{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:11:50Z","timestamp":1760242310575,"version":"build-2065373602"},"reference-count":21,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2017,4,12]],"date-time":"2017-04-12T00:00:00Z","timestamp":1491955200000},"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":"<jats:p>While most filtering approaches based on random finite sets have focused on improving performance, in this paper, we argue that computation times are very important in order to enable real-time applications such as pedestrian detection. Towards this goal, this paper investigates the use of OpenCL to accelerate the computation of random finite set-based Bayesian filtering in a heterogeneous system. In detail, we developed an efficient and fully-functional pedestrian-tracking system implementation, which can run under real-time constraints, meanwhile offering decent tracking accuracy. An extensive evaluation analysis was carried out to ensure the fulfillment of sufficient accuracy requirements. This was followed by extensive profiling analysis to spot the potential bottlenecks in terms of execution performance, which were then targeted to come up with an OpenCL accelerated application. Video-throughput improvements from roughly 15 fps to 100 fps (6\u00d7) were observed on average while processing typical MOT benchmark videos. Moreover, the worst-case frame processing yielded an 18\u00d7 advantage from nearly 2 fps to 36 fps, thereby comfortably meeting the real-time constraints. Our implementation is released as open-source code.<\/jats:p>","DOI":"10.3390\/s17040843","type":"journal-article","created":{"date-parts":[[2017,4,12]],"date-time":"2017-04-12T10:15:06Z","timestamp":1491992106000},"page":"843","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Random Finite Set Based Bayesian Filtering with OpenCL in a Heterogeneous Platform"],"prefix":"10.3390","volume":"17","author":[{"given":"Biao","family":"Hu","sequence":"first","affiliation":[{"name":"Robotics and Embedded Systems, Technische Universit\u00e4t M\u00fcnchen, 80333 M\u00fcnchen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Uzair","family":"Sharif","sequence":"additional","affiliation":[{"name":"Robotics and Embedded Systems, Technische Universit\u00e4t M\u00fcnchen, 80333 M\u00fcnchen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajat","family":"Koner","sequence":"additional","affiliation":[{"name":"Robotics and Embedded Systems, Technische Universit\u00e4t M\u00fcnchen, 80333 M\u00fcnchen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang","family":"Chen","sequence":"additional","affiliation":[{"name":"Robotics and Embedded Systems, Technische Universit\u00e4t M\u00fcnchen, 80333 M\u00fcnchen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Data and Computer Science, Sun Yat-sen University, Xiaoguwei Island, Panyu District, Guangzhou 510006, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1774-727X","authenticated-orcid":false,"given":"Feihu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Marine Science and Technology, Northwestern Polytechnical University, 127, Youyi West Road, Xi\u2019an 710072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Walter","family":"Stechele","sequence":"additional","affiliation":[{"name":"Integrated Systems, Technische Universit\u00e4t M\u00fcnchen, 80333 M\u00fcnchen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Robotics and Embedded Systems, Technische Universit\u00e4t M\u00fcnchen, 80333 M\u00fcnchen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2017,4,12]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"4091","DOI":"10.1109\/TSP.2006.881190","article-title":"The Gaussian mixture probability hypothesis density filter","volume":"54","author":"Vo","year":"2006","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.inffus.2011.08.001","article-title":"Multisensor data fusion: A review of the state-of-the-art","volume":"14","author":"Khaleghi","year":"2013","journal-title":"Inf. Fusion"},{"key":"ref_3","unstructured":"Leal-Taix\u00e9, L., Milan, A., Reid, I., Roth, S., and Schindler, K. (arXiv, 2015). MOTChallenge 2015: Towards a benchmark for multi-target tracking, arXiv."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"6554","DOI":"10.1109\/TSP.2014.2364014","article-title":"Labeled random finite sets and the Bayes multi-target tracking filter","volume":"62","author":"Vo","year":"2014","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1975","DOI":"10.1109\/TSP.2016.2641392","article-title":"An Efficient Implementation of the Generalized Labeled Multi-Bernoulli Filter","volume":"65","author":"Vo","year":"2016","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_6","unstructured":"Bar-Shalom, Y. (1987). Tracking and Data Association, Academic Press Professional, Inc."},{"key":"ref_7","unstructured":"Goodman, I.R., Mahler, R.P., and Nguyen, H.T. (2013). Mathematics of Data Fusion, Springer Science & Business Media."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1109\/MAES.2004.1263231","article-title":"\u201cStatistics 101\u201d for multisensor, multitarget data fusion","volume":"19","author":"Mahler","year":"2004","journal-title":"IEEE Aerosp. Electron. Syst. Mag."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1109\/JSTSP.2013.2253084","article-title":"\u201cStatistics 102\u201d for multisource-multitarget detection and tracking","volume":"7","author":"Mahler","year":"2013","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Mahler, R.P. (2007). Statistical Multisource-Multitarget Information Fusion, Artech House, Inc.","DOI":"10.1201\/9781420053098.ch16"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1109\/TSP.2008.2007924","article-title":"The cardinality balanced multi-target multi-Bernoulli filter and its implementations","volume":"57","author":"Vo","year":"2009","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3460","DOI":"10.1109\/TSP.2013.2259822","article-title":"Labeled random finite sets and multi-object conjugate priors","volume":"61","author":"Vo","year":"2013","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3246","DOI":"10.1109\/TSP.2014.2323064","article-title":"The labeled multi-Bernoulli filter","volume":"62","author":"Reuter","year":"2014","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_14","unstructured":"Reuter, S., Vo, B.T., Vo, B.N., and Dietmayer, K. (2014, January 7\u201310). Multi-Object Tracking Using Labeled Multi-Bernoulli Random Finite Sets. Proceedings of the 2014 17th International Conference on Information Fusion (FUSION), Salamanca, Spain."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1109\/TPAMI.2014.2300479","article-title":"Fast feature pyramids for object detection","volume":"36","author":"Appel","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_16","unstructured":"Dalal, N., and Triggs, B. (2005, January 20\u201325). Histograms of oriented gradients for human detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, San Diego, CA, USA."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Panta, K., Clark, D.E., and Vo, B.N. (2009). Data association and track management for the Gaussian mixture probability hypothesis density filter. IEEE Trans. Aerosp. Electron. Syst., 45.","DOI":"10.1109\/TAES.2009.5259179"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1137\/S0097539795290477","article-title":"Finding the k shortest paths","volume":"28","author":"Eppstein","year":"1998","journal-title":"SIAM J. Comput."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1090\/qam\/102435","article-title":"On a routing problem","volume":"16","author":"Bellman","year":"1958","journal-title":"Q. Appl. Math."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1287\/opre.16.3.682","article-title":"Letter to the editor\u2014An algorithm for ranking all the assignments in order of increasing cost","volume":"16","author":"Murty","year":"1968","journal-title":"Oper. Res."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3447","DOI":"10.1109\/TSP.2008.920469","article-title":"A consistent metric for performance evaluation of multi-object filters","volume":"56","author":"Schuhmacher","year":"2008","journal-title":"IEEE Trans. Signal Process."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/4\/843\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:32:28Z","timestamp":1760207548000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/4\/843"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,12]]},"references-count":21,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2017,4]]}},"alternative-id":["s17040843"],"URL":"https:\/\/doi.org\/10.3390\/s17040843","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2017,4,12]]}}}