{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T14:51:55Z","timestamp":1740149515569,"version":"3.37.3"},"reference-count":32,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2022,3,11]],"date-time":"2022-03-11T00:00:00Z","timestamp":1646956800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"In recent years there has been an increase in the number of research and developments in deep learning solutions for object detection applied to driverless vehicles. This application benefited from the growing trend felt in innovative perception solutions, such as LiDAR sensors. Currently, this is the preferred device to accomplish those tasks in autonomous vehicles. There is a broad variety of research works on models based on point clouds, standing out for being efficient and robust in their intended tasks, but they are also characterized by requiring point cloud processing times greater than the minimum required, given the risky nature of the application. This research work aims to provide a design and implementation of a hardware IP optimized for computing convolutions, rectified linear unit (ReLU), padding, and max pooling. This engine was designed to enable the configuration of features such as varying the size of the feature map, filter size, stride, number of inputs, number of filters, and the number of hardware resources required for a specific convolution. Performance results show that by resorting to parallelism and quantization approach, the proposed solution could reduce the amount of logical FPGA resources by 40 to 50%, enhancing the processing time by 50% while maintaining the deep learning operation accuracy.<\/jats:p>","DOI":"10.3390\/s22062184","type":"journal-article","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T01:44:17Z","timestamp":1647222257000},"page":"2184","source":"Crossref","is-referenced-by-count":7,"title":["Customizable FPGA-Based Hardware Accelerator for Standard Convolution Processes Empowered with Quantization Applied to LiDAR Data"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4772-8659","authenticated-orcid":false,"given":"Jo\u00e3o","family":"Silva","sequence":"first","affiliation":[{"name":"Algoritmi Centre, University of Minho, 4800-058 Guimaraes, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1723-421X","authenticated-orcid":false,"given":"Pedro","family":"Pereira","sequence":"additional","affiliation":[{"name":"Algoritmi Centre, University of Minho, 4800-058 Guimaraes, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9929-8705","authenticated-orcid":false,"given":"Rui","family":"Machado","sequence":"additional","affiliation":[{"name":"Algoritmi Centre, University of Minho, 4800-058 Guimaraes, Portugal"},{"name":"Associa\u00e7\u00e3o Laborat\u00f3rio Colaborativo em Transforma\u00e7\u00e3o Digital\u2014DTx Colab, 4800-058 Guimaraes, Portugal"}]},{"given":"Rafael","family":"N\u00e9voa","sequence":"additional","affiliation":[{"name":"Algoritmi Centre, University of Minho, 4800-058 Guimaraes, Portugal"},{"name":"Bosch Company, 4700-113 Braga, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8257-0143","authenticated-orcid":false,"given":"Pedro","family":"Melo-Pinto","sequence":"additional","affiliation":[{"name":"Algoritmi Centre, University of Minho, 4800-058 Guimaraes, Portugal"},{"name":"Centre for Research and Technology of Agro-Environmental and Biological Sciences, University of Tr\u00e1s-os-Montes and Alto Douro, 5000-801 Vila Real, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9736-5812","authenticated-orcid":false,"given":"Duarte","family":"Fernandes","sequence":"additional","affiliation":[{"name":"Algoritmi Centre, University of Minho, 4800-058 Guimaraes, Portugal"},{"name":"Associa\u00e7\u00e3o Laborat\u00f3rio Colaborativo em Transforma\u00e7\u00e3o Digital\u2014DTx Colab, 4800-058 Guimaraes, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1109\/MM.2015.133","article-title":"An open approach to autonomous vehicles","volume":"35","author":"Kato","year":"2015","journal-title":"IEEE Micro"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"101823","DOI":"10.1016\/j.adhoc.2018.12.006","article-title":"A review on safety failures, security attacks, and available countermeasures for autonomous vehicles","volume":"90","author":"Cui","year":"2019","journal-title":"Ad Hoc Netw."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Li, Y., Ma, L., Zhong, Z., Liu, F., Cao, D., Li, J., and Chapman, M.A. (2020). Deep learning for lidar point clouds in autonomous driving: A review. arXiv.","DOI":"10.1109\/TNNLS.2020.3015992"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., and Xia, T. (2016). Multiview 3d object detection network for autonomous driving. arXiv.","DOI":"10.1109\/CVPR.2017.691"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., and Waslander, S.L. (2017). Joint 3d proposal generation and object detection from view aggregation. arXiv.","DOI":"10.1109\/IROS.2018.8594049"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., and Beijbom, O. (2018). Pointpillars: Fast encoders for object detection from point clouds. arXiv.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhou, Y., and Tuzel, O. (2017). Voxelnet: End-to-end learning for point cloud based 3d object detection. arXiv.","DOI":"10.1109\/CVPR.2018.00472"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., and Guibas, L.J. (2017). Frustum pointnets for 3d object detection from rgb-d data. arXiv.","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref_9","unstructured":"Wang, B., An, J., and Cao, J. (2019). Voxel-fpn: Multi-scale voxel feature aggregation in 3d object detection from point clouds. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wang, Z., and Jia, K. (2019). Frustum convnet: Sliding frustums to aggregate local point-wise features for amodal 3d object detection. arXiv.","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"ref_11","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2016). Pointnet: Deep learning on point sets for 3d classification and segmentation. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yang, B., Luo, W., and Urtasun, R. (2019). PIXOR: Real-time 3d object detection from point clouds. arXiv.","DOI":"10.1109\/CVPR.2018.00798"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chen, Y.-H., Member, S., Yang, T.-J., Emer, J., Sze, V., and Member, S. (2019). Eyeriss v2: A flexible accelerator for emerging deep neural networks on mobile devices. arXiv.","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Desoli, G., Chawla, N., Boesch, T., Singh, S., Guidetti, E., de Ambroggi, F., Majo, T., Zambotti, P., Ayodhyawasi, M., and Singh, H. (2017, January 5\u20139). 14.1 a 2.9tops\/w deep convolutional neural network soc in fd-soi 28 nm for intelligent embedded systems. Proceedings of the 2017 IEEE International Solid-State Circuits Conference (ISSCC), San Francisco, CA, USA.","DOI":"10.1109\/ISSCC.2017.7870349"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., and Cong, J. (2015). Optimizing Fpga-Based Accelerator Design for Deep Convolutional Neural Networks, Association for Computing Machinery, Inc.","DOI":"10.1145\/2684746.2689060"},{"key":"ref_16","unstructured":"Jahanshahi, A. (2019). Tinycnn: A tiny modular CNN accelerator for embedded FPGA. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Shen, Y., Ferdman, M., and Milder, P. (2017). Maximizing CNN accelerator efficiency through resource partitioning. arXiv.","DOI":"10.1145\/3079856.3080221"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4196","DOI":"10.1109\/TCSI.2018.2840092","article-title":"Energy-efficient convolution architecture based on rescheduled dataflow","volume":"65","author":"Jo","year":"2018","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"ref_19","unstructured":"O\u2019Shea, K., and Nash, R. (2015). An introduction to convolutional neural networks. arXiv."},{"key":"ref_20","unstructured":"LeCun, Y. (2021, March 09). Lenet-5, Convolutional Neural Networks. Available online: Http:\/\/yann.lecun.com\/exdb\/lenet."},{"key":"ref_21","unstructured":"Zhang, X., Zou, J., He, K., and Sun, J. (2015). Accelerating very deep convolutional networks for classification and detection. arXiv."},{"key":"ref_22","unstructured":"Targ, S., Almeida, D., and Lyman, K. (2016). Resnet in resnet: Generalizing residual architectures. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1109\/JSSC.2016.2616357","article-title":"Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks","volume":"52","author":"Chen","year":"2017","journal-title":"IEEE J. Solid-State Circuits"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lo, C.Y., and Sham, C.-W. (2020, January 9\u201312). Energy Efficient Fixed-point Inference System of Convolutional Neural Network. Proceedings of the 2020 IEEE 63rd International Midwest Symposium on Circuits and Systems (MWSCAS), Springfield, MA, USA.","DOI":"10.1109\/MWSCAS48704.2020.9184436"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ansari, A., and Ogunfunmi, T. (2019, January 4\u20137). Empirical analysis of fixed point precision quantization of CNNs. Proceedings of the 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS), Dallas, TX, USA.","DOI":"10.1109\/MWSCAS.2019.8885263"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Lo, C.Y., Lau, F.C.-M., and Sham, C.-W. (2018, January 18\u201320). FixedPoint Implementation of Convolutional Neural Networks for Image Classification. Proceedings of the 2018 International Conference on Advanced Technologies for Communications (ATC), Ho Chi Minh City, Vietnam.","DOI":"10.1109\/ATC.2018.8587580"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1478","DOI":"10.1109\/TNS.2020.2983662","article-title":"Understanding the impact of quantization, accuracy, and radiation on the reliability of convolutional neural networks on fpgas","volume":"67","author":"Libano","year":"2020","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"ref_28","unstructured":"Xilinx Inc. (2020). Convolutional Neural Network with INT4 Optimization on Xilinx Devices 2 Convolutional Neural Network with INT4 Optimization on Xilinx Devices, Xilinx Inc."},{"key":"ref_29","unstructured":"Fu, Y., Wu, E., and Sirasao, A. (2017). 8-Bit Dot-Product Acceleration White Paper (wp487), Xilinx Inc."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Vestias, M.P., Duarte, R.P., de Sousa, J.T., and Neto, H. (2019, January 8\u201312). Hybrid dot-product calculation for convolutional neural networks in FPGA. Proceedings of the 2019 29th International Conference on Field Programmable Logic and Applications (FPL), Barcelona, Spain.","DOI":"10.1109\/FPL.2019.00062"},{"key":"ref_31","unstructured":"Xilinx Inc. (2021). Ultrascale Architecture DSP Slice User Guide, Xilinx Inc."},{"key":"ref_32","unstructured":"Diligent Inc. (2018). Zybo Z7 Board Reference Manual, Diligent Inc."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/6\/2184\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,27]],"date-time":"2024-07-27T07:51:26Z","timestamp":1722066686000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/6\/2184"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,11]]},"references-count":32,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,3]]}},"alternative-id":["s22062184"],"URL":"https:\/\/doi.org\/10.3390\/s22062184","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,3,11]]}}}