Teledyne Technologies. has been granted a patent for a high-resolution image target classification system. This system utilizes a multi-scale neural network to classify objects in images by determining regions of interest and optimizing resource allocation for efficient processing and detection. GlobalData’s report on Teledyne Technologies gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Access deeper industry intelligence
Experience unmatched clarity with a single platform that combines unique data, AI, and human expertise.
According to GlobalData’s company profile on Teledyne Technologies, Photovoltaic drones was a key innovation area identified from patents. Teledyne Technologies's grant share as of June 2024 was 66%. Grant share is based on the ratio of number of grants to total number of patents.
High resolution image target classification system and method
The patent US12046031B2 describes a sophisticated system and method for object classification using a multi-scale neural network architecture. The system includes a proposal component that receives a dataset containing images of a scene and identifies regions of interest for further analysis. This proposal component works in conjunction with a multi-scale neural network, which consists of multiple neural networks, each trained to classify objects within specific regions. The attention coordinator plays a crucial role by determining which regions of interest to process based on available system resources and the resource allocation associated with each neural network. This ensures efficient processing and maximizes the probability of accurately detecting objects within the image.
Additionally, the system incorporates various input devices, such as visible spectrum cameras and other sensors like radar and infrared imaging systems, to enhance the dataset. The proposal component can analyze the dataset to identify proposed regions of interest, including those associated with detected motion or through stochastic search methods. Each neural network is designed to handle different input image sizes, allowing for flexibility in processing. The method further optimizes the allocation of regions to neural networks based on the likelihood of detecting objects and minimizing the number of pixels processed. A short-term target memory is also utilized to track classified objects and generate predictive proposals for future analysis, enhancing the system's overall effectiveness in real-time object classification scenarios.
To know more about GlobalData’s detailed insights on Teledyne Technologies, 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.
