and motor vehicle
Publication Date: 2019.04.10 CONNAUGHT ELECTRONICS
  • EP2936385B1 patent drawingFigure 1
  • EP2936385B1 patent drawingFigure 2a~2b
  • EP2936385B1 patent drawingFigure 3a~3b

AI summary

The invention relates to a method for tracking a target object (5) in an environmental region (6) of a motor vehicle (1) based on an image sequence, which is provided by means of a camera (3), by: - detecting the target object (5) in the environmental region (6), - tracking the target object (5) by means of an electronic image processing device by determining optical flow vectors to the target object (5) based on the sequence of images during a relative movement between the motor vehicle (1) and the target object (5), - detecting a stationary state, in which both the motor vehicle (1) and the target object (5) come to a standstill, - after detecting the stationary state, storing the current relative position of the target object (5) with respect to the motor vehicle (1), and - examining if a predetermined criterion with respect to the relative movement is satisfied, and after satisfaction of the predetermined criterion, continuing the tracking of the target object (5) starting from the stored relative position.