Edge Computing for Trajectory-Based Object Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion tracking technologies face challenges such as inaccuracy in tracking complex movements or occlusions, latency in tracking information, and reliance on significant computing power, as well as the inability to seamlessly filter information based on user preferences.
Innovation Solution
A system that uses edge computing to process and analyze object data, allowing for real-time identification and tracking of moving objects. This system receives user requests including geographic regions or time periods of interest, identifies video-derived object trajectories, and selects preview images using a ranking algorithm to display relevant events to the user.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If motion tracking is performed using traditional centralized computing, then comprehensive tracking information can be collected, but latency increases and processing speed decreases
Solution Approach 1:
The patent segments the centralized computing system into distributed edge computing nodes deployed across multiple locations. Each edge node independently processes motion tracking data for its local region, eliminating the need to transmit all raw data to a central server. This segmentation enables parallel processing across multiple nodes, significantly reducing latency and improving tracking speed while maintaining comprehensive coverage.
Solution Approach 2:
The patent introduces a spatial dimension to the computing architecture by distributing edge nodes across geographic locations. Instead of a single centralized processing point, the system creates a three-dimensional computing landscape where processing occurs at multiple spatial levels (edge devices, local servers, cloud). This dimensional transformation enables simultaneous local processing and centralized coordination, resolving the latency-speed tradeoff.
2Speed
If edge computing is used to reduce latency, then processing speed improves, but computing power requirements at edge devices increase
Solution Approach 1:
The patent merges multiple edge computing nodes into a collaborative network where each node contributes its computing resources. Instead of requiring any single edge device to have full centralized computing capabilities, the system combines the processing power of distributed nodes to achieve equivalent or superior total computing capacity. This merging approach enables fast local processing while distributing the computational burden across the network.
Solution Approach 2:
The patent designs edge computing nodes with multi-functional capabilities that can handle various motion tracking tasks (detection, tracking, analysis, filtering) locally. These universal nodes can dynamically adjust their processing functions based on local needs and network conditions, reducing the need for specialized high-power hardware at each location while maintaining flexible, fast processing across different scenarios.
3Loss of information
If all tracking data is processed and stored, then complete information is available, but data filtering based on user preferences becomes difficult
Solution Approach 1:
The patent implements preliminary filtering at the edge computing nodes before data is transmitted or stored. Each edge node applies user preference filters locally to its captured data, pre-processing the information to match user needs. This preliminary action reduces the volume of data that requires comprehensive storage and makes subsequent retrieval and filtering operations much more efficient, while still maintaining access to complete raw data when needed.
Solution Approach 2:
The patent enables different edge nodes to apply customized filtering based on local user preferences and contextual requirements. Each node can optimize its data processing and filtering strategies according to local conditions, user profiles, and specific application needs. This local quality approach allows the system to maintain information completeness across the network while providing personalized, easily filterable data at each location.
Data Source
AI summary
A trajectory-based object search process includes receiving a user request specifying a geographic region of interest and/or a time period of interest. A set of video-derived object trajectories is identified based on the user request. At least one event is identified based on the set of video-derived object trajectories, by processing each video-derived object trajectory individually or by aggregating video-derived object trajectories, from the set of video-derived object trajectories, that overlap with respect to at least one feature. For each event, a preview image is selected that includes a thumbnail image and/or a video frame, based on the user request and using a ranking algorithm, and event metadata associated with the preview image is received. Also for each event, a video segment associated with that event is received, and the preview image and/or the video segment is caused to be displayed to a user associated with the user request.