Moving Object Detection Distance Invariance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Moving object detection systems often misrecognize multiple objects as a single object when they have the same velocity, leading to inaccurate detection.

Innovation Solution

The system determines whether reflection points correspond to a single moving object by assessing the variability of the distance between specific reflective portions over time, using modules to calculate and evaluate scenarios where the distance is fixed or varies, and applying statistical methods to differentiate between single and multiple objects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If reflection points with substantially the same velocity are merged as a single moving object, then the number of detected objects is reduced, but different moving objects may be misrecognized as a single object

Engineering Contradiction:
Improvedetection accuracyVSAvoidobject differentiation precision
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent transitions from one-dimensional velocity-based merging to two-dimensional merging criteria by incorporating both velocity similarity and distance invariance. This dimensional expansion allows the system to distinguish between objects with same velocity but different spatial relationships, preventing misrecognition while maintaining accurate merging of true single objects.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The system continuously monitors the distance between reflection points over time and uses this feedback to determine whether to merge or separate objects. By evaluating whether the distance varies over time, the system dynamically adjusts its merging decisions, providing feedback-based control that improves both reliability and measurement precision.

Inventive Principle:
Principle #23Feedback

2Device complexity

If a region is defined and reflection points within the region are merged based on velocity similarity, then processing complexity is reduced, but misrecognition of multiple objects as single object increases

Engineering Contradiction:
Improveprocessing complexityVSAvoidobject identification reliability
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent performs preliminary velocity calculation for all reflection points and uses this pre-computed information to quickly identify candidate pairs for merging. This preliminary action reduces the search space and processing complexity while maintaining high reliability by ensuring that only velocity-similar points are considered for further distance-based evaluation.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically evaluates the distance between reflection points over time rather than using static regional grouping. This dynamic approach adapts to changing object configurations, maintaining high object identification reliability while managing processing complexity through efficient temporal comparison of distance metrics.

Inventive Principle:
Principle #15Dynamics

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

This approach reduces the occurrence of misrecognition, improving the accuracy of detecting moving objects by correctly identifying separate objects even when they have the same velocity.

Implementation Method 1

a radar device that transmits a radar wave and receives echoes that are generated based on the radar wave

Methodology Applied
Scientific EffectRadar: Radar

Implementation Method 2

receives echoes that are generated based on the radar wave

Methodology Applied
Scientific EffectEcho: Echo

Data Source

PatentUS9030349B2Moving object detection system
Publication Date: 2015.05.12 DENSO CORP
  • US9030349B2 patent drawing
  • US9030349B2 patent drawing
  • US9030349B2 patent drawing

AI summary

In a system, a detecting module cyclically detects positional information of reflection points of received echoes. A sampling module cyclically samples, from the detected reflection points for each cycle, first and second reflection points. The first and second reflection points are expected to be reflection points of the respective first and second reflective portions of a moving object in front of the system. A first determining module determines whether a distance between the first and second reflection points varies over time. A second determining module determines that the first and second reflection points correspond to reflection points of the respective first and second reflective portions of a single moving object when it is determined that the distance between the first reflection point and the second reflection point is substantially invariant over time.