Abstract: Methods and structures are presented for implementing an automatic target recognition system as a convolutional neural network (CNN) in a satellite or other environment with constrained resources, such as limited memory capacity and limited processing capability. For example, this allows for the automatic target recognition to be implemented on a field programmable gate array (FPGA). Image data is split into subsets of contiguous pixels, with the subsets processed in parallel in a CNN of a corresponding processing node using quantized weight values that are determined in a training process that accounts for the constraints of the automatic target recognition system. The results of the automatic target recognition process is based on the combined output of the processing nodes.

Abstract: Methods and structures are presented for implementing an automatic target recognition system as a convolutional neural network (CNN) in a satellite or other environment with constrained resources, such as limited memory capacity and limited processing capability. For example, this allows for the automatic target recognition to be implemented on a field programmable gate array (hdFPGA). Image data is split into subsets of contiguous pixels, with the subsets processed in parallel in a CNN of a corresponding processing node using quantized weight values that are determined in a training process that accounts for the constraints of the automatic target recognition system. The results of the automatic target recognition process is based on the combined output of the processing nodes.

Abstract: A system for detecting a position of an object includes a position sensor and a demodulator. The position sensor receives a first excitation signal, senses a displacement of the object with respect to a reference point based on the first excitation signal, and generates first and second sense signals based on the first excitation signal. The demodulator receives the first sense signal and the second sense signal from the position sensor, performs a first cross-correlation calculation between the first sense signal and a second excitation signal and a second cross-correlation calculation between the second sense signal and the second excitation signal, determines displacement of the object with respect to the reference point based on results of the first and second cross-correlation calculations, and determine a position of the object based on the displacement.

Abstract: A system for detecting a position of an object includes a position sensor and a demodulator. The position sensor receives a first excitation signal, senses a displacement of the object with respect to a reference point based on the first excitation signal, and generates first and second sense signals based on the first excitation signal. The demodulator receives the first sense signal and the second sense signal from the position sensor, performs a first cross-correlation calculation between the first sense signal and a second excitation signal and a second cross-correlation calculation between the second sense signal and the second excitation signal, determines displacement of the object with respect to the reference point based on results of the first and second cross-correlation calculations, and determine a position of the object based on the displacement.