Parallelization strategies of the canny edge detector for multi-core CPUs and many-core GPUs

Cheikh, Taieb Lamine Ben; Beltrame, Giovanni; Nicolescu, Gabriela; Cheriet, Foued; Tahar, Sofiène

doi:10.1109/newcas.2012.6328953

Cited by 6 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The smoothing process is usually performed using a fixed predetermined Sigma value [14]- [19]. However, because of the direct correlation between the degree of smoothing and the Sigma value (this value itself corresponds to the standard deviation of the Gaussian filter), it may be reasonable to change the Sigma value if the input image specification changes.…”

Section: A Canny Parameters and Performancementioning

confidence: 99%

“…predefined sizes and coefficients), supported by a Gaussian filter implementation capable of working flexibly with each of those kernels. Table 4 indicates that based on the experiments setup (MDP and noise intensity ranges), only four (out of 14) distinct Sigma values (i.e. 0.9, 1.1, 1.3 and 1.5) are enough to satisfy the requirements of the proposed APS Canny implementation.…”

Section: B Adaptive Smoothing Modulementioning

confidence: 99%

See 1 more Smart Citation

Noise-Robust, Reconfigurable Canny Edge Detection and its Hardware Realization

Kalbasi

Nikmehr

2020

IEEE Access

View full text Add to dashboard Cite

Edge detection is a common operation in image/video processing applications. Canny edge detection, which performs well in different conditions, is one of the most popular and widely used of these algorithms. Canny's superior performance is due mainly to its provision of the ability to adjust the output quality by manipulating the edge detection parameters, Sigma and Threshold. Calculating values for these two parameters on-the-fly and based on the application's circumstances requires additional preprocessing, which increases the algorithm's computational complexity. To reduce the complexity, several proposed methods simply employ precalculated, fixed values for the Canny parameters (based on either the worst or typical conditions), which sacrifices the edge detection's performance in favor of the computational complexity. In this paper, an adaptive parameter selection method is proposed that selects values for the Canny parameters from a configuration table (rather than calculating in run-time), based on the estimated noise intensity of the input image and the minimum output performance that can satisfy the application requirements. This adaptive implementation of the Canny algorithm ensures that, while the edge detection performance (noise robustness) is higher than state-of-the-art counterparts in different circumstances, the execution time of the proposed Canny remains lower than those of recent cutting-edge Canny realizations. INDEX TERMS Adaptive systems, Gaussian noise, computational complexity, image edge detection, reconfigurable architectures. HOOMAN NIKMEHR received the B.Sc. degree in electronic engineering and the M.Sc. degree in computer architecture engineering from the University of Tehran, Tehran, Iran, in 1992 and 1997, respectively, and the Ph.D. degree in computer engineering from

show abstract

Section: A Canny Parameters and Performancementioning

confidence: 99%

Section: B Adaptive Smoothing Modulementioning

confidence: 99%

Noise-Robust, Reconfigurable Canny Edge Detection and its Hardware Realization

Kalbasi

Nikmehr

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To overcome this drawback, an attempt is made to make the conventional edge detectors to operate in a parallel environment [1,2,8,12,15]. In any multi-core CPU and on many-core Graphics Processors Units (GPU), parallelization can be employed using various strategies.…”

Section: Related Workmentioning

confidence: 99%

“…Parallelization is an efficient solution for applications that process enormous amount of data which requires huge computational time. In [1], two strategies are proposed namely, loop-level parallelism and domain decomposition, for Canny Edge Detection. The impact of data size on scalability is evaluated using different sizes (512x512 and 2048x2048) of images.…”

Section: Related Workmentioning

confidence: 99%

Parallel Algorithms for Edge Detection in an Image

Mala

Sridevi

2014

2014 17th International Conference on Network-Based Information Systems

View full text Add to dashboard Cite

Edge detection is an important process in image segmentation, object recognition, template matching, etc. It computes gradients in both horizontal and vertical directions of the image at each pixel position to find the image boundaries. The conventional edge detectors take significant time to detect the edges in the image. To reduce the computational time, this paper proposes parallel algorithms for edge detection with Sobel, Prewitt and Robert first order derivatives using a Shared Memory -Single Instruction Multiple Data (SM -SIMD) parallel architecture. From the experimental results, it is inferred that the proposed parallel algorithms for edge detection are faster than the conventional methods.

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

Parallelization strategies of the canny edge detector for multi-core CPUs and many-core GPUs

Cited by 6 publications

References 7 publications

Noise-Robust, Reconfigurable Canny Edge Detection and its Hardware Realization

Noise-Robust, Reconfigurable Canny Edge Detection and its Hardware Realization

Parallel Algorithms for Edge Detection in an Image

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

Contact Info

Product

Resources

About