Object Feature Compression for Faster Multichannel Video Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing surveillance systems face challenges in efficiently searching multi-channel videos due to the large amount of data required for storing object features, leading to slow searches and the need for extensive databases.
Innovation Solution
A video search device and method that utilizes feature information of objects detected in videos, generating final object information with reduced attributes for faster searches, and storing this information in a database along with temporary object information for future interest, allowing users to search by object features, channel numbers, and time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If feature information on objects is extracted and stored for each multi-channel video, then search capability is improved, but database size increases and search speed decreases
Solution Approach 1:
The patent extracts only the most essential feature information from video content, storing minimal necessary attributes rather than complete video data. This selective extraction reduces database size while maintaining search functionality by capturing key identifying characteristics of objects in videos.
Solution Approach 2:
The patent applies different storage strategies to different types of data: essential feature information is stored in a compressed format for quick access, while temporary object information is stored with lower priority. This differential quality approach optimizes the balance between search capability and database size.
2Ease of operation
If feature information on objects is extracted and stored for each multi-channel video, then search capability is improved, but search speed becomes very slow
Solution Approach 1:
The patent segments object information into two categories: final object information (high similarity, essential features) and temporary object information (low similarity, less critical features). This segmentation allows the system to prioritize searching through final object information first, significantly improving search speed by avoiding exhaustive searches through all possible data.
Solution Approach 2:
The patent assigns different quality levels to different types of stored information, with final object information receiving higher priority for storage and retrieval. This quality differentiation ensures that the most search-relevant data is readily accessible while maintaining overall system efficiency.
3Measurement precision
If all attribute items are stored in final object information, then search accuracy is improved, but database size increases
Solution Approach 1:
The patent extracts and stores only the number of attribute items that exceed a predetermined threshold in final object information, rather than storing all possible attributes. This selective extraction maintains search accuracy for critical features while reducing database size by excluding less important attributes.
Solution Approach 2:
The patent changes the parameter of attribute storage by using a dynamic threshold mechanism. When the number of matching attribute items exceeds the threshold, the information is stored in final object information; otherwise, it is stored as temporary object information. This parameter-based approach optimizes the balance between search accuracy and database size.
Data Source
AI summary
Disclosed herein is a video search device comprising: at least one processor configured to implement an updating unit generating event object information based on feature information on an object detected in a video; and a storage configured to store comparison object information containing feature information on a reference object, wherein the processor is further configured to implement: an object information generating/deleting unit configured to create information on an object having a predetermined degree of similarity between the event object information and the comparison object information as final object information, and storing the final object information in the storage; and a data searching unit searching the final object information for data that satisfies a search criterion entered by a user.