Guillermo Botella

Robust Bioinspired Architecture for Optical-Flow Computation

Motion estimation from image sequences, called optical flow, has been deeply analyzed by the scientific community. Despite the number of different models and algorithms, none of them covers all problems associated with real-world processing. This paper presents a novel customizable architecture of a neuromorphic robust optical flow (multichannel gradient model) based on reconfigurable hardware with the properties of the cortical motion pathway, thus obtaining a useful framework for building future complex bioinspired real-time systems with high computational complexity. The presented architecture is customizable and adaptable, while emulating several neuromorphic properties, such as the use of several information channels of small bit width, which is the nature of the brain. This paper includes the resource usage and performance data, as well as a comparison with other systems. This hardware platform has many application fields in difficult environments due to its bioinspired nature and robustness properties, and it can be used as starting point in more complex systems.

FPGA-Based Multimodal Embedded Sensor System Integrating Low- and Mid-Level Vision

Motion estimation is a low-level vision task that is especially relevant due to its wide range of applications in the real world. Many of the best motion estimation algorithms include some of the features that are found in mammalians, which would demand huge computational resources and therefore are not usually available in real-time. In this paper we present a novel bioinspired sensor based on the synergy between optical flow and orthogonal variant moments. The bioinspired sensor has been designed for Very Large Scale Integration (VLSI) using properties of the mammalian cortical motion pathway. This sensor combines low-level primitives (optical flow and image moments) in order to produce a mid-level vision abstraction layer. The results are described trough experiments showing the validity of the proposed system and an analysis of the computational resources and performance of the applied algorithms.

A low cost matching motion estimation sensor based on the NIOS II microprocessor.

This work presents the implementation of a matching-based motion estimation sensor on a Field Programmable Gate Array (FPGA) and NIOS II microprocessor applying a C to Hardware (C2H) acceleration paradigm. The design, which involves several matching algorithms, is mapped using Very Large Scale Integration (VLSI) technology. These algorithms, as well as the hardware implementation, are presented here together with an extensive analysis of the resources needed and the throughput obtained. The developed low-cost system is practical for real-time throughput and reduced power consumption and is useful in robotic applications, such as tracking, navigation using an unmanned vehicle, or as part of a more complex system.

Acceleration of block-matching algorithms using a custom instruction-based paradigm on a Nios II microprocessor

This contribution focuses on the optimization of matching-based motion estimation algorithms widely used for video coding standards using an Altera custom instruction-based paradigm and a combination of synchronous dynamic random access memory (SDRAM) with on-chip memory in Nios II processors. A complete profile of the algorithms is achieved before the optimization, which locates code leaks, and afterward, creates a custom instruction set, which is then added to the specific design, enhancing the original system. As well, every possible memory combination between on-chip memory and SDRAM has been tested to achieve the best performance. The final throughput of the complete designs are shown. This manuscript outlines a low-cost system, mapped using very large scale integration technology, which accelerates software algorithms by converting them into custom hardware logic blocks and showing the best combination between on-chip memory and SDRAM for the Nios II processor.

GPU‐based acceleration of bio‐inspired motion estimation model

In this paper, we describe the specific and efficient implementation of a gradient‐based optical flow model. This scheme was particularized using a validated neuromorphic motion estimation system for the robust extraction of image velocity. This model contains many characteristics that enhanced the capability when compared with other optical flow gradient family algorithms. Our implementation was performed using specific graphic processing units designed in an ad hoc framework for this model, which could be reused in several low‐level machine‐vision approaches. Observed performance results indicate that these accelerators be highly recommended. Furthermore, the throughput obtained in comparison with a general CPU was analyzed for the accurateness of a system built with regard to other optical flow systems. Additionally, several visual examples, commonly used for testing motion estimation sequences, were shown to reveal implementation behavior features. Copyright

Optimization of high speed pipelining in FPGA-based FIR filter design using genetic algorithm

This paper compares FPGA-based full pipelined multiplierless FIR filter design options. Comparison of Distributed Arithmetic (DA), Common Sub-Expression (CSE) sharing and n-dimensional Reduced Adder Graph (RAG-n) multiplierless filter design methods in term of size, speed, and A*T product are provided. Since DA designs are table-based and CSE/RAG-n designs are adder-based, FPGA synthesis design data are used for a realistic comparison. Superior results of a genetic algorithm based optimization of pipeline registers and non-output fundamental coefficients are shown. FIR filters (posted as open source by Kastner et al.) for filters in the length from 6 to 151 coefficients are used.

Dyna-H: A heuristic planning reinforcement learning algorithm applied to role-playing game strategy decision systems

In a Role-Playing Game, finding optimal trajectories is one of the most important tasks. In fact, the strategy decision system becomes a key component of a game engine. Determining the way in which decisions are taken (online, batch or simulated) and the consumed resources in decision making (e.g. execution time, memory) will influence, in mayor degree, the game performance. When classical search algorithms such as A* can be used, they are the very first option. Nevertheless, such methods rely on precise and complete models of the search space, and there are many interesting scenarios where their application is not possible. Then, model free methods for sequential decision making under uncertainty are the best choice. In this paper, we propose a heuristic planning strategy to incorporate the ability of heuristic-search in path-finding into a Dyna agent. The proposed Dyna-H algorithm, as A* does, selects branches more likely to produce outcomes than other branches. Besides, it has the advantages of being a model-free online reinforcement learning algorithm. The proposal was evaluated against the one-step Q-Learning and Dyna-Q algorithms obtaining excellent experimental results: Dyna-H significantly overcomes both methods in all experiments. We suggest also, a functional analogy between the proposed sampling from worst trajectories heuristic and the role of dreams (e.g. nightmares) in human behavior.

Stochastic stability analysis of competitive neural networks with different time-scales

Most computational models for competitive neural networks describe activity-connectivity interactions at different time-scales. We extend these existing models by considering stochastic processes and establish stability results based on the theory of singularly perturbed stochastic systems. Based on a reduced-order model we determine conditions that ensure the existence of the exponentially mean-square stability equilibria of the stochastic nonlinear system. It is assumed that the system is described by Ito-type equations. We derive a Lyapunov function for the coupled system and an upper bound for the parameters of the independent stochastic process.

Multi-GPU based on multicriteria optimization for motion estimation system

Graphics processor units (GPUs) offer high performance and power efficiency for a large number of data-parallel applications. Previous research has shown that a GPU-based version of a neuromorphic motion estimation algorithm can achieve a ×32 speedup using these devices. However, the memory consumption creates a bottleneck due to the expansive tree of signal processing operations performed. In the present contribution, an improvement in memory reduction was carried out, which limited accelerator viability usage. An evolutionary algorithm was used to find the best configuration. It supposes a trade-off solution between consumption resources, parallel efficiency, and accuracy. A multilevel parallel scheme was exploited: grain level by means of multi-GPU systems, and a finer level by data parallelism. In order to achieve a more relevant analysis, some optical flow benchmarks were used to validate this study. Satisfactory results opened the chance of building an intelligent motion estimation system that auto-adapted according to real-time, resource consumption, and accuracy requirements.

Early Experiences with OpenCL on FPGAs: Convolution Case Study

Many proprietary standards and tools have been designed in order to cover a closed set of architectures, and OpenCL has become a free standard for parallel programming on heterogeneous systems, which include custom devices, CPUs, GPUs, FPGAs. This work evaluates the use of the well-known convolution operator in signal processing disciplines focused on FPGA evaluation under different optimizations with respect to thread and memory level exploitation.