Object detection in remote sensing images on a satellite or aircraft has important economic and military significance and is full of challenges. This task requires not only accurate and efficient algorithms, but also high-performance and low power hardware architecture. However, existing deep learning based object detection algorithms require further optimization in small objects detection, reduced computational complexity and parameter size. Meanwhile, the general-purpose processor cannot achieve better power efficiency, and the previous design of deep learning processor has still potential for mining parallelism. To address these issues, we propose an efficient context-based feature fusion single shot multi-box detector (CBFF-SSD) framework, using lightweight MobileNet as the backbone network to reduce parameters and computational complexity, adding feature fusion units and detecting feature maps to enhance the recognition of small objects and improve detection accuracy. Based on the analysis and optimization of the calculation of each layer in the algorithm, we propose efficient hardware architecture of deep learning processor with multiple neural processing units (NPUs) composed of 2-D processing elements (PEs), which can simultaneously calculate multiple output feature maps. The parallel architecture, hierarchical on-chip storage organization, and the local register are used to achieve parallel processing, sharing and reuse of data, and make the calculation of processor more efficient. Extensive experiments and comprehensive evaluations on the public NWPU VHR-10 dataset and comparisons with some state-of-the-art approaches demonstrate the effectiveness and superiority of the proposed framework. Moreover, for evaluating the performance of proposed hardware architecture, we implement it on Xilinx XC7Z100 field programmable gate array (FPGA) and test on the proposed CBFF-SSD and VGG16 models. Experimental results show that our processor are more power efficient than general purpose central processing units (CPUs) and graphics processing units (GPUs), and have better performance density than other state-of-the-art FPGA-based designs.
This is an open access article distributed under the Creative Commons Attribution License
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited