Dynamic Label Placement on Photographic Images

Solution Overview

Problem

Conventional systems for displaying photographic images of geolocations often obstruct the image content with labels, interfering with the user's viewing experience, as labels are typically placed directly on objects or at fixed offsets, rather than considering the image context.

Innovation Solution

The system analyzes photographic images to determine optimal placement positions for labels based on the image content, such as the top or bottom, or on objects like roads or skies, ensuring that labels do not obstruct important features, using a combination of image analysis and user data to select and position advertisements and labels dynamically.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If labels are placed directly on objects or at fixed offsets, then label information is easily accessible, but the image content is obstructed and user viewing experience deteriorates

Engineering Contradiction:

Improvelabel information accessibilityVSAvoidimage content obstruction

Core Design Contradiction:

Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent applies local quality by analyzing different regions of the image to identify areas with specific characteristics (e.g., sky regions, road areas, empty spaces) and placing labels in locations that match the appropriate region type. This ensures labels are positioned in areas that are less likely to obstruct important visual content while maintaining information accessibility.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent transitions from traditional 2D label placement on the image plane to 3D spatial positioning by detecting objects in the image and placing labels in three-dimensional space relative to those objects. This allows labels to be positioned above, below, or beside objects rather than directly on them, reducing obstruction while maintaining association.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Object-affected harmful factors

If labels are placed to avoid obstructing objects, then image viewing experience is improved, but label placement complexity increases

Engineering Contradiction:

Improveimage content obstructionVSAvoidlabel placement processing

Core Design Contradiction:

Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The patent performs preliminary actions by pre-processing the image to detect objects, determine their boundaries, and identify suitable placement regions before label placement. This includes pre-identifying sky areas, road regions, and empty spaces, which simplifies the subsequent label positioning process and reduces real-time computational complexity.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system employs self-service mechanisms by using automated image analysis algorithms that independently identify placement regions and position labels without requiring manual intervention. The system analyzes image characteristics, detects objects, and autonomously determines optimal label positions based on predefined criteria.

Inventive Principle:

Principle #25Self-service

3Loss of information

If advertisements are displayed on photographic images, then user engagement and information delivery are enhanced, but the clarity and integrity of the image presentation deteriorates

Engineering Contradiction:

Improveinformation delivery effectivenessVSAvoidimage clarity and integrity

Core Design Contradiction:

Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent applies local quality by analyzing different regions of the image to identify areas with specific characteristics (e.g., sky regions, road areas, empty spaces) and placing labels in locations that match the appropriate region type. This ensures labels are positioned in areas that are less likely to obstruct important visual content while maintaining information accessibility.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent transitions from traditional 2D label placement on the image plane to 3D spatial positioning by detecting objects in the image and placing labels in three-dimensional space relative to those objects. This allows labels to be positioned above, below, or beside objects rather than directly on them, reducing obstruction while maintaining association.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS10445772B1Label placement based on objects in photographic images

Publication Date: 2019.10.15 GOOGLE LLC

AI summary

Aspects of the disclosure relate to placing labels on photographic images so as not to obstruct a particular object. An image associated with a geolocation is identified, where the geolocation is based on a user action. The image is analyzed to identify at least first and second objects within the image. Object types for each object are determined. A determination is made that the first object is to be annotated with a label according to the first object type, and that the first and second object types differ. The image is also analyzed to determine a position on the second object to place the label so that the label does not obstruct the first object. Based on this analysis, the label is placed on the second object without obstructing the first object.