Abstract: Technology disclosed herein may involve a computing system that (i) based on an image of a target object of a given class of object and at least one GAN configured to generate artificial images of the given class of object, generates an artificial image of the target object that is substantially similar to real-world images of objects of the given class of objects captured by real-world scanning devices, (ii) based on an image of a receptacle, selects an insertion location within the receptacle in the image of the receptacle to insert the artificial image of the target object, (iii) generates a combined image of the receptacle and the target object, wherein generating the combined image comprises inserting the artificial image of the target object into the image of the receptacle at the insertion location, and (iv) trains one or more object detection algorithms with the combined image of the receptacle and the target object.

Abstract: Technology disclosed herein may involve a computing system that (i) based on an image of a target object of a given class of object and at least one GAN configured to generate artificial images of the given class of object, generates an artificial image of the target object that is substantially similar to real-world images of objects of the given class of objects captured by real-world scanning devices, (ii) based on an image of a receptacle, selects an insertion location within the receptacle in the image of the receptacle to insert the artificial image of the target object, (iii) generates a combined image of the receptacle and the target object, wherein generating the combined image comprises inserting the artificial image of the target object into the image of the receptacle at the insertion location, and (iv) trains one or more object detection algorithms with the combined image of the receptacle and the target object.

Abstract: Technology disclosed herein may involve a computing system that (i) based on an image of a target object of a given class of object and at least one GAN configured to generate artificial images of the given class of object, generates an artificial image of the target object that is substantially similar to real-world images of objects of the given class of objects captured by real-world scanning devices, (ii) based on an image of a receptacle, selects an insertion location within the receptacle in the image of the receptacle to insert the artificial image of the target object, (iii) generates a combined image of the receptacle and the target object, wherein generating the combined image comprises inserting the artificial image of the target object into the image of the receptacle at the insertion location, and (iv) trains one or more object detection algorithms with the combined image of the receptacle and the target object.

Abstract: Technology disclosed herein may involve a computing system that (i) based on an image of a target object of a given class of object and at least one GAN configured to generate artificial images of the given class of object, generates an artificial image of the target object that is substantially similar to real-world images of objects of the given class of objects captured by real-world scanning devices, (ii) based on an image of a receptacle, selects an insertion location within the receptacle in the image of the receptacle to insert the artificial image of the target object, (iii) generates a combined image of the receptacle and the target object, wherein generating the combined image comprises inserting the artificial image of the target object into the image of the receptacle at the insertion location, and (iv) trains one or more object detection algorithms with the combined image of the receptacle and the target object.

Abstract: In example embodiments, a computing system is capable of (a) receiving image data that represents a scene that was scanned by a detection device of a security screening system, (b) based at least on the image data, at least one neural network, and a confidence threshold defined for the security screening system, determining that the image data includes an identified item that has been deemed to be of interest, (c) based at least on determining that the image data includes the identified item that has been deemed to be of interest and one or more security parameters for the security screening system, determining that the identified item is deemed to be a security interest for the security screening system, and (d) based at least on determining that the identified item is deemed to be a security interest for the security screening system, presenting a visualization corresponding to the identified item.

Abstract: Technology disclosed herein may involve a computing system that (i) generates (a) a first feature map based on a first visual input from a first perspective of a scene utilizing at least one first neural network and (b) a second feature map based on a second visual input from a second, different perspective of the scene utilizing at least one second neural network, where the first perspective and the second perspective share a common dimension, (ii) based on the first feature map and a portion of the second feature map corresponding to the common dimension, generates cross-referenced data for the first visual input, (iii) based on the second feature map and a portion of the first feature map corresponding to the common dimension, generates cross-referenced data for the second visual input, and (iv) based on the cross-referenced data, performs object detection on the scene.

Abstract: Disclosed is an object-detection system configured to utilize multiple object-detection models that generate respective sets of object-detection conclusions to detect objects of interest within images of scenes. The object-detection system is configured to implement a series of functions to reconcile any discrepancies that exist in its multiple sets of object-detection conclusions in order to generate one set of conclusions for each perceived object of interest within a given image.

Abstract: Disclosed is an object-detection system configured to utilize multiple object-detection models that generate respective sets of object-detection conclusions to detect objects of interest within images of scenes. The object-detection system is configured to implement a series of functions to reconcile any discrepancies that exist in its multiple sets of object-detection conclusions in order to generate one set of conclusions for each perceived object of interest within a given image.

Abstract: Technology disclosed herein may involve a computing system that (i) generates (a) a first feature map based on a first visual input from a first perspective of a scene utilizing at least one first neural network and (b) a second feature map based on a second visual input from a second, different perspective of the scene utilizing at least one second neural network, where the first perspective and the second perspective share a common dimension, (ii) based on the first feature map and a portion of the second feature map corresponding to the common dimension, generates cross-referenced data for the first visual input, (iii) based on the second feature map and a portion of the first feature map corresponding to the common dimension, generates cross-referenced data for the second visual input, and (iv) based on the cross-referenced data, performs object detection on the scene.

Abstract: Technology disclosed herein may involve a computing system that (i) generates (a) a first feature map based on a first visual input from a first perspective of a scene utilizing at least one first neural network and (b) a second feature map based on a second visual input from a second, different perspective of the scene utilizing at least one second neural network, where the first perspective and the second perspective share a common dimension, (ii) based on the first feature map and a portion of the second feature map corresponding to the common dimension, generates cross-referenced data for the first visual input, (iii) based on the second feature map and a portion of the first feature map corresponding to the common dimension, generates cross-referenced data for the second visual input, and (iv) based on the cross-referenced data, performs object detection on the scene.

Abstract: In example embodiments, a computing system is capable of (a) receiving image data that represents a scene that was scanned by a detection device of a security screening system, (b) based at least on the image data, at least one neural network, and a confidence threshold defined for the security screening system, determining that the image data includes an identified item that has been deemed to be of interest, (c) based at least on determining that the image data includes the identified item that has been deemed to be of interest and one or more security parameters for the security screening system, determining that the identified item is deemed to be a security interest for the security screening system, and (d) based at least on determining that the identified item is deemed to be a security interest for the security screening system, presenting a visualization corresponding to the identified item.

Abstract: According to an aspect, a system comprises at least one processor, a memory, and a non-transitory computer-readable storage medium storing instructions. The stored instructions are executable to cause the at least one processor to: receive a digital image that represents an object scanned by a detection device, determine a region of the digital image that is likely to contain an item, transform the region of the digital image to an embedding, classify, based on the embedding, the region as containing a known class of known item, and responsive to classifying the region as containing the known class of item: generate a graphical representation based on the known class of item.

Abstract: Technology disclosed herein may involve a computing system that (i) based on an image of a target object of a given class of object and at least one GAN configured to generate artificial images of the given class of object, generates an artificial image of the target object that is substantially similar to real-world images of objects of the given class of objects captured by real-world scanning devices, (ii) based on an image of a receptacle, selects an insertion location within the receptacle in the image of the receptacle to insert the artificial image of the target object, (iii) generates a combined image of the receptacle and the target object, wherein generating the combined image comprises inserting the artificial image of the target object into the image of the receptacle at the insertion location, and (iv) trains one or more object detection algorithms with the combined image of the receptacle and the target object.

Abstract: Technology disclosed herein may involve a computing system that (i) generates (a) a first feature map based on a first visual input from a first perspective of a scene utilizing at least one first neural network and (b) a second feature map based on a second visual input from a second, different perspective of the scene utilizing at least one second neural network, where the first perspective and the second perspective share a common dimension, (ii) based on the first feature map and a portion of the second feature map corresponding to the common dimension, generates cross-referenced data for the first visual input, (iii) based on the second feature map and a portion of the first feature map corresponding to the common dimension, generates cross-referenced data for the second visual input, and (iv) based on the cross-referenced data, performs object detection on the scene.

Abstract: According to an aspect, a system comprises at least one processor, a memory, and a non-transitory computer-readable storage medium storing instructions. The stored instructions are executable to cause the at least one processor to: receive a digital image that represents an object scanned by a security scanning device, receive, from a neural network, information indicating an item identified within the image, receive, from a database, item data for the identified item, and generate, for output at a display, a graphical representation corresponding to the identified item based on the received item data, wherein the graphical representation indicates a location of the identified item by a neural network, and wherein the generated graphical representation comprises at least a portion of the digital image corresponding to the identified item, and output, for display, the graphical representation.

Abstract: According to an aspect, a method comprises: generating a 2D projection from a 3D representation of an object, wherein the 2D projection comprises an edgemapped projection of the 3D representation, generating, with a generative adversarial neural network (GAN), and based on the edgemapped projection, a simulated image of the object, wherein the simulated image appears as though the object has been scanned by a detection device, combining the simulated image of the object with a background image to form a synthesized image, wherein the background image was captured by a detection device, and outputting the synthesized image.

Abstract: Various systems, methods and non-transitory computer-readable media are described, which may involve performing operations comprising: receiving, with an object detector, a first image from a first positional angle comprising a first perspective of a scene, receiving, with the object detector, a second image from a second, different positional angle comprising a second perspective of the scene, and performing, with the object detector, object detection on the first image from the first perspective and on the second image from the second perspective by cross-referencing data related to the first image and the second image within the object detector.

Abstract: In an example, a computing device comprises at least one processor, a memory, and a non-transitory computer-readable storage medium storing instructions thereon that, when executed, cause the at least one processor to perform functions comprising: performing an initial security screening on an object based on a first set of security-related data associated with the object and a first set of security screening parameters, and performing a supplemental security screening on the object based on a second set of security-related data associated with the object and a second set of security screening parameters. The first set of security-related data may be different from the second set of security-related data, and the first set of security screening parameters may be different from the second set of security screening parameters.

Abstract: According to an aspect, a method comprises: generating a 2D projection from a 3D representation of an object, generating, based on the 2D projection, a simulated image of the object, wherein the simulated image appears as though the object has been scanned by a detection device, combining the simulated object with a background image to form a synthesized image, wherein the background image was captured by a detection device, and outputting the synthesized image.

Abstract: According to an aspect, a method comprises: generating a 2D projection from a 3D representation of an object, wherein the 2D projection comprises an edgemapped projection of the 3D representation, generating, with a generative adversarial neural network (GAN), and based on the edgemapped projection, a simulated image of the object, wherein the simulated image appears as though the object has been scanned by a detection device, combining the simulated image of the object with a background image to form a synthesized image, wherein the background image was captured by a detection device, and outputting the synthesized image.