Vehicle Object Detection Depth Estimation and Cryptographic Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing object recognition systems in vehicles struggle to differentiate between true objects and false objects, such as projected images of objects, which can lead to incorrect vehicle operations and safety issues.
Innovation Solution
The system employs a combination of computer vision and cryptography to verify the authenticity of detected objects. It uses convolutional neural networks to estimate the depth of objects and determine if they are projected images. Additionally, a cryptography-based traffic sign verification system secures and authenticates traffic sign data transmitted to vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If computer vision systems are used to detect objects, then object detection capability is improved, but the system cannot distinguish between real objects and projected fake objects
Solution Approach 1:
The patent introduces depth estimation as an intermediary verification layer between object detection and decision-making. The system first detects objects using computer vision, then estimates their depth using neural networks, and only then makes decisions. This intermediary depth verification step blocks fake projected objects that lack true depth information, resolving the contradiction between detection capability and authenticity verification.
2Reliability
If depth estimation is added to verify object authenticity, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent replaces complex multi-camera mechanical depth sensing systems with a single camera combined with neural network-based depth estimation. Instead of using multiple physical sensors to capture depth information, the system uses a trained neural network to estimate depth from standard 2D images, significantly reducing hardware complexity while maintaining reliability.
3Reliability
If cryptographic verification is implemented for traffic signs, then security is improved, but processing time increases
Solution Approach 1:
The patent implements preliminary cryptographic signing of traffic sign data at the source (traffic light controller) before transmission to vehicles. This allows receiving vehicles to perform fast verification using pre-shared keys without requiring complex real-time cryptographic operations, thus improving security while minimizing verification time.
Data Source
AI summary
Examples are provided for object detection systems for vehicles. In one example, a system for a vehicle includes an image sensor, a processor, and a storage device storing instructions executable by the processor to capture, via the image sensor, an image of an environment of the vehicle, detect an object in the image of the environment of the vehicle, determine whether the object is a projected image of the object, and selectively control one or more vehicle systems of the vehicle to perform one or more actions if the object is not the projected image.