Leidos. has been granted a patent for a method that utilizes artificial neural networks to validate cargo manifests by analyzing radiographic images of shipping containers. The system compares extracted feature vectors from both the images and manifests to determine the likelihood of object matches. GlobalData’s report on Leidos gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Leidos, was a key innovation area identified from patents. Leidos's grant share as of July 2024 was 70%. Grant share is based on the ratio of number of grants to total number of patents.
Object identification in shipping containers using radiographic images
The patent US12067760B2 outlines a method and system for validating cargo manifests associated with shipping containers using advanced neural network techniques. The process begins with the receipt of a radiographic image of a scanned shipping container, which is analyzed using an autoencoder neural network to extract a feature vector. Simultaneously, a cargo manifest is received and processed through a natural language processing (NLP) neural network to derive another feature vector. These vectors are then compared against historical distributions of prior feature vectors from similar shipping containers and manifests to determine the statistical probability of the objects in the scanned container matching those listed in the manifest. The system generates an automated detection indication based on this probability, which can include graphical displays of consistency and rankings of radiographic images.
Additionally, the patent details various configurations and enhancements to the system, such as real-time updates to the historic distribution of feature vectors, the use of pretrained word embeddings for the NLP network, and the ability to display categorical assignments of validation or rejection for the cargo manifest. The method also allows for the graphical representation of parameters quantifying the match between the scanned container's contents and the manifest, as well as the display of prior images and manifests for comparative analysis. This innovative approach aims to improve the accuracy and efficiency of cargo manifest validation, leveraging machine learning techniques to enhance the reliability of shipping container inspections.
To know more about GlobalData’s detailed insights on Leidos, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
