Vehicle Distance Histogram Tracking for Crossing Objects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image processing techniques for tracking crossing objects, such as vehicles or pedestrians, using optical flow methods require significant computational resources, making it challenging to achieve real-time processing and are inefficient due to the need to account for changes in size and movement in both horizontal and vertical directions.
Innovation Solution
An image processing apparatus that generates distance histograms and edge histogram data, allowing for the calculation of object movement by comparing past and current edge histogram data, thereby reducing computational load and enhancing real-time tracking capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If optical flow analysis is used to track crossing objects, then tracking accuracy is improved, but computational load increases significantly
Solution Approach 1:
The patent segments the complex optical flow analysis into distinct functional modules: a distance histogram generation unit that processes depth information, an edge histogram extraction unit that identifies object boundaries, and a movement amount calculation unit that computes displacement. This segmentation allows each module to handle specific computational tasks efficiently, reducing overall computational load while maintaining tracking accuracy.
Solution Approach 2:
The patent extracts only the essential features needed for tracking—distance histograms and edge histograms—from the full image data. By taking out and processing only these critical elements rather than performing complete optical flow analysis on all pixels, the system significantly reduces computational requirements while preserving the ability to accurately track crossing objects.
2Reliability
If complete optical flow analysis is performed to account for size and movement changes, then tracking reliability is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary actions by pre-computing and storing distance histograms and edge histograms for each frame before full tracking analysis is needed. These pre-processed features are stored in memory and can be quickly retrieved and compared for movement calculation, eliminating the need to re-process raw image data during tracking and significantly reducing processing time while maintaining reliability.
Solution Approach 2:
The patent changes the parameter representation from raw pixel data to histogram-based features (distance histograms and edge histograms). This parameter transformation allows the system to capture essential object characteristics in a compressed format that requires less computational processing for comparison and analysis, thereby reducing processing time while preserving tracking reliability.
3Measurement precision
If detailed distance data is processed for each pixel, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent merges the processing of distance information from multiple pixels into a single distance histogram representation. By combining individual pixel distance measurements into a consolidated histogram that shows the distribution of distances across the image, the system maintains precise distance measurement capabilities while significantly simplifying the data structure and reducing processing complexity.
Solution Approach 2:
The patent transforms the two-dimensional spatial data into a one-dimensional histogram representation. By converting pixel coordinates and distance values into a histogram where the x-axis represents distance and the y-axis represents frequency, the system preserves measurement precision while reducing the dimensional complexity of the data, making it easier to process and compare across frames.
Data Source
AI summary
An image processing apparatus includes a distance histogram generator, a computation processor, an extractor, and a movement amount calculator. The distance histogram generator generates, for each horizontal angle of view of an imaging unit mounted on a vehicle, a distance histogram based on distance data of a distance image captured by the imaging unit. The distance image has a pixel value corresponding to a distance to a crossing object in captured images of the front of a vehicle. The computation processor computes edge histogram data for each distance histogram. The extractor extracts, from the edge histogram data computed in the past, any edge histogram data matching with the edge histogram data computed latest. The movement amount calculator calculates a movement amount of the object in a vehicle width direction, based on a difference between the extracted edge histogram data computed in the past and the edge histogram data computed latest.