Object Recognition Device Subregion Feature Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object recognition techniques that use two light beams to generate distance images increase processing load, as they require executing recognition processes on both reflected light images, which can be computationally intensive.
Innovation Solution
An object recognition device that divides reflection intensity and background light images into subregions, calculates feature amounts for each subregion, and selects the data with higher recognition ease, minimizing the processing load by configuring overall image data from selected partial image data pieces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If recognition processes are executed on both reflected light images, then object recognition accuracy is improved, but processing load increases
Solution Approach 1:
The image is divided into multiple subregions, and feature amounts are calculated separately for each subregion. This segmentation allows the system to process only relevant portions of the image with high computational detail, while maintaining overall recognition accuracy without executing full recognition processes on entire images.
Solution Approach 2:
Different processing strategies are applied to different subregions based on their characteristics. The system calculates feature amounts for subregions and selectively processes only those that contribute most to recognition accuracy, rather than uniformly processing all image data at full computational intensity.
2Reliability
If feature amount calculation is performed for all subregions of both reflection intensity image and background light image, then recognition completeness is improved, but computational requirements increase
Solution Approach 1:
The system performs feature amount calculation on subregions of both reflection intensity image and background light image, but then selectively uses only the necessary results. By calculating features for all subregions but strategically selecting which ones to use in final recognition, the system maintains completeness while controlling computational expenditure.
Solution Approach 2:
The system extracts and utilizes only the essential feature amounts from the calculated subregions. After computing features for multiple subregions, the system identifies and extracts only those feature amounts that are most critical for accurate object recognition, discarding redundant computational results.
Data Source
AI summary
An object recognition device of the present disclosure divides a reflection intensity image and a background light image acquired from a light sensor into the same number of subregions. The object recognition device calculates a feature amount for partial image data of each of the subregions of the reflection intensity image and partial image data of each of the subregions of the background light image that have been divided. The object recognition device compares the feature amounts calculated for the partial image data of the reflection intensity image and the partial image data of the background light image in the same one of the subregions and selects the feature amount with which an object is more easily recognized as the selected partial image data. The object recognition device recognizes the object based on overall image data configured by the selected partial image data pieces that have been selected.