Image Recognition Apparatus for Vehicle Window Glass
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image recognition apparatuses experience a significant reduction in frame rate when a wiper is operating, particularly in rainy weather, due to the interference of wiper and rain-related substances on the window glass.
Innovation Solution
An image recognition apparatus that divides frame images into multiple areas and performs object recognition and tracking only on areas where the wiper and attached substances do not appear, using a wiper operation acquisition function, rainy weather determination, execution-in-each-area determination, object recognition, object tracking, and object position prediction functions to maintain frame rate and prevent erroneous tracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If object recognition is performed on all frame images when wiper is operating, then measurement precision is improved, but productivity deteriorates due to significant frame rate reduction
Solution Approach 1:
The frame image is divided into multiple regions, and the determinator evaluates each region separately to determine whether the wiper or attached substances appear. This segmentation allows the system to process only the necessary portions of the image, maintaining object detection accuracy while improving frame rate by avoiding unnecessary processing of regions affected by wiper interference.
2Measurement precision
If wiper operation is detected and frame images are discarded, then measurement precision is improved by avoiding erroneous detection, but productivity deteriorates due to loss of usable frame images
Solution Approach 1:
Instead of discarding entire frame images when wiper operation is detected, the system applies local quality assessment by determining whether the wiper or attached substances appear in each specific region of the frame image. This allows the system to utilize frame images for object detection in regions not affected by wiper interference, thereby maintaining tracking accuracy while maximizing the number of usable frames.
3Productivity
If object detection is performed in all regions including those with wiper, then productivity is improved by processing all frames, but measurement precision deteriorates due to erroneous detection from wiper interference
Solution Approach 1:
The frame image is divided into multiple regions, and the determinator evaluates each region separately to determine whether the wiper or attached substances appear. This segmentation enables the system to maintain high processing throughput by quickly identifying and excluding only the specific regions affected by wiper interference, while performing accurate object detection in the remaining clean regions.
Solution Approach 2:
The system applies local quality assessment by determining whether each region contains the wiper or attached substances. This allows the system to maintain high processing throughput by processing only the necessary portions of each frame image, while ensuring detection accuracy by excluding regions with wiper interference from object detection.
Data Source
AI summary
An image recognition apparatus is provided with: a divider configured to divide a frame image into a plurality of areas, wherein the frame image is obtained by imaging or capturing a scene outside through a window glass on which a wiper is mounted, from an interior of a moving body; a determinator configured to determine whether or not at least one of the wiper and an attached substance to the window glass appears, for each of the plurality of areas; an object detector configured to detect an object included in such an area of the plurality of areas that it is determined that the wiper and the attached substance do not appear; and a tracking device configured to track a tracking target, which is an object included in two or more frame images, on the basis of a detection result of the object detector.