Upright Object Detection Using Road Plane Consistency Checks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advanced driver assistance systems (ADAS) and autonomous vehicle (AV) systems face challenges in accurately detecting upright objects, often mistakenly identifying steep graded roads as such due to their limited ability to differentiate between road environments and dynamic conditions, leading to false positive detections.
Innovation Solution
The system employs cameras and processing devices to analyze images, using a level road plane model to warp and track image patches, determining whether the detected object is more consistent with a road plane or an upright object model, thereby suppressing false positive detections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If preconfigured object classifiers are used to detect objects in the environment, then object detection capability is provided, but false positive detections occur when steep graded roads are mistakenly identified as upright objects
Solution Approach 1:
The detection process is segmented into multiple stages: initial object classification, road plane model fitting, and consistency verification. By dividing the detection pipeline into distinct segments, the system can identify and eliminate false positives caused by steep graded roads while maintaining detection of actual upright objects.
Solution Approach 2:
A road plane model is introduced as an intermediary verification step between image capture and final object detection. This mediator compares detected objects against the fitted road plane model to determine whether they represent actual upright objects or are artifacts of road gradient, thereby reducing false positive detections.
2Adaptability or versatility
If the system uses a single solution approach with preconfigured classifiers, then device complexity is minimized, but the system cannot adequately handle the infinitesimal variety and dynamic nature of road environments
Solution Approach 1:
The system dynamically adapts to varying road conditions by continuously fitting road plane models to current image data and adjusting detection thresholds based on detected road gradients. This dynamic adaptation allows the system to handle diverse and changing environmental conditions without requiring completely different detection strategies for each scenario.
Solution Approach 2:
The detection system changes parameters such as detection thresholds and classification criteria based on the fitted road plane model characteristics. When steep graded roads are detected, the system adjusts its parameters to prevent false positive upright object detections, thereby adapting to environmental variations while maintaining manageable system complexity.
Data Source
AI summary
Systems and methods are provided for augmenting upright object detection. In one implementation, a system for augmenting detection of objects in an environment of a vehicle may include at least one processing device. The at least one processing device may be programmed to: receive, from an image capture device, a first image frame, the first image frame including an attention area associated with a suspected upright object indication; warp, using a level road plane model, an area in a second earlier image frame that corresponds to the attention area; track a plurality of image patches across the warped area and the attention area; compute a road plane model fit to the tracked image patches; and determine whether to suppress the upright object indication based on the tracked image patches being more consistent with a road plane model than with an upright object model.