Database Object Recognition via Parallel Template Comparison

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing object recognition systems in video and image analysis are inefficient as they require reloading data and lack parallel processing capabilities, making them slow and resource-intensive.

Innovation Solution

Implementing a database comparison operation that executes user-defined functions to store and compare object templates within a database system, utilizing parallel processing to identify objects by comparing stored templates to a target template, allowing for efficient object recognition without reloading data and enabling simultaneous comparison of multiple data sets.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If traditional object recognition systems reload data for each comparison operation, then data can be accessed for analysis, but the system becomes slow and resource-intensive

Engineering Contradiction:

Improveobject recognition speedVSAvoidsystem resource consumption

Core Design Contradiction:

SpeedVSUse of energy by moving object

Solution Approach 1:

The patent applies preliminary action by pre-loading object data into the database system before comparison operations are needed. The database engine maintains data in memory, eliminating the need to reload data for each comparison operation. This pre-positioning of data resolves the contradiction by enabling fast access (improving speed) while avoiding repeated data loading (reducing resource consumption).

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements universality by creating a multi-functional database system that simultaneously performs data storage, data management, and parallel comparison operations. The database engine serves multiple functions: storing object data, managing data access, and executing parallel template comparisons. This consolidation improves recognition speed while optimizing resource utilization through unified data management.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Productivity

If sequential processing is used for object template comparisons, then system complexity remains low, but processing speed decreases

Engineering Contradiction:

Improveobject identification throughputVSAvoidparallel processing complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent applies copying by creating multiple copies of the database engine or comparison processing units that can operate simultaneously. Each processing unit can compare templates in parallel without interfering with others. This copying approach enables high-throughput object identification while managing complexity through standardized, replicated processing units rather than complex sequential logic.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent implements segmentation by dividing the comparison task into multiple independent parallel operations. The database system segments the workload into simultaneous template comparisons that can be executed concurrently. This segmentation increases identification throughput while keeping individual processing units relatively simple, resolving the contradiction between productivity and device complexity.

Inventive Principle:

Principle #1Segmentation

3Loss of time

If data is stored externally and loaded for analysis, then data storage is efficient, but analysis speed decreases due to data reloading

Engineering Contradiction:

Improvedata access timeVSAvoidmemory resource usage

Core Design Contradiction:

Loss of timeVSQuantity of substance

Solution Approach 1:

The patent applies preliminary action by pre-positioning data in the database system's memory storage before it is needed for comparison operations. This eliminates data access time by having data ready in advance, while the database's memory management optimizes the quantity of memory used through efficient data structures and caching strategies.

Inventive Principle:

Principle #10Preliminary action

4Ease of operation

If specialized object recognition software is used outside the database, then recognition algorithms can be flexible, but integration complexity increases

Engineering Contradiction:

Improveobject recognition accessibilityVSAvoidsystem integration complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The patent applies merging by combining object recognition capabilities directly within the database system. The comparison functions are integrated into the database engine, allowing users to perform object recognition through standard database operations. This merging improves ease of operation by using familiar database interfaces while reducing integration complexity by eliminating the need for separate software systems and their associated integration layers.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS10956493B2Database comparison operation to identify an object

Publication Date: 2021.03.23 ROCKET SOFTWARE

AI summary

Examples disclosed herein relate to a database comparison operation to identify an object. For example, a processor may enroll a set of object templates in a storage based on objects within input content and enroll a target object template in the storage based on a target object in target content. The processor may identify an object within the input content associated with the target object based on a database comparison operation of the stored set of object templates to the stored target object template. The processor may output object recognition information related to the identified object.