Abstract: Detection device 1 for recognizing an object and/or a person 3, 3a, b, c in a monitoring area 2 monitored with a plurality of cameras 4, 4a, b, c, having a plurality of analysis modules 6, 6a, b, c, wherein each analysis module 6, 6a, b, c in each case preferably has and/or forms a neural network, wherein the analysis modules 6, 6a, b, c in each case have a data connection to at least one camera 4, 4a, b, c, wherein monitoring data from the connected cameras 4, 4a, b, c are provided in each case to the analysis modules 6, 6a, b, c, having a shared memory module 7, wherein the analysis modules 6, 6a, b, c have a data connection to the shared memory module 7, wherein the analysis modules 6, 6a, b, c are designed in each case to retrieve memory data associated with the monitoring data from the shared memory module 7, wherein the analysis modules 6, 6a, b, c are designed in each case to determine features, object features and/or person features on the basis of the monitoring data and the memory data.

Abstract: A method for tracking and/or characterizing multiple objects in a sequence of images. The method includes: assigning a neural network to each object to be tracked; providing a memory that is shared by all neural networks; providing a local memory for each neural network, respectively; supplying images from the sequence, and/or details of these images, to each neural network; during the processing of each image and/or image detail by one of the neural networks, generating an address vector from at least one processing product of this neural network; based on this address vector, writing at least one further processing product of the neural network into the shared memory and/or into the local memory, and/or reading out data from this shared memory and/or local memory and further processing the data by the neural network.

Abstract: A method for tracking and/or characterizing multiple objects in a sequence of images. The method includes: assigning a neural network to each object to be tracked; providing a memory shared by all neural networks, and designed to map an address vector of address components, via differentiable operations, onto one or multiple memory locations, and to read data from these memory locations or write data into these memory locations; supplying images from the sequence, and/or details of these images, to each neural network; during the processing of each image and/or image detail by one of the neural networks, generating an address vector from at least one processing product of this neural network; based on this address vector, writing at least one further processing product of the neural network into the shared memory, and/or reading out data from this shared memory and further processing the data by the neural network.

Abstract: A method for tracking and/or characterizing multiple objects in a sequence of images. The method includes: assigning a neural network to each object to be tracked; providing a memory shared by all neural networks, and designed to map an address vector of address components, via differentiable operations, onto one or multiple memory locations, and to read data from these memory locations or write data into these memory locations; supplying images from the sequence, and/or details of these images, to each neural network; during the processing of each image and/or image detail by one of the neural networks, generating an address vector from at least one processing product of this neural network; based on this address vector, writing at least one further processing product of the neural network into the shared memory, and/or reading out data from this shared memory and further processing the data by the neural network.

Abstract: A method for tracking and/or characterizing multiple objects in a sequence of images. The method includes: assigning a neural network to each object to be tracked; providing a memory that is shared by all neural networks; providing a local memory for each neural network, respectively; supplying images from the sequence, and/or details of these images, to each neural network; during the processing of each image and/or image detail by one of the neural networks, generating an address vector from at least one processing product of this neural network; based on this address vector, writing at least one further processing product of the neural network into the shared memory and/or into the local memory, and/or reading out data from this shared memory and/or local memory and further processing the data by the neural network.

Abstract: Detection device 1 for recognizing an object and/or a person 3, 3a, b, c in a monitoring area 2 monitored with a plurality of cameras 4, 4a, b, c, having a plurality of analysis modules 6, 6a, b, c, wherein each analysis module 6, 6a, b, c in each case preferably has and/or forms a neural network, wherein the analysis modules 6, 6a, b, c in each case have a data connection to at least one camera 4, 4a, b, c, wherein monitoring data from the connected cameras 4, 4a, b, c are provided in each case to the analysis modules 6, 6a, b, c, having a shared memory module 7, wherein the analysis modules 6, 6a, b, c have a data connection to the shared memory module 7, wherein the analysis modules 6, 6a, b, c are designed in each case to retrieve memory data associated with the monitoring data from the shared memory module 7, wherein the analysis modules 6, 6a, b, c are designed in each case to determine features, object features and/or person features on the basis of the monitoring data and the memory data.

Abstract: Systems and methods are disclosed for medical image processing using neural networks. A first and a second controller network share a memory to which both the first and second controller network can write data and from which both the first and the second controller network can read data. Reading and writing is performed by respective read and write heads which are advantageously neural networks trained how to write and read in an optimal way. The memory thus provides each controller network with context data generated by the respective other controller network.

Abstract: Systems and methods are disclosed for medical image processing using neural networks. A first and a second controller network share a memory to which both the first and second controller network can write data and from which both the first and the second controller network can read data. Reading and writing is performed by respective read and write heads which are advantageously neural networks trained how to write and read in an optimal way. The memory thus provides each controller network with context data generated by the respective other controller network.