LPR Camera Motion Detection Neural Network Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional License Plate Recognition (LPR) cameras are large, expensive, and inefficient, consuming excessive power and memory, as they capture and transmit numerous images without selective processing, lacking intelligence for local image analysis.
Innovation Solution
A compact LPR camera system with a processor that detects motion, applies filters using a neural network algorithm to select significant images, and transmits only those with high confidence scores, reducing power consumption and storage needs through local processing and wireless transmission.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional LPR cameras capture and store all images for remote processing, then comprehensive surveillance coverage is achieved, but power consumption and memory usage become excessive
Solution Approach 1:
The patent applies preliminary action by implementing a motion detection mechanism that activates the image capture function only when motion is detected in the field of view. This prevents continuous operation of the camera and processor, significantly reducing power consumption while maintaining surveillance reliability. The system performs preliminary filtering of scenes before full image processing occurs.
Solution Approach 2:
The patent extracts and isolates only the significant portions of surveillance data by implementing intelligent image analysis that identifies and flags only those images containing relevant information (such as license plates). This extraction approach allows the system to maintain comprehensive surveillance coverage while transmitting and storing only the essential extracted data, reducing overall power and memory requirements.
2Reliability
If conventional LPR cameras capture numerous images without selective processing, then complete image records are maintained, but the system lacks intelligence for local image analysis
Solution Approach 1:
The patent introduces an intermediary intelligent processing layer between image capture and storage/transmission. This intermediary component analyzes captured images locally using algorithms to determine significance, acting as a mediator that filters and prioritizes data. This adds processing intelligence to the system while maintaining complete image records, as all images are captured but only significant ones are transmitted and stored remotely.
Solution Approach 2:
The patent segments the surveillance system into distinct functional modules: a capture module that records all images, an analysis module that evaluates image significance, and a transmission module that sends only relevant data. This segmentation allows the system to maintain complete records locally while adding intelligent processing capabilities, resolving the contradiction between record completeness and processing intelligence.
3Use of energy by stationary object
If trailer-mounted LPR cameras include large battery-banks and solar panels, then sufficient power supply is ensured, but the overall system size and cost increase significantly
Solution Approach 1:
The patent implements periodic action by having the camera and processor operate in alternating active and sleep states. The camera captures images periodically based on motion detection events rather than continuously, and the processor activates only when image analysis is required. This periodic operation reduces the required power supply capacity, allowing the system to use smaller, lighter battery-banks and solar panels while ensuring sufficient power for actual operations.
4Loss of information
If all digital images are stored and transmitted for remote processing, then comprehensive data is available for analysis, but memory consumption and transmission costs increase
Solution Approach 1:
The patent extracts only the essential information from captured images by implementing intelligent analysis that identifies significant images containing relevant data such as license plates. This extraction process allows the system to maintain complete image data locally for reference while transmitting only the extracted significant images for remote processing, dramatically reducing memory consumption and transmission requirements without losing critical information.
Data Source
AI summary
A method and system for capturing and filtering surveillance images are described. A processor detects motion of an object in a field of view and then generates a plurality of images in response to detecting motion of the object in the field of view. A first filter is then applied to the plurality of images and later, the one or remaining images based on the first filter are stored in a memory device. In response to a triggering event, an energy conserving processor is activated from a sleep mode of operation where the energy conserving processor applies a second filter to the remaining images from the first filter. The energy conserving processor assigns a confidence score to one or more images matching the second filter. With the second filter, the energy conserving processor selects fewer images for RF transmission to a remote image analyzer, resulting in increased power savings.