A Scalable Object Detection Framework Based on Embedded Manycore Cluster

摘要

Performance of high resolution image process is one of the kernel problems that must be addressed to promote the development of embedded system. In this study, a scalable bi-level parallel object detection framework based on heterogeneous manycore cluster was established to improve object detection performance for embedded device. First, the fundamental principle of local binary pattern and cascade classifier combined object detection method was introduced as the basis of the research. Second, a set of key algorithm design to parallel access and process image for object detection based on Parallella manycore platform was proposed to improve the detection speed and the computational resource efficiency on single node. Third, a Message Passing Interface based distributed framework was established for cluster environment to further improve the performance. Finally, an experiment of face detection application was conducted to evaluate the accuracy and performance of this framework. The experimental results show that on one node, the proposed object detection system provides 7.8 times speedup than a serial algorithm on dual-core ARM which was integrated in Parallella with similar accuracy, and in cluster environment, the performance will be doubled. The results demonstrate the promising application of the proposed framework in the field of object detection performance improvement.