Search

Background: Model based analysis of human upper limb movements has key importance in understanding the motor control processes of our nervous system. Various simulation software packages have been developed over the years to perform model based analysis. These packages provide computationally intensive-and therefore off-line-solutions to calculate the anatomical joint angles from motion captured raw measurement data (also referred as inverse kinematics). In addition, recent developments in inertial motion sensing technology show that it may replace large, immobile and expensive optical systems with small, mobile and cheaper solutions in cases when a laboratory-free measurement setup is needed. The objective of the presented work is to extend the workflow of measurement and analysis of human arm movements with an algorithm that allows accurate and real-time estimation of anatomical joint angles for a widely used OpenSim upper limb kinematic model when inertial sensors are used for movement recording.Methods: The internal structure of the selected upper limb model is analyzed and used as the underlying platform for the development of the proposed algorithm. Based on this structure, a prototype marker set is constructed that facilitates the reconstruction of model-based joint angles using orientation data directly available from inertial measurement systems. The mathematical formulation of the reconstruction algorithm is presented along with the validation of the algorithm on various platforms, including embedded environments.Results: Execution performance tables of the proposed algorithm show significant improvement on all tested platforms. Compared to OpenSim's Inverse Kinematics tool 50-15,000x speedup is achieved while maintaining numerical accuracy.Conclusions: The proposed algorithm is capable of real-time reconstruction of standardized anatomical joint angles even in embedded environments, establishing a new way for complex applications to take advantage of accurate and fast model-based inverse kinematics calculations. [ABSTRACT FROM AUTHOR]

Develops a new emulated digital multilayer cellular neural network chip architecture called Falcon. Main steps of the field-programmable gate array implementation; Critical parameters of the implementation in a single layer configuration; Power requirements of the architecture; Use of reconfigurable devices to implement emulated digital architectures.

An emulated digital CNN-UM (CASTLE) architecture was published few years ago.1 Different emulated digital CNN-UM architectures are analyzed in the paper. These new modified architectures are optimized according to the silicon area, operating speed or dissipated power. A reconfigurable arithmetic core will also be shown in the paper, by which solution of the neighborhood size can be changed. An advanced CASTLE with pipe-lining is presented. The operation frequency is increased by using this solution in approximately 10 times. [ABSTRACT FROM AUTHOR]

Summary: In this paper we describe an FPGA implementation of the Scale Invariant Feature Transform (SIFT) algorithm. The FPGA is required as its a lightweight device which makes it ideal for vision‐guided hybrid neuro‐prostheses utilised for upper limbs replacement. SIFT point detection is needed for computation of coordinates of the object‐to‐grasp in a wearable multi‐camera system. A modified SIFT algorithm is proposed and an implementation of it into C/C++ language on Xilinx ZCU102 FPGA board. The proposed hybrid hardware/software solution is compared to other hardware or hybrid implementations of the SIFT algorithm and with the baseline software detector OpenSIFT. The algorithm optimised for FPGA gives an average precision of 0.84 and the average recall of 0.94 in SIFT‐point detection compared to the baseline. The proposed solution has lower dissipated power than other solutions like CPU or GPU, and it has better computational speed. This solution allows for processing medium‐sized images in real‐time with low power consumption. [ABSTRACT FROM AUTHOR]