Low-cost, high-speed computer vision using NVIDIA's CUDA architecture

Park, Seung In; Ponce, Sean P.; Jing, Huang; Cao, Yong; Quek, Francis

doi:10.1109/aipr.2008.4906458

Cited by 29 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature tracking refers to the process of extracting dynamics, which seeks to identify and describe movement or transport of data. Feature tracking techniques can be broadly classified into: (i) pixel‐based [RdE90] [Adi] [PPH*08], or (ii) feature‐based. Pixel‐based tracking methods have the disadvantage that they require small time steps for accurate matching.…”

Section: Background and Related Workmentioning

confidence: 99%

Interactive Fusion and Tracking For Multi‐Modal Spatial Data Visualization

Gračanin

Gad

Elmongui

et al. 2015

Computer Graphics Forum

View full text Add to dashboard Cite

Scientific data acquired through sensors which monitor natural phenomena, as well as simulation data that imitate time-identified events, have fueled the need for interactive techniques to successfully analyze and understand trends and patterns across space and time. We present a novel interactive visualization technique that fuses ground truth measurements with simulation results in real-time to support the continuous tracking and analysis of spatiotemporal patterns. We start by constructing a reference model which densely represents the expected temporal behavior, and then use GPU parallelism to advect measurements on the model and track their location at any given point in time. Our results show that users can interactively fill the spatio-temporal gaps in real world observations, and generate animations that accurately describe physical phenomena.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Interactive Fusion and Tracking For Multi‐Modal Spatial Data Visualization

Gračanin

Gad

Elmongui

et al. 2015

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Regarding Canny algorithm [2], the vast majority of the related works refer to GPU architectures; although the proposed methodology can be extended to these architectures, this is not the scope of this paper. In [42][43][44][45][46][47][48][49], the Canny algorithm is optimized in several GPU architectures. Also, Zhang et al [50] present experiments in parallelizing an edge detection algorithm on three representative message passing architectures: a low cost heterogeneous PVM network, an Intel iPSC/860 hypercube, and a CM-5 massively parallel multicomputer.…”

Section: Related Workmentioning

confidence: 99%

A methodology for speeding up edge and line detection algorithms focusing on memory architecture utilization

2013

View full text Add to dashboard Cite

In this paper, a new methodology for speeding up edge and line detection algorithms is presented, achieving improved performance over the state of the art software library OpenCV (speedup from 1.35 up to 2.22) and other conventional implementations, in both general and embedded processors, by reducing the number of load/store and arithmetic instructions, the number of data cache accesses and data cache misses in memory hierarchy and the algorithm memory size. This is achieved by fully exploiting the combination of the software and hardware parameters which are considered simultaneously as one problem and not separately. Furthermore, the edge and line detection algorithms have been simplified for a computer vision application in a Virtex-5 Xilinx FPGA using Microblaze soft processor (detection and measurement of flow fronts in a microfluid device); it achieves speedup up to 660 times in comparison with conventional software implementations.

show abstract

“…Graphics Processing Units (GPUs) provide massive computational throughput for a wide spectrum of applications from various domains such as computer vision [42], inance [37,49], machine learning [1,18], and bioinformatics [55]. As progressively more applications get ported to GPUs for parallelization, the shortcomings of the traditional GPU execution model become evident.…”

Section: Introductionmentioning

confidence: 99%

Quantifying Data Locality in Dynamic Parallelism in GPUs

Tang

Pattnaik

Kayıran

et al. 2018

Proc. ACM Meas. Anal. Comput. Syst.

View full text Add to dashboard Cite

GPUs are becoming prevalent in various domains of computing and are widely used for streaming (regular) applications. However, they are highly inefficient when executing irregular applications with unstructured inputs due to load imbalance. Dynamic parallelism (DP) is a new feature of emerging GPUs that allows new kernels to be generated and scheduled from the device-side (GPU) without the host-side (CPU) intervention to increase parallelism. To efficiently support DP, one of the major challenges is to saturate the GPU processing elements and provide them with the required data in a timely fashion. There have been considerable efforts focusing on exploiting data locality in GPUs. However, there is a lack of quantitative analysis of how irregular applications using dynamic parallelism behave in terms of data reuse. In this paper, we quantitatively analyze the data reuse of dynamic applications in three different granularities of schedulable units: kernel, work-group, and wavefront. We observe that, for DP applications, data reuse is highly irregular and is heavily dependent on the application and its input. Thus, existing techniques cannot exploit data reuse effectively for DP applications. To this end, we first conduct a limit study on the performance improvements that can be achieved by hardware schedulers that are provided with accurate data reuse information. This limit study shows that, on an average, the performance improves by 19.4% over the baseline scheduler. Based on the key observations from the quantitative analysis of our DP applications, we next propose LASER, a Locality-Aware SchedulER, where the hardware schedulers employ data reuse monitors to help make scheduling decisions to improve data locality at runtime. Our experimental results on 16 benchmarks show that LASER, on an average, can improve performance by 11.3%.

show abstract

Low-cost, high-speed computer vision using NVIDIA's CUDA architecture

Cited by 29 publications

References 5 publications

Interactive Fusion and Tracking For Multi‐Modal Spatial Data Visualization

Interactive Fusion and Tracking For Multi‐Modal Spatial Data Visualization

A methodology for speeding up edge and line detection algorithms focusing on memory architecture utilization

Quantifying Data Locality in Dynamic Parallelism in GPUs

Contact Info

Product

Resources

About