FPGA-based circular hough transform with graph clustering for vision-based multi-robot tracking

Irwansyah, Arif; Ibraheem, Omar W.; Hagemeyer, Jens; Porrmann, Mario; Rueckert, Ulrich

doi:10.1109/reconfig.2015.7393313

Cited by 8 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our FPGA based architecture for a real-time implementation of the 1D Hough transform multi-circles detection is focused on the acceleration of the construction of histograms V x and V y, [1 -7] and [8][9][10][11][12][13][14] respectively to the algorithm 1. Our solution significantly reduces the use of memory and the latency execution.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…Our solution significantly reduces the use of memory and the latency execution. First, we propose an equivalent algorithm, algorithm 2, which gives the same results, that is to say the same x-coordinate and y-coordinate histograms as in steps [1 -7] and [8][9][10][11][12][13][14] of the algorithm 1.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…Here, we present the highlights found, a survey of Hough transform methods can be read in [2] and [13]. We can notice some facts: 1) all the FPGA implementations [1], [3], [19], [16], [8], [11] use embedded internal memories or BRAMs (Block RAMs), 2) all the works consider only the acceleration of the voting process of the Hough transform. In this process the goal is to accumulate intersection points in the Hough parameter space, corresponding to the number of possible circles.…”

Section: State Of the Artmentioning

confidence: 99%

“…Then a vote is done to find the local maximum that are considered as real circle. This process is memory and time consuming, two different approaches emerged, the first approach uses the original Hough transform algorithm were the parametric equations of a circle are used to find the center and the radius of the circles [1], [3], [16], [8], [11] and the second approach uses a modified version of Hough transform called One dimensional Hough transform algorithm [19]. We describe below the works related to both approaches.…”

Section: State Of the Artmentioning

confidence: 99%

“…In [8], authors propose a Hough transform algorithm combined with a graph clustering algorithm for FPGA-based multi-circle detection.…”

Section: A Original Hough Transform Implementationsmentioning

confidence: 99%

See 4 more Smart Citations

FPGA-Based Real Time Embedded Hough Transform Architecture for Circles Detection

Chuquimia¹,

Pinna²,

Christophel³

et al. 2018

2018 Conference on Design and Architectures for Signal and Image Processing (DASIP)

View full text Add to dashboard Cite

Hough Transform is a widely used shapebased algorithm for object detection and localization [6], this technique can be generalized to parametric curves as circles. For a real time execution and embedded integration, several optimizations are necessary due to the large memory and computational requirements. This paper presents an efficient real-time pipelined architecture with a FPGA implementation of our Hough Transform for multi-circles detection. The computation of center candidates was improved. A three stages pipeline architecture was designed in order to reduce the processing latency and cadence. The architecture has been integrated into a Xilinx Zynq-7000 XC7Z020 containing a FPGA Artix-7. The global system uses 78.5 BRAMs, 153 DSP slices, 21638 LUTs. Our global system can support a maximum clock frequency of 128.89 MHz. We validate our architecture using a 125MHz clock frequency and we obtain a latency of 33.214 ms and an interval between two images of 16,607 ms for a 1920x1080 pixels image. According to our results, our architecture offer a throughput more than 4 times better than the faster state of the art architecture.

show abstract