Abstract: Disclosed herein is a system and method for matching products detected in an image of a shelf. The match or non-match of the products is then used to make a determination that the products are correctly positioned on the shelf of if the positioning of the products represents a plug or spread situation.

Abstract: Disclosed herein is a system and method for the automatic detection of persons engaged in the open carry of firearms at a venue. The system and method comprise strategically placed cameras at the venue which are connected to edge devices which extract frames from video generated by the cameras. The video frames are sent to a server for analysis by an AI/ML model trained to detect firearms and, specifically, to detect persons carrying firearms. If a person wielding a firearm is detected in any image, an alert is raised and local authorities are automatically contacted. The system is designed to run continuously such as to be able to quickly detect a person in a venue carrying a firearm.

Abstract: Disclosed herein is an improved few-shot detector which utilizes semantic relation reasoning to learn novel objects from both visual information and the semantic relation of base class objects Specifically, a semantic space is constructed using word embeddings. Guided by the word embeddings of the classes, the detector is trained to project the objects from the visual space to the semantic space and to align their image representations with the corresponding class embeddings.

Abstract: Disclosed herein is an improvement to prior art feature pyramids for general object detection that inserts a simple norm calibration (NC) operation between the feature pyramids and detection head to alleviate and balance the norm bias caused by feature pyramid network (FPN) and which leverages an enhanced multi-feature selective strategy (MS) during training to assign the ground-truth to one or more levels of the feature pyramid.

Abstract: Disclosed herein is a system and method for generating quadrilateral bonding boxes which tightly cover the most representative faces of retail products having arbitrary poses. The quadrilateral boxes do not include unnecessary background information or miss parts of the objects, as would the axis-aligned bounding boxes produced by prior art detectors. A simple projection transformation can correct the pose of products for downstream tasks.

Abstract: Disclosed herein is a method of soft anchor-point detection (SAPD), which implements a concise, single-stage anchor-point detector with both faster speed and higher accuracy. Also disclosed is a novel training strategy with two softened optimization techniques: soft-weighted anchor points and soft-selected pyramid levels.

Abstract: Disclosed herein is a system and method of identifying new products on a retail shelf using a feature extractor trained to extract features from images of products on the shelf and output identifying information regarding the product in the product image. The extracted features are compared to extracted features in a product library and a best-fit is obtained. A new product is identified if the distance between the features of the product on the shelf and the features of the best-fit product from the product library are above a predetermined threshold.

Abstract: Disclosed herein are designs for two baselines to detect products in a retail setting. A novel detector, referred to herein as RetailDet, detects quadrilateral products. To match products using visual texts on 2D space, text features are encoded with spatial positional encoding and the Hungarian Algorithm that calculates optimal assignment plans between varying text sequences is used.

Abstract: Disclosed herein is an improved few-shot detector which utilizes a dynamic semantic network which takes as input a language feature and generates trainable parameters for a visual network. The visual network takes a visual feature as input and generates a classification and localization of an object.

Abstract: An automated inventory monitoring system includes an image capture module able to create a panoramic image of an aisle of a retail store. Images captured from the all of the store are stitched together to create a panoramic image of the aisle. Product images and label images are isolated from the panoramic image and classified, and a list of product images and label images is provided.

Abstract: Disclosed herein is an improved few-shot detector which utilizes semantic relation reasoning to learn novel objects from both visual information and the semantic relation of base class objects Specifically, a semantic space is constructed using word embeddings. Guided by the word embeddings of the classes, the detector is trained to project the objects from the visual space to the semantic space and to align their image representations with the corresponding class embeddings.

Abstract: Disclosed herein is a system and method of identifying new products on a retail shelf using a feature extractor trained to extract features from images of products on the shelf and output identifying information regarding the product in the product image. The extracted features are compared to extracted features in a product library and a best-fit is obtained. A new product is identified if the distance between the features of the product on the shelf and the features of the best-fit product from the product library are above a predetermined threshold.

Abstract: Disclosed herein is an improvement to prior art feature pyramids for general object detection that inserts a simple norm calibration (NC) operation between the feature pyramids and detection head to alleviate and balance the norm bias caused by feature pyramid network (FPN) and which leverages an enhanced multi-feature selective strategy (MS) during training to assign the ground-truth to one or more levels of the feature pyramid.

Abstract: A method and system for an AI-based communication training system for individuals and organizations is disclosed. A video analyzer is used to convert a video signal into a plurality of human morphology features with an accompanying audio analyzer converting an audio signal into a plurality of human speech features. A transformation module transforms the morphology features and the speech features into a current multi-dimensional performance vector and combinatorial logic generates an integration of the current multi-dimensional performance vector and one or more prior multi-dimensional performance vectors to generate a multi-session rubric. Backpropagation logic applies a current multi-dimensional performance vector from the combinatorial logic to the video analyzer and the audio analyzer.

Abstract: The present invention provides a novel approach to simultaneously extracting the 3D shape of the face and the semantically consistent 2D alignment using a 3D Spatial Transformer Network (3DSTN) to model both the camera projection matrix and the warping parameters of a 3D model. By utilizing a generic 3D model and a thin plate spline (TPS) warping function, subject-specific 3D shapes are able to be generated without the need for a large 3D shape basis.

Abstract: A method and system for an Al-based communication training system for individuals and organizations is disclosed. A video analyzer is used to convert a video signal into a plurality of human morphology features with an accompanying audio analyzer converting an audio signal into a plurality of human speech features. A transformation module transforms the morphology features and the speech features into a current multi-dimensional performance vector and combinatorial logic generates an integration of the current multi-dimensional performance vector and one or more prior multi-dimensional performance vectors to generate a multi-session rubric. Backpropagation logic applies a current multi-dimensional performance vector from the combinatorial logic to the video analyzer and the audio analyzer.

Abstract: Methods of detecting an object in an image using a convolutional neural network based architecture that processes multiple feature maps of differing scales from differing convolution layers within a convolutional network to create a regional-proposal bounding box. The bounding box is projected back to the feature maps of the individual convolution layers to obtain a set of regions of interest. These regions of interest are then processed to ultimately create a confidence score representing the confidence that the object detected in the bounding box is the desired object. These processes allow the method to utilize deep features encoded in both the global and the local representation for object regions, allowing the method to robustly deal with challenges in the problem of robust object detection. Software for executing the disclosed methods within an object-detection system is also disclosed.

Abstract: Methods of detecting an object in an image using a convolutional neural-network-based architecture that processes multiple feature maps of differing scales from differing convolution layers within a convolutional network to create a regional-proposal bounding box. The bounding box is projected back to the feature maps of the individual convolution layers to obtain a set of regions of interest (ROIs) and a corresponding set of context regions that provide additional context for the ROIs. These ROIs and context regions are processed to create a confidence score representing a confidence that the object detected in the bounding box is the desired object. These processes allow the method to utilize deep features encoded in both the global and the local representation for object regions, allowing the method to robustly deal with challenges in the problem of object detection. Software for executing the disclosed methods within an object-detection system is also disclosed.

Abstract: The present invention provides a novel approach to simultaneously extracting the 3D shape of the face and the semantically consistent 2D alignment using a 3D Spatial Transformer Network (3DSTN) to model both the camera projection matrix and the warping parameters of a 3D model. By utilizing a generic 3D model and a thin plate spline (TPS) warping function, subject-specific 3D shapes are able to be generated without the need for a large 3D shape basis.

Abstract: Methods of detecting an object in an image using a convolutional neural network based architecture that processes multiple feature maps of differing scales from differing convolution layers within a convolutional network to create a regional-proposal bounding box. The bounding box is projected back to the feature maps of the individual convolution layers to obtain a set of regions of interest. These regions of interest are then processed to ultimately create a confidence score representing the confidence that the object detected in the bounding box is the desired object. These processes allow the method to utilize deep features encoded in both the global and the local representation for object regions, allowing the method to robustly deal with challenges in the problem of robust object detection. Software for executing the disclosed methods within an object-detection system is also disclosed.