Container Number Recognition Using Multi-Camera OCR and Laser Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The manual capture of container numbers in container yards leads to errors and reduces throughput, making it challenging to accurately identify and track containers due to varied imaging angles and non-horizontal or vertical arrangements.
Innovation Solution
A system utilizing cameras and laser sensors for motion detection, combined with multi-scale structural similarity index measurement, neural networks, and character segmentation techniques, processes images in real-time to detect and identify container numbers, even in low light conditions, and separates frames from stacked containers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual capture of container numbers is used, then system complexity is reduced, but accuracy deteriorates due to manual errors and throughput decreases
Solution Approach 1:
The patent replaces manual mechanical capture methods with an automated optical recognition system using cameras and image processing algorithms. The system captures images of container numbers and automatically processes them to extract the numbers, eliminating manual intervention and its associated errors while maintaining manageable system complexity through standardized image processing pipelines.
Solution Approach 2:
The system enables self-service operation where the automated detection system performs container number capture and processing without human surveyors. The system independently captures images, processes them through character recognition algorithms, and outputs the container numbers, making the entire process autonomous and continuously operational.
2Measurement precision
If automated detection is implemented, then throughput increases and accuracy improves, but device complexity increases
Solution Approach 1:
The patent segments the detection system into distinct functional modules: image capture module, motion detection module, character segmentation module, and number recognition module. Each module performs a specific function and can be independently optimized or replaced, making the overall complex system more manageable while maintaining high accuracy through specialized processing at each stage.
Solution Approach 2:
The system performs preliminary actions by capturing multiple images at different positions before final number extraction. The motion detection module identifies when a container is present and triggers image capture at optimal moments, and the character segmentation module pre-processes images to separate and order characters before recognition, ensuring accurate identification even in challenging conditions.
3Adaptability or versatility
If images are captured at multiple angles, then detection coverage improves, but processing complexity increases due to non-horizontal or vertical arrangements
Solution Approach 1:
The patent employs dynamic image processing that adapts to different camera angles and container orientations. The character segmentation and ordering algorithms dynamically adjust their processing based on the detected arrangement pattern, whether horizontal, vertical, or diagonal, allowing the system to handle varied capture geometries without requiring separate processing pipelines for each orientation.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances accuracy and efficiency by automating the detection process, reducing manual errors, and ensuring reliable identification of container numbers under various conditions.
Implementation Method 1
laser sensors configured to improve the accuracy of motion detection logic
Implementation Method 2
uses a laser sensor to detect separation between the containers
Data Source
AI summary
Exemplary embodiments of the present disclosure are directed towards a method for detecting and identifying container number in real-time. Monitoring vehicle carrying containers and triggering first camera, second camera, third camera, fourth camera, fifth camera, and laser sensors to capture container views by pre-processing module. Transmitting containers image data to computing device by the pre-processing module. Detecting container number region in container image frames by visual object detection module. Cropping container number region by visual object detection module. Applying two-dimensional Fast Fourier Transform on cropped container number region. Segmenting each character situated in container number region by segmentation and character classification module. Classifying each character situated in container number region by segmentation and character classification module. Arranging characters in order based on relative positions of characters to obtain container number information by segmentation and character classification module. Aggregating container image frames and generating container number by post-processing module.