New Hampshire Patent of the Month – May 2024

Position Imaging, Inc., a logistics and asset location company, has secured a paent for a machine-learning object-identification tool capable of self improvements over time. Their object-identification system, powered by advanced machine learning and deep neural networks, offers a glimpse into the future of automated processes and enhanced user experiences.

At the heart of this system lies an image sensor that captures images of objects within a designated area. These images are then processed by a controller equipped with a deep neural network, which is trained to detect and recognize objects. What sets this system apart is its ability to continuously improve its object recognition capabilities through retraining.

When the deep neural network encounters an object it doesn’t recognize, it doesn’t simply give up. Instead, it leverages human input to learn and adapt. For instance, if the network fails to identify an object in an image, it prompts the user to provide labeling information. This information is then used to retrain the network, enhancing its ability to identify similar objects in the future.

The system also incorporates depth sensors, allowing it to capture not just images but also depth data. This additional layer of information further enhances object identification accuracy, especially in complex environments with varying lighting conditions and obstructed views.

Moreover, Position Imaging’s sensor modules are designed for versatility. Whether deployed in a fixed position or integrated into mobile devices like smartphones or tablets, they provide seamless object identification and tracking capabilities. This means users can effortlessly interact with their surroundings, whether they’re in a retail store, warehouse, or any other environment where object recognition is crucial.

Beyond its practical applications, Position Imaging’s technology offers a glimpse into the future of AI-driven automation. By combining machine learning with human input, their object-identification system exemplifies the power of collaboration between man and machine in creating smarter, more adaptive systems.

Are you developing new technology for an existing application? Did you know your development work could be eligible for the R&D Tax Credit and you can receive up to 14% back on your expenses? Even if your development isn’t successful your work may still qualify for R&D credits (i.e. you don’t need to have a patent to qualify). To find out more, please contact a Swanson Reed R&D Specialist today or check out our free online eligibility test.

Who We Are:

Swanson Reed is one of the U.S.’ largest Specialist R&D tax advisory firms. We manage all facets of the R&D tax credit program, from claim preparation and audit compliance to claim disputes.

Swanson Reed regularly hosts free webinars and provides free IRS CE and CPE credits for CPAs. For more information please visit us at or contact your usual Swanson Reed representative.

Recent Posts