Solid Object Detection Using Masked Subtracted Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The detection precision of solid objects around a traveling vehicle is impaired by shadows from structures like buildings or traffic signals, which can be mistaken for the actual objects due to relative movement.
Innovation Solution
A solid object detection device and method that transforms and aligns overhead view images taken at different times, generates a subtracted image to highlight object positions, and uses masked images to isolate and specify object locations by masking regions other than candidate object areas, employing threshold values in histograms to accurately identify object positions and regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If overhead view images are transformed and subtracted to detect solid objects, then detection capability is improved, but detection precision deteriorates due to shadow interference
Solution Approach 1:
The detection process is segmented into multiple stages: initial subtracted image generation, shadow region identification through histogram analysis, masked subtracted image generation excluding shadow regions, and final solid object detection. This segmentation allows the system to handle shadow interference systematically by isolating and excluding shadow regions before final detection.
Solution Approach 2:
A masked subtracted image is introduced as an intermediary between the initial subtracted image and the final detection result. This intermediate representation excludes shadow regions identified through histogram analysis, thereby eliminating shadow interference before solid object detection is performed on the cleaned image.
2Loss of information
If shadow regions are included in subtracted images, then image data completeness is maintained, but detection accuracy decreases
Solution Approach 1:
Shadow regions are extracted and removed from the subtracted image through histogram-based analysis. The system identifies shadow regions by analyzing pixel value distributions and generates a masked subtracted image that excludes only the shadow portions while retaining all other image data, thereby maintaining data completeness for non-shadow regions.
Solution Approach 2:
The masking operation applies local quality differentiation by selectively removing shadow regions while preserving other regions. The histogram analysis identifies specific local areas containing shadows, and masking is applied only to those local regions, maintaining high-quality image data in non-shadow areas for accurate object detection.
Data Source
AI summary
A solid object detection device includes an overhead view transformation processing unit transforming first and second photographed images photographed by a camera at different timings in travel of a vehicle into first and second overhead view images, respectively, a subtracted image generation unit generating a subtracted image between the first and second overhead view images whose photographing positions are aligned with each other, a solid object position specification unit specifying a position of a solid object present around the vehicle based on the subtracted image, and a masked subtracted image generation unit generating a masked subtracted image in which a region other than a solid object candidate region as a candidate where the solid object appears in the subtracted image is masked and the solid object position specification unit specifies a position of the solid object in the subtracted image based on the masked subtracted image.