Vehicle Object Recognition with Concave-Section Cluster Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object recognition devices erroneously recognize multiple objects as a single object when they are close to each other due to the formation of a single cluster point group, especially when the outer shape of the objects has a concave section.
Innovation Solution
An object recognition device for vehicles that forms cluster point groups and includes a unit to divide these groups into quasi-cluster point groups based on concave sections, using reflecting points of interest extracted at varying ratios depending on the distance from the vehicle, and recognizes each quasi-cluster point group as a separate object.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If clustering is performed for a plurality of reflecting points to form cluster point groups, then object recognition can be achieved, but multiple objects close to each other are erroneously recognized as one object
Solution Approach 1:
The patent divides a cluster point group into multiple sub-cluster point groups by detecting concave sections in the outer shape of the upper surface. This segmentation allows multiple objects that were previously merged into one cluster to be separated into distinct groups, thereby improving object separation precision while maintaining reliable object recognition
Solution Approach 2:
The patent introduces a new dimension for object separation by analyzing the outer shape of the upper surface in the horizontal plane (XY plane). By examining the two-dimensional projection and detecting concave sections, the system can distinguish between multiple objects without requiring additional spatial dimensions, thus improving measurement precision in the existing dimensional space
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This configuration allows accurate identification of multiple objects as separate entities by correctly distinguishing concave sections in the object's outer shape, reducing erroneous recognition.
Implementation Method 1
a plurality of reflecting points specified by radiating transmission waves in a plurality of irradiation directions and receiving reflected waves of the transmission waves
Data Source
AI summary
An object recognition device to be mounted to a vehicle includes a cluster point group formation unit and an object recognition unit. The cluster point group formation unit is configured to form a cluster point group by executing clustering for a plurality of reflecting points. The object recognition unit recognizes the cluster point group as an object. The object recognition unit is configured to, in response to determining that an outer shape of an upper surface that is an outer shape of the recognized object viewed from the top has a concave section when viewed from a vehicle side, divide the cluster point group into a plurality of quasi-cluster point groups based on a position of the concave section and recognizes each of the plurality of quasi-cluster point groups as an object.