Abstract: A computer for computing a convolutional layer of an artificial neural network, includes at least one set of at least two partial sum computing modules connected in series, a storage member for storing the coefficients of at least one convolution filter, each partial sum computing module comprising at least one computing unit configured so as to carry out a multiplication of an item of input data of the computer and a coefficient of a convolution filter, followed by an addition of the output of the preceding partial sum computing module in the series, each set furthermore comprising, for each partial sum computing module except the first in the series, a shift register connected at input for storing the item of input data for the processing duration of the preceding partial sum computing modules in the series.

Abstract: The invention provides a filtering device with hierarchical structure making it possible to carry out finite impulse response and infinite impulse response linear filtering functions and which can be combined with one or more devices of the same type. The device includes at least one first and one second filtering module having means for carrying out filtering functions with N configurable coefficients. A first subset of the N coefficients of a module is configured to carry out nonrecursive filtering functions, a second subset of the coefficients configured to carry out recursive filtering functions, one or more feedback loops able to be activated per module, at least one result sample of the filtering being generated at each clock cycle. The invention also provides a reconfigurable filtering device using at least two filtering devices with the hierarchical structure.

Abstract: The invention provides a reconfigurable module allowing morphological operations to be carried out for image processing. The module includes an operational block having five inputs, three outputs, three adders/subtracters and four logic blocks. The logic blocks provide various routings between the three adders/subtracters to enable the outputs to deliver the result of basic operations carried out on the five inputs. The reconfigurable module has a reduced number of components while at the same time allowing various morphological operations to be performed whose parameters can be modified. Furthermore, the reconfigurable module is serially combined to carry out more complex morphological operations. The invention also provides a method for implementing the reconfigurable module allowing an integral image, an eroded image, an expanded image, a distance image or projections along the rows and columns of the original image to be determined starting from an original image.

Abstract: A device for recognizing and locating objects in an image by scanning detection windows comprises a data stream architecture designed in pipeline form for concurrent hardware tasks and includes means for generating a descriptor for each detection window, a histogram determination unit determining a histogram of orientation gradients for each descriptor, and N processing units in parallel, capable of analyzing the histograms as a function of parameters associated with the descriptors to provide a partial score representing the probability that the descriptor concerned contains at least part of the object to be recognized, the sum of the partial scores of each detection window providing a global score representing the probability that the detection window contains the object to be recognized.

Abstract: The invention provides a filtering device with hierarchical structure making it possible to carry out finite impulse response and infinite impulse response linear filtering functions and which can be combined with one or more devices of the same type. The device includes at least one first and one second filtering module having means for carrying out filtering functions with N configurable coefficients. A first subset of the N coefficients of a module is configured to carry out nonrecursive filtering functions, a second subset of the coefficients configured to carry out recursive filtering functions, one or more feedback loops able to be activated per module, at least one result sample of the filtering being generated at each clock cycle. The invention also provides a reconfigurable filtering device using at least two filtering devices with the hierarchical structure.

Abstract: The invention provides a reconfigurable module allowing morphological operations to be carried out for image processing. The module includes an operational block having five inputs, three outputs, three adders/subtracters and four logic blocks. The logic blocks provide various routings between the three adders/subtracters to enable the outputs to deliver the result of basic operations carried out on the five inputs. The reconfigurable module has a reduced number of components while at the same time allowing various morphological operations to be performed whose parameters can be modified. Furthermore, the reconfigurable module is serially combined to carry out more complex morphological operations. The invention also provides a method for implementing the reconfigurable module allowing an integral image, an eroded image, an expanded image, a distance image or projections along the rows and columns of the original image to be determined starting from an original image.

Abstract: The invention relates to a component with a large grain dynamically reconfigurable architecture for processing of data by processing units organized in rows and connected to each other through interconnections so as to enable processing in pipeline or parallel mode or in dependent rows mode. All data types may be processed and the component may process several applications at the same time. The choice of the grain, control at several levels with limited control interconnection resources and the data distribution circuit enable local or general reconfiguration of the component in one clock cycle.

Abstract: The invention relates to a component with a large grain dynamically reconfigurable architecture for processing of data by processing units organized in rows and connected to each other through interconnections so as to enable processing in pipeline or parallel mode or in dependent rows mode. All data types may be processed and the component may process several applications at the same time. The choice of the grain, control at several levels with limited control interconnection resources and the data distribution circuit enable local or general reconfiguration of the component in one clock cycle.