Marker Detection Load Reduction via Sub-identifier Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As the number of markers increases for identifying objects, the load of the marker detection process from a camera image also increases, leading to higher computational demands and inefficiencies, particularly when using template matching for 1,000 or more unique markers.
Innovation Solution
An information processing apparatus and method that detects multiple markers from an image, converts them into sub-identifiers, and computes a single identifier by combining these sub-identifiers, reducing the number of markers required for identification and thus the detection load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If template matching is used to detect each of 1,000 marker types, then identification accuracy is maintained, but processing time and computational load increase significantly
Solution Approach 1:
The patent segments the marker detection process into two distinct phases: (1) a preprocessing phase that extracts feature values from template images and stores them in a lookup table, and (2) a detection phase that rapidly compares captured marker images against the pre-computed feature values. This segmentation eliminates redundant computations during real-time detection, significantly reducing processing time while maintaining detection accuracy.
Solution Approach 2:
The patent performs preliminary computation of feature values from template images before actual marker detection begins. By pre-calculating and storing feature values for all 1,000 marker types in a lookup table, the system prepares all necessary comparison data in advance, allowing rapid identification during detection without repeating computationally intensive template matching operations.
2Adaptability or versatility
If the number of marker types increases to identify more objects, then identification capability improves, but detection process complexity increases
Solution Approach 1:
The patent changes the parameter representation from storing complete template images to storing extracted feature values. This parameter transformation reduces the dimensionality and complexity of the data that must be processed and stored, allowing the system to handle 1,000 marker types efficiently without proportionally increasing detection process complexity.
3Measurement precision
If template matching is performed for each marker type, then accurate marker identification is achieved, but computational energy consumption increases
Solution Approach 1:
The patent extracts essential feature values from complete template images and uses only these extracted features for comparison during detection. By taking out only the necessary discriminatory features rather than processing entire images, the system maintains identification accuracy while dramatically reducing computational energy requirements.
Data Source
AI summary
An information processing apparatus (2000) includes a conversion unit (2020) and a computation unit (2040). The conversion unit (2020) detects a plurality of markers from a camera image (10). The conversion unit (2020) converts the detected markers into corresponding sub-identifier information. The computation unit (2040) computes an identifier using a plurality of sub-identifiers converted by the conversion unit (2020).