Image Processor Depth-Based Template Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In environments with numerous objects, accurately identifying and tracking a desired target in a three-dimensional space is challenging due to factors like changing light sources and high processing loads, leading to delayed response times.

Innovation Solution

An image processor that acquires depth images to determine object distances and adjusts template image sizes based on these distances, enabling efficient matching and position detection of targets within the three-dimensional space.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If template matching is performed at high spatial resolution for accurate target detection, then detection precision improves, but processing load increases and response time deteriorates

Engineering Contradiction:
Improvetarget detection precisionVSAvoidprocessing speed
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent divides the image processing into multiple stages: first performing template matching at low resolution to identify candidate regions, then refining detection at high resolution only in those specific regions. This segmentation allows accurate target detection while reducing overall processing load by avoiding full high-resolution processing.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces depth information as an additional dimension to create a three-dimensional search space. By using depth maps and performing matching in 3D space rather than 2D, the system can more accurately identify targets and reduce false positives, improving detection precision without proportionally increasing processing complexity.

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

2Measurement precision

If template matching is performed across the entire image at high resolution, then target detection accuracy improves, but processing time increases

Engineering Contradiction:
Improvetarget detection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary template matching at low resolution before conducting high-resolution matching. This preliminary action identifies candidate regions where targets are likely to be located, allowing the system to skip high-resolution processing in regions where no targets exist, thereby reducing total processing time while maintaining detection accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent applies different processing qualities to different regions of the image: low resolution for most areas and high resolution only for candidate regions identified by the preliminary low-resolution matching. This local quality approach ensures accurate detection where needed while minimizing processing time in other areas.

Inventive Principle:
Principle #3Local quality

3Measurement precision

If depth information is utilized for three-dimensional target detection, then detection accuracy in complex environments improves, but device complexity increases

Engineering Contradiction:
Improvedetection accuracyVSAvoidprocessing system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent uses depth maps as an intermediary data structure that simplifies three-dimensional target detection. By representing depth information as a 2D map with depth values, the system can perform 3D matching operations without requiring complex three-dimensional processing hardware, thus improving detection accuracy while managing device complexity.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS9542755B2Image processor and image processing method
Publication Date: 2017.01.10 SONY INTERACTIVE ENTERTAINMENT LLC
  • US9542755B2 patent drawing
  • US9542755B2 patent drawing
  • US9542755B2 patent drawing

AI summary

An image acquisition section of an information processor acquires stereo images from an imaging device. An input information acquisition section acquires an instruction input from a user. A depth image acquisition portion of a position information generation section generates a depth image representing a position distribution of subjects existing in the field of view of the imaging device in the depth direction using stereo images. A matching portion adjusts the size of a reference template image in accordance with the position of each of the subjects in the depth direction represented by the depth image first, then performs template matching on the depth image, thus identifying the position of a target having a given shape and size in the three-dimensional space. An output information generation section generates output information by performing necessary processes based on the target position.