Autonomous Vehicle Object Detection Using FOV Crop and Downsampling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In the field of machine vision for autonomous vehicles, existing object detection methods face challenges due to high computational requirements, which necessitate downsampling of images, reducing detection accuracy and range.
Innovation Solution
A method that involves cropping a high-resolution field of view and downsampling the remaining image, allowing for simultaneous processing by a detector to enhance object detection accuracy and range while maintaining low computational resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high resolution images are used for object detection, then detection accuracy and range are improved, but computational requirements increase
Solution Approach 1:
The patent divides the image processing task into two segments: a first downscaled image for detecting distant objects and a second cropped image for detecting closer objects. This segmentation allows the system to process different regions of the scene at different resolutions, improving overall detection accuracy while managing computational resources efficiently. The detector processes both images and combines their results to achieve accurate object detection across various distances.
2Productivity
If images are downsampled to reduce computational load, then processing speed increases, but detection range decreases
Solution Approach 1:
The patent introduces a spatial dimension solution by creating two images with different field of view characteristics. The first downscaled image maintains a wide field of view for detecting distant objects, while the second cropped image provides a zoomed-in view for closer objects. This dimensional approach allows the system to extend detection range beyond what a single downsampled image could achieve, while still maintaining processing speed through selective downsampling.
3Measurement precision
If high resolution images are processed, then object detection fidelity is improved, but processing time increases
Solution Approach 1:
The patent applies partial action by selectively downsampling only the portions of the scene that require it. Instead of processing the entire high-resolution image, the system creates a downscaled version for distant object detection and a cropped version for closer objects. This partial processing approach maintains detection fidelity for objects in both distance ranges while significantly reducing overall processing time compared to processing the full high-resolution image.
Data Source
AI summary
Systems and methods for enhanced object detection for autonomous vehicles based on field of view. An example method includes obtaining an image from an image sensor of one or more image sensors positioned about a vehicle. A field of view for the image is determined, with the field of view being associated with a vanishing line. A crop portion corresponding to the field of view is generated from the image, with a remaining portion of the image being downsampled. Information associated with detected objects depicted in the image is outputted based on a convolutional neural network, with detecting objects being based on performing a forward pass through the convolutional neural network of the crop portion and the remaining portion.