Event Timeline Indicators for Video Surveillance Motion Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing video surveillance systems face challenges in efficiently identifying and presenting meaningful motion events from continuous video streams, as motion detection can generate too many irrelevant alerts due to trivial movements, leading to a high burden on reviewers to sift through non-significant data.
Innovation Solution
The implementation of methods for displaying indicators on an event timeline, categorizing motion events, and generating smart time-lapse video clips, which allow for efficient identification and presentation of significant motion events by associating categories with similar events, suppressing false positives, and enabling user-defined zones of interest for real-time notifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If motion detection sensitivity is increased to capture more events, then the quantity of detected events increases, but the proportion of false positives from trivial movements increases
Solution Approach 1:
The patent segments the continuous video stream into discrete motion events, each with associated metadata. By dividing the monitoring task into individual event segments that can be independently analyzed and categorized, the system can apply different filtering and prioritization rules to different types of events, thereby capturing more events while maintaining reliability through selective processing.
Solution Approach 2:
The patent introduces an intermediary classification layer between motion detection and event presentation. Motion events are first detected, then classified into categories (e.g., significant vs. trivial), and finally presented selectively to reviewers. This intermediary classification mechanism acts as a mediator that filters out false positives while preserving true events.
2Reliability
If all motion events are presented to reviewers for manual review, then comprehensive monitoring is achieved, but the time and effort required for review increases significantly
Solution Approach 1:
The patent extracts and highlights only the most significant motion events for reviewer attention, rather than presenting all detected events. By taking out and isolating high-priority events based on classification criteria, the system maintains comprehensive monitoring capability while dramatically reducing the time reviewers need to spend on obvious false positives.
Solution Approach 2:
The patent applies different presentation qualities to different events based on their significance. Significant events receive prominent display with detailed information, while trivial events are either suppressed or shown with minimal information. This local differentiation in presentation quality allows reviewers to focus attention where it is most needed.
3Ease of operation
If motion detection is used as the only selection criterion, then the system is simple to operate, but too many irrelevant video segments are generated for review
Solution Approach 1:
The patent implements a multi-functionality approach where the system not only detects motion events but also automatically classifies them into categories, prioritizes them based on significance criteria, and selectively presents them for review. By combining multiple functions (detection, classification, prioritization, presentation) into a single integrated system, it maintains ease of operation while dramatically reducing the quantity of irrelevant video segments requiring manual review.
Data Source
AI summary
The various embodiments described herein include methods, devices, and systems for displaying event indicators on an event timeline. In one aspect, a method includes: displaying a video monitoring user interface including: video information corresponding to a video stream of remote camera's field of view in a first region, and the event timeline in a second region; obtaining identification of a new zone of interest corresponding to a portion of the camera's field of view; sending information indicative of the new zone of interest to a server system; obtaining identification of one or more past motion events detected by the remote camera involving the new zone of interest; and updating display of the event timeline to display an event indicator having a visual characteristic corresponding to the new zone of interest for each of the one or more past motion events.