Vehicle Object Detection Using Horizontal Edge Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional object detection systems face challenges in accurately detecting vehicles while minimizing processing time, often leading to incorrect detection of structures and road signs due to reliance on edge detection and lengthy comparison processes.

Innovation Solution

An object detection device that extracts horizontal edges and sets a recognition region based on specific horizontal edges, using characteristic points to group and correct the edge narrowing-down region, thereby improving detection accuracy and reducing processing time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If edge detection is used to detect objects, then detection speed is improved, but detection accuracy deteriorates causing incorrect detection of structures and road signs

Engineering Contradiction:

Improvedetection speedVSAvoiddetection accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent segments the detection process into multiple stages: first extracting horizontal edges specifically, then performing template matching only in regions containing these horizontal edges. This segmentation allows the system to maintain fast processing while improving accuracy by focusing computational resources on relevant areas.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent applies different processing qualities to different regions of the image. Template matching is performed only in regions containing horizontal edges, while other regions are processed more simply. This local quality approach improves detection accuracy for vehicles (which have horizontal edges) without unnecessarily processing entire images, thus maintaining speed.

Inventive Principle:

Principle #3Local quality

2Measurement precision

If template matching is performed on all image regions, then detection accuracy is improved, but processing time increases

Engineering Contradiction:

Improvedetection accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary horizontal edge extraction before template matching. This preliminary action creates a filter that identifies regions likely to contain vehicles, allowing template matching to be applied only to these pre-selected regions rather than the entire image, thus reducing processing time while maintaining accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Instead of performing template matching on all possible regions (excessive action), the patent applies it only to regions containing horizontal edges (partial action). This partial application is sufficient to achieve accurate vehicle detection while significantly reducing the computational burden and processing time.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS10325171B2Object detection device, driving assistance device, object detection method, and object detection program

Publication Date: 2019.06.18 HONDA MOTOR CO LTD

AI summary

An object detection device includes: an imaging unit configured to image the surroundings of a vehicle; a horizontal edge extraction unit configured to extract horizontal edges that are characteristic lines of approximately horizontal direction components in a search region of an image captured by the imaging unit; and a detection object recognition unit configured to recognize a detection object within a recognition region set on the basis of, among the horizontal edges extracted by the horizontal edge extraction unit, a specific horizontal edge satisfying a predetermined condition.