BIT-LEVEL SYSTOLIC ARRAYS FOR SIGNAL AND IMAGE PROCESSING.

This paper describes the design and the architecture of a bit-level systolic array processor. The bit-level systolic array described is directly applicable to a wide range of image processing operations where high performance and throughput are essential. The architecture is illustrated by describing the operation of the correlator and convolver chips which are being developed. The advantage of the system is also discussed.

Architectural synthesis of an image processing algorithm using IRIS

Details are presented of the IRIS synthesis system for high-performance digital signal processing. This tool allows non-specialists to automatically derive VLSI circuit architectures from high-level, algorithmic representations, and provides a quick route to silicon implementation. The applicability of the system is demonstrated using the design example of a one-dimensional Discrete Cosine Transform circuit.

Programmable image processing chip

A new high performance, programmable image processing chip targeted at video and HDTV applications is described. This was initially developed for image small object recognition but has much broader functional application including 1D and 2D FIR filtering as well as neural network computation. The core of the circuit is made up of an array of twenty one multiplication-accumulation cells based on systolic architecture. Devices can be cascaded to increase the order of the filter both vertically and horizontally. The chip has been fabricated in a 0.6 µ, low power CMOS technology and operates on 10 bit input data at over 54 Megasamples per second. The introduction gives some background to the chip design and highlights that there are few other comparable devices. Section 2 gives a brief introduction to small object detection. The chip architecture and the chip design will be described in detail in the later sections.

IPPro: FPGA based Image Processing Processor

The paper presents IPPro which is a high performance, scalable soft-core processor targeted for image processing applications. It has been based on the Xilinx DSP48E1 architecture using the ZYNQ Field Programmable Gate Array and is a scalar 16-bit RISC processor that operates at 526MHz, giving 526MIPS of performance. Each IPPro core uses 1 DSP48, 1 Block RAM and 330 Kintex-7 slice-registers, thus making the processor as compact as possible whilst maintaining flexibility and programmability. A key aspect of the approach is in reducing the application design time and implementation effort by using multiple IPPro processors in a SIMD mode. For different applications, this allows us to exploit different levels of parallelism and mapping for the specified processing architecture with the supported instruction set. In this context, a Traffic Sign Recognition (TSR) algorithm has been prototyped on a Zedboard with the colour and morphology operations accelerated using multiple IPPros. Simulation and experimental results demonstrate that the processing platform is able to achieve a speedup of 15 to 33 times for colour filtering and morphology operations respectively, with a reduced design effort and time.

Dataflow toolset for soft-core processors on FPGA for image processing applications

With security and surveillance, there is an increasing need to be able to process image data efficiently and effectively either at source or in a large data networks. Whilst Field Programmable Gate Arrays have been seen as a key technology for enabling this, they typically use high level and/or hardware description language synthesis approaches; this provides a major disadvantage in terms of the time needed to design or program them and to verify correct operation; it considerably reduces the programmability capability of any technique based on this technology. The work here proposes a different approach of using optimised soft-core processors which can be programmed in software. In particular, the paper proposes a design tool chain for programming such processors that uses the CAL Actor Language as a starting point for describing an image processing algorithm and targets its implementation to these custom designed, soft-core processors on FPGA. The main purpose is to exploit the task and data parallelism in order to achieve the same parallelism as a previous HDL implementation but avoiding the design time, verification and debugging steps associated with such approaches.

Inexact floating-point adder for dynamic image processing

Power has become a key constraint in current nanoscale integrated circuit design due to the increasing demands for mobile computing and a low carbon economy. As an emerging technology, an inexact circuit design offers a promising approach to significantly reduce both dynamic and static power dissipation for error tolerant applications. Although fixed-point arithmetic circuits have been studied in terms of inexact computing, floating-point arithmetic circuits have not been fully considered although require more power. In this paper, the first inexact floating-point adder is designed and applied to high dynamic range (HDR) image processing. Inexact floating-point adders are proposed by approximately designing an exponent subtractor and mantissa adder. Related logic operations including normalization and rounding modules are also considered in terms of inexact computing. Two HDR images are processed using the proposed inexact floating-point adders to show the validity of the inexact design. HDR-VDP is used as a metric to measure the subjective results of the image addition. Significant improvements have been achieved in terms of area, delay and power consumption. Comparison results show that the proposed inexact floating-point adders can improve power consumption and the power-delay product by 29.98% and 39.60%, respectively.

Streaming Elements for FPGA Signal and Image Processing Accelerators

Field programmable gate array devices boast abundant resources with which custom accelerator components for signal, image and data processing may be realised; however, realising high performance, low cost accelerators currently demands manual register transfer level design. Software-programmable ’soft’ processors have been proposed as a way to reduce this design burden but they are unable to support performance and cost comparable to custom circuits. This paper proposes a new soft processing approach for FPGA which promises to overcome this barrier. A high performance, fine-grained streaming processor, known as a Streaming Accelerator Element, is proposed which realises accelerators as large scale custom multicore networks. By adopting a streaming execution approach with advanced program control and memory addressing capabilities, typical program inefficiencies can be almost completely eliminated to enable performance and cost which are unprecedented amongst software-programmable solutions. When used to realise accelerators for fast fourier transform, motion estimation, matrix multiplication and sobel edge detection it is shown how the proposed architecture enables real-time performance and with performance and cost comparable with hand-crafted custom circuit accelerators and up to two orders of magnitude beyond existing soft processors.

FPGA based Streaming Image Processing Processor (SIPPro) architecture to accelerate data intensive applications

Current data-intensive image processing applications push traditional embedded architectures to their limits. FPGA based hardware acceleration is a potential solution but the programmability gap and time consuming HDL design flow is significant. The proposed research approach to develop “FPGA based programmable hardware acceleration platform” that uses, large number of Streaming Image processing Processors (SIPPro) potentially addresses these issues. SIPPro is pipelined in-order soft-core processor architecture with specific optimisations for image processing applications. Each SIPPro core uses 1 DSP48, 2 Block RAMs and 370 slice-registers, making the processor as compact as possible whilst maintaining flexibility and programmability. It is area efficient, scalable and high performance softcore architecture capable of delivering 530 MIPS per core using Xilinx Zynq SoC (ZC7Z020-3). To evaluate the feasibility of the proposed architecture, a Traffic Sign Recognition (TSR) algorithm has been prototyped on a Zedboard with the color and morphology operations accelerated using multiple SIPPros. Simulation and experimental results demonstrate that the processing platform is able to achieve a speedup of 15 and 33 times for color filtering and morphology operations respectively, with a significant reduced design effort and time.

FPGA-based soft-core processors for image processing applications

With security and surveillance, there is an increasing need to process image data efficiently and effectively either at source or in a large data network. Whilst a Field-Programmable Gate Array (FPGA) has been seen as a key technology for enabling this, the design process has been viewed as problematic in terms of the time and effort needed for implementation and verification. The work here proposes a different approach of using optimized FPGA-based soft-core processors which allows the user to exploit the task and data level parallelism to achieve the quality of dedicated FPGA implementations whilst reducing design time. The paper also reports some preliminary
progress on the design flow to program the structure. An implementation for a Histogram of Gradients algorithm is also reported which shows that a performance of 328 fps can be achieved with this design approach, whilst avoiding the long design time, verification and debugging steps associated with conventional FPGA implementations.

Discovery of Spatial Periodicities in a Coronal Loop Using Automated Edge-Tracking Algorithms

A new method for automated coronal loop tracking, in both spatial and temporal domains, is presented. Applying this technique to TRACE data, obtained using the 171 angstrom filter on 1998 July 14, we detect a coronal loop undergoing a 270 s kink-mode oscillation, as previously found by Aschwanden et al. However, we also detect flare-induced, and previously unnoticed, spatial periodicities on a scale of 3500 km, which occur along the coronal loop edge. Furthermore, we establish a reduction in oscillatory power for these spatial periodicities of 45% over a 222 s interval. We relate the reduction in detected oscillatory power to the physical damping of these loop-top oscillations.

Machine learning for transient discovery in Pan-STARRS1 difference imaging

Efficient identification and follow-up of astronomical transients is hindered by the need for humans to manually select promising candidates from data streams that contain many false positives. These artefacts arise in the difference images that are produced by most major ground-based time-domain surveys with large format CCD cameras. This dependence on humans to reject bogus detections is unsustainable for next generation all-sky surveys and significant effort is now being invested to solve the problem computationally. In this paper, we explore a simple machine learning approach to real-bogus classification by constructing a training set from the image data of similar to 32 000 real astrophysical transients and bogus detections from the Pan-STARRS1 Medium Deep Survey. We derive our feature representation from the pixel intensity values of a 20 x 20 pixel stamp around the centre of the candidates. This differs from previous work in that it works directly on the pixels rather than catalogued domain knowledge for feature design or selection. Three machine learning algorithms are trained (artificial neural networks, support vector machines and random forests) and their performances are tested on a held-out subset of 25 per cent of the training data. We find the best results from the random forest classifier and demonstrate that by accepting a false positive rate of 1 per cent, the classifier initially suggests a missed detection rate of around 10 per cent. However, we also find that a combination of bright star variability, nuclear transients and uncertainty in human labelling means that our best estimate of the missed detection rate is approximately 6 per cent.

Confounds in pictorial sets: The role of complexity and familiarity in basic-level picture processing

Complexity is conventionally defined as the level of detail or intricacy contained within a picture. The study of complexity has received relatively little attention-in part, because of the absence of an acceptable metric. Traditionally, normative ratings of complexity have been based on human judgments. However, this study demonstrates that published norms for visual complexity are biased. Familiarity and learning influence the subjective complexity scores for nonsense shapes, with a significant training x familiarity interaction [F(1,52) = 17.53, p <.05]. Several image-processing techniques were explored as alternative measures of picture and image complexity. A perimeter detection measure correlates strongly with human judgments of the complexity of line drawings of real-world objects and nonsense shapes and captures some of the processes important in judgments of subjective complexity, while removing the bias due to familiarity effects.

An optimisation of Gaussian mixture models for integer processing units

This paper investigates sub-integer implementations of the adaptive Gaussian mixture model (GMM) for background/foreground segmentation to allow the deployment of the method on low cost/low power processors that lack Floating Point Unit (FPU). We propose two novel integer computer arithmetic techniques to update Gaussian parameters. Specifically, the mean value and the variance of each Gaussian are updated by a redefined and generalised "round'' operation that emulates the original updating rules for a large set of learning rates. Weights are represented by counters that are updated following stochastic rules to allow a wider range of learning rates and the weight trend is approximated by a line or a staircase. We demonstrate that the memory footprint and computational cost of GMM are significantly reduced, without significantly affecting the performance of background/foreground segmentation.