Autonomous Driving Control Apparatus Using Moving Object Removal
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving control systems face challenges in processing images quickly enough to accurately recognize changes in vehicle position and nearby objects, leading to potential collisions due to degraded position recognition performance.
Innovation Solution
The system employs deep-learning to differentiate between fixed and moving objects within images, using feature points from fixed objects to recognize vehicle position and control driving, thereby improving processing speed and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the number of feature points in an image being processed increases, then the accuracy of position recognition is improved, but the image processing speed is slowed
Solution Approach 1:
The patent extracts and removes moving objects from the image before processing feature points. By separating moving objects (which cause positional changes) from the static background, the system can process fewer feature points while maintaining position recognition accuracy, thus resolving the contradiction between processing speed and recognition accuracy
Solution Approach 2:
The patent segments the image processing task into two distinct phases: first detecting and removing moving objects, then processing feature points on the remaining static background. This segmentation allows the system to reduce the number of feature points needed for accurate position recognition, improving processing speed without sacrificing accuracy
2Productivity
If the image processing speed is increased to maintain stable driving control, then the response time to position changes is improved, but the position recognition performance is degraded
Solution Approach 1:
By extracting and removing moving objects from the image before feature point processing, the system reduces computational complexity and increases processing speed. This allows the autonomous driving system to respond faster to position changes while maintaining accurate position recognition through processing of static background features
Data Source
AI summary
A vehicle according to the present disclosure includes a vehicle body, an image acquirer provided in the vehicle body and configured to acquire an image of a road and a surrounding of the road, and an autonomous driving control apparatus. The driving control apparatus is configured to receive a first image and a second image in real time from the image acquirer, detect a moving object in each of the first image and the second image, compare the first image from which the moving object is removed with the second image from which the moving object is removed to recognize a change in position of the vehicle body, and control driving of the vehicle based on the recognized change in position of the vehicle body.