Embedded Hardware-Efficient Real-Time Classification With Cascade Support Vector Machines. Kyrkou, C.; Bouganis, C. S.; Theocharides, T.; and Polycarpou, M. M. 27(1):99–112.
doi  abstract   bibtex   
Cascade support vector machines (SVMs) are optimized to efficiently handle problems, where the majority of the data belong to one of the two classes, such as image object classification, and hence can provide speedups over monolithic (single) SVM classifiers. However, SVM classification is a computationally demanding task and existing hardware architectures for SVMs only consider monolithic classifiers. This paper proposes the acceleration of cascade SVMs through a hybrid processing hardware architecture optimized for the cascade SVM classification flow, accompanied by a method to reduce the required hardware resources for its implementation, and a method to improve the classification speed utilizing cascade information to further discard data samples. The proposed SVM cascade architecture is implemented on a Spartan-6 field-programmable gate array (FPGA) platform and evaluated for object detection on 800×600 (Super Video Graphics Array) resolution images. The proposed architecture, boosted by a neural network that processes cascade information, achieves a real-time processing rate of 40 frames/s for the benchmark face detection application. Furthermore, the hardware-reduction method results in the utilization of 25% less FPGA custom-logic resources and 20% peak power reduction compared with a baseline implementation.
@article{kyrkouEmbeddedHardwareEfficientRealTime2016,
  title = {Embedded {{Hardware}}-{{Efficient Real}}-{{Time Classification With Cascade Support Vector Machines}}},
  volume = {27},
  issn = {21622388},
  doi = {10.1109/TNNLS.2015.2428738},
  abstract = {Cascade support vector machines (SVMs) are optimized to efficiently handle problems, where the majority of the data belong to one of the two classes, such as image object classification, and hence can provide speedups over monolithic (single) SVM classifiers. However, SVM classification is a computationally demanding task and existing hardware architectures for SVMs only consider monolithic classifiers. This paper proposes the acceleration of cascade SVMs through a hybrid processing hardware architecture optimized for the cascade SVM classification flow, accompanied by a method to reduce the required hardware resources for its implementation, and a method to improve the classification speed utilizing cascade information to further discard data samples. The proposed SVM cascade architecture is implemented on a Spartan-6 field-programmable gate array (FPGA) platform and evaluated for object detection on 800×600 (Super Video Graphics Array) resolution images. The proposed architecture, boosted by a neural network that processes cascade information, achieves a real-time processing rate of 40 frames/s for the benchmark face detection application. Furthermore, the hardware-reduction method results in the utilization of 25\% less FPGA custom-logic resources and 20\% peak power reduction compared with a baseline implementation.},
  number = {1},
  journaltitle = {IEEE Transactions on Neural Networks and Learning Systems},
  date = {2016},
  pages = {99--112},
  keywords = {Cascade classifier,field-programmable gate array (FPGA),local binary pattern (LBP),neural networks (NNs),parallel architectures,real-time and embedded systems,support vector machines (SVMs)},
  author = {Kyrkou, Christos and Bouganis, Christos Savvas and Theocharides, Theocharis and Polycarpou, Marios M.},
  file = {/home/dimitri/Nextcloud/Zotero/storage/5LBY3ARV/Unknown - Unknown - Embedded Hardware-Efficient Real-Time Classification with Cascade Support Vector Machines.pdf},
  eprinttype = {pmid},
  eprint = {26011869}
}
Downloads: 0