Science Applications International has been granted a patent for a method that uses cameras to detect target objects in a search space. The method involves projecting search points onto images captured by the cameras, selecting and processing subimages corresponding to the search points, and determining the positions of the target objects based on the detected subimages and orientation data from the cameras. GlobalData’s report on Science Applications International 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 Science Applications International, MITM attack solutions was a key innovation area identified from patents. Science Applications International's grant share as of September 2023 was 67%. Grant share is based on the ratio of number of grants to total number of patents.
Patent granted for method of detecting and locating target objects
A recently granted patent (Publication Number: US11776158B2) describes a method and computing device for determining the positions of target objects in a three-dimensional search space using images from multiple cameras. The method involves several steps, including determining a set of subimages based on spatial positions in the search space and images from the cameras. From this set, a first plurality of subimages is ignored if the search point image position is within a predetermined distance of an image edge. The remaining subimages are then used to determine a second plurality of subimages that contain the target object image. The method further involves determining whether two subimages in the second plurality correspond to the same target object and outputting information indicating the positions of the target objects.
The method also includes assigning a corresponding subset of search points to each target object and determining the search point spatial positions in the search space based on the positions of the target objects. This involves determining positions within a predetermined distance of the corresponding target object's position. Additionally, the cameras used in the method correspond to a field of view (FOV), with some FOVs being smaller than the search space, and each camera moves independently of the others.
The method includes selecting random locations in the search space for each search point spatial position and selecting subimages based on projections of randomly selected search point spatial positions onto the images. The first plurality of subimages is determined by ignoring subimages that contain man-made or natural objects. The second plurality of subimages is determined by searching for target object images in the remaining subimages and excluding portions of the images outside of the set of subimages from the search.
The patent also describes a computing device that includes one or more processors and memory storing instructions for executing the method. The computing device performs the same steps as described above, including determining the positions of target objects in the search space based on the second plurality of subimages and outputting information indicating these positions.
Overall, this patent presents a method and computing device for accurately determining the positions of target objects in a three-dimensional search space using images from multiple cameras. The method involves various steps, including subimage selection, target object identification, and search point determination. The computing device executes these steps to provide information about the positions of the target objects.
To know more about GlobalData’s detailed insights on Science Applications International, buy the report here.
Premium 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.
