Real-time Video Annotation for Driver Action Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for training human assistive products, such as those in automobiles, are laborious and costly as they require manual labeling of training instances, which is time-consuming and inefficient.

Innovation Solution

A system that automatically annotates real-time video images based on detected human actions in environmental situations, allowing for quick and inexpensive data collection and labeling by monitoring user responses to environmental stimuli, such as vehicle control actions, and using this data to train user assistive products.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual labeling of training instances is used, then training data can be obtained, but the process becomes laborious and time-consuming

Engineering Contradiction:
Improveannotation accuracyVSAvoidlabeling time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-service by automatically generating annotations through machine learning models that analyze environmental situations and predict appropriate user responses, eliminating the need for manual human labeling while maintaining annotation quality

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual labeling process with an automated computational system that uses environmental data, user response monitoring, and machine learning algorithms to generate annotations automatically

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If manual labeling of training instances is used, then training data can be obtained, but the process becomes cost intensive

Engineering Contradiction:
Improveannotation accuracyVSAvoidtraining cost
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The system performs self-service by automatically generating annotations through machine learning models that analyze environmental situations and predict appropriate user responses, eliminating the need for manual human labeling while maintaining annotation quality

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent employs cost-effective computational resources and algorithms that can be rapidly deployed and replaced, substituting expensive manual human labor with more economical automated processing systems

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

3Productivity

If automated annotation based on user response monitoring is implemented, then labeling efficiency improves, but system complexity increases

Engineering Contradiction:
Improveannotation efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system achieves multi-functionality by integrating environmental monitoring, user response tracking, action determination, and automatic annotation generation into a single unified platform that serves multiple purposes simultaneously

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces an intermediary environment manager that coordinates between various system components including sensors, user response monitors, and annotation generators, simplifying the overall system architecture through a central coordinating layer

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS8494223B2Real-time annotation of images in a human assistive environment
Publication Date: 2013.07.23 HYUNDAI MOTOR CO LTD
  • US8494223B2 patent drawing
  • US8494223B2 patent drawing
  • US8494223B2 patent drawing

AI summary

A method, information processing system, and computer program storage product annotate video images associated with an environmental situation based on detected actions of a human interacting with the environmental situation. A set of real-time video images are received that are captured by at least one video camera associated with an environment presenting one or more environmental situations to a human. One or more user actions made by the human that is associated with the set of real-time video images with respect to the environmental situation are monitored. A determination is made, based on the monitoring, that the human driver has one of performed and failed to perform at least one action associated with one or more images of the set of real-time video images. The one or more images of the set of real-time video images are annotated with a set of annotations.