An Efficient Hardware-Oriented Single-Pass Approach for Connected Component Analysis
作者： Fanny Spagnolo , Stefania Perri , Pasquale Corsonello
DOI: 10.3390/S19143055
关键词:
摘要: Connected Component Analysis (CCA) plays an important role in several image analysis and pattern recognition algorithms. Being one of the most time-consuming tasks such applications, specific hardware accelerator for CCA are highly desirable. As its main characteristic, design must be able to complete a run-time process input frame without suspending streaming data-flow, by using reasonable amount resources. This paper presents new approach that allows virtually any feature interest extracted single-pass from frames. The proposed method has been validated proper system implemented heterogeneous design, within Xilinx Zynq-7000 Field Programmable Gate Array (FPGA) System on Chip (SoC) device. For processing 640 × 480 resolution, only 760 LUTs 787 FFs were required. Moreover, frame-rate ~325 fps throughput 95.37 Mp/s achieved. When compared recent competitors, exhibits favorable performance-resources trade-off.
mdpi.com
sci-hub.se 参考文章(27)
Robert Walczyk, Alistair Armitage, T. David Binnie, Comparative study on connected component labeling algorithms for embedded video processing systems. IPCV. pp. 853- 859 ,(2010)
Brent E. Tweddle, Alvar Saenz-Otero, Relative Computer Vision-Based Navigation for Small Inspection Spacecraft Journal of Guidance Control and Dynamics. ,vol. 38, pp. 969- 978 ,(2015) , 10.2514/1.G000687
Abdul Waheed Malik, Benny Thörnberg, Muhammad Imran, Najeem Lawal, Hardware Architecture for Real-Time Computation of Image Component Feature Descriptors on a FPGA: International Journal of Distributed Sensor Networks. ,vol. 10, pp. 815378- ,(2014) , 10.1155/2014/815378
Phaisarn Sutheebanjard, Wichian Premchaiswadi, Efficient scan mask techniques for connected components labeling algorithm Eurasip Journal on Image and Video Processing. ,vol. 2011, pp. 14- ,(2011) , 10.1186/1687-5281-2011-14
Sedat Nazlibilek, Deniz Karacor, Tuncay Ercan, Murat Husnu Sazli, Osman Kalender, Yavuz Ege, Automatic segmentation, counting, size determination and classification of white blood cells Measurement. ,vol. 55, pp. 58- 65 ,(2014) , 10.1016/J.MEASUREMENT.2014.04.008
S. L. Happy, Aurobinda Routray, Automatic Facial Expression Recognition Using Features of Salient Facial Patches IEEE Transactions on Affective Computing. ,vol. 6, pp. 1- 12 ,(2015) , 10.1109/TAFFC.2014.2386334
Kesheng Wu, Ekow Otoo, Kenji Suzuki, Optimizing two-pass connected-component labeling algorithms Pattern Analysis and Applications. ,vol. 12, pp. 117- 135 ,(2009) , 10.1007/S10044-008-0109-Y
Omar Abuzaghleh, Buket D. Barkana, Miad Faezipour, Noninvasive Real-Time Automated Skin Lesion Analysis System for Melanoma Early Detection and Prevention IEEE Journal of Translational Engineering in Health and Medicine. ,vol. 3, pp. 2900310- 2900310 ,(2015) , 10.1109/JTEHM.2015.2419612
Lifeng He, Yuyan Chao, Kenji Suzuki, Kesheng Wu, Fast connected-component labeling Pattern Recognition. ,vol. 42, pp. 1977- 1987 ,(2009) , 10.1016/J.PATCOG.2008.10.013
Vikram Sampath Kumar, Kevin Irick, Ahmed Al Maashri, N. Vijaykrishnan, A Scalable Bandwidth Aware Architecture for Connected Component Labeling ieee computer society annual symposium on vlsi. pp. 116- 121 ,(2010) , 10.1109/ISVLSI.2010.89