Vehicle Object Tracking via Image Sub-Image Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing object tracking systems for vehicles face challenges in efficiently detecting and recognizing objects in real-time due to high computational demands and the inclusion of irrelevant objects, which affects driving safety.

Innovation Solution

An object tracking method that divides images into sub-images based on threshold conditions, excluding objects outside specific distance, height, and width ranges, using a monocular camera to calculate object dimensions and employing a strong classifier for accurate recognition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If object tracking is performed on the entire image, then detection accuracy is improved, but computation time increases

Engineering Contradiction:

Improvedetection accuracyVSAvoidcomputation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The image is divided into multiple sub-images based on distance ranges from the vehicle. The processing system selectively tracks objects only in relevant sub-images (e.g., medium and far distance sub-images) while excluding near distance sub-images where no target objects are expected. This segmentation approach maintains detection accuracy for relevant objects while significantly reducing computation time by avoiding processing of irrelevant image regions.

Inventive Principle:

Principle #1Segmentation

2Reliability

If all objects in the image are tracked, then detection completeness is improved, but computational power requirements increase

Engineering Contradiction:

Improvedetection completenessVSAvoidcomputational power requirements

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system extracts and processes only the relevant portions of the image that contain potential target objects. By using distance threshold conditions to identify and exclude near distance sub-images where vehicles and pedestrians are not present, the system reduces computational power requirements while maintaining detection completeness for actual targets of interest.

Inventive Principle:

Principle #2Taking out (Extraction)

3Adaptability or versatility

If irrelevant objects are included in tracking, then coverage is improved, but detection accuracy for relevant objects deteriorates

Engineering Contradiction:

ImprovecoverageVSAvoiddetection accuracy for relevant objects

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

Different quality levels of processing are applied to different regions of the image based on their relevance to the detection task. Relevant sub-images (medium and far distance) receive full processing attention with high computational resources, while irrelevant sub-images (near distance) are excluded from processing. This local quality approach improves detection accuracy for relevant objects by concentrating computational resources where they are most needed.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS11482013B2Object tracking method, object tracking apparatus, vehicle having the same, and computer-program product

Publication Date: 2022.10.25 BEIJING BOE TECH DEV CO LTD

AI summary

The present application provides an object tracking method. The object tracking method includes obtaining an image of an area in front of a vehicle; dividing the image of the area in the front of the vehicle into a plurality of sub-images; determining a plurality of first sub-images that satisfy a plurality of threshold conditions out of the plurality of sub-images; selecting a plurality of target sub-images out of the plurality of first sub-images, at least one of the plurality of first sub-images is not selected as one of the plurality of target sub-images; and recognizing a target object in one of the plurality of target sub-images.