Random Finite Set Based Bayesian Filtering with OpenCL in a Heterogeneous Platform
AbstractWhile 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×) were observed on average while processing typical MOT benchmark videos. Moreover, the worst-case frame processing yielded an 18× advantage from nearly 2 fps to 36 fps, thereby comfortably meeting the real-time constraints. Our implementation is released as open-source code. View Full-Text
A printed edition of this Special Issue is available here.
Share & Cite This Article
Hu, B.; Sharif, U.; Koner, R.; Chen, G.; Huang, K.; Zhang, F.; Stechele, W.; Knoll, A. Random Finite Set Based Bayesian Filtering with OpenCL in a Heterogeneous Platform. Sensors 2017, 17, 843.
Hu B, Sharif U, Koner R, Chen G, Huang K, Zhang F, Stechele W, Knoll A. Random Finite Set Based Bayesian Filtering with OpenCL in a Heterogeneous Platform. Sensors. 2017; 17(4):843.Chicago/Turabian Style
Hu, Biao; Sharif, Uzair; Koner, Rajat; Chen, Guang; Huang, Kai; Zhang, Feihu; Stechele, Walter; Knoll, Alois. 2017. "Random Finite Set Based Bayesian Filtering with OpenCL in a Heterogeneous Platform." Sensors 17, no. 4: 843.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.