Object detection has made impressive progress in recent years with the help
of deep learning. However, state-of-the-art algorithms are both computation and
memory intensive. Though many lightweight networks are developed for a
trade-off between accuracy and efficiency, it is still a challenge to make it
practical on an embedded device. In this paper, we present a system-level
solution for efficient object detection on a heterogeneous embedded device. The
detection network is quantized to low bits and allows efficient implementation
with shift operators. In order to make the most of the benefits of low-bit
quantization, we design a dedicated accelerator with programmable logic. Inside
the accelerator, a hybrid dataflow is exploited according to the heterogeneous
property of different convolutional layers. We adopt a straightforward but
resource-friendly column-prior tiling strategy to map the computation-intensive
convolutional layers to the accelerator that can support arbitrary feature
size. Other operations can be performed on the low-power CPU cores, and the
entire system is executed in a pipelined manner. As a case study, we evaluate
our object detection system on a real-world surveillance video with input size
of 512x512, and it turns out that the system can achieve an inference speed of
18 fps at the cost of 6.9W (with display) with an mAP of 66.4 verified on the
PASCAL VOC 2012 dataset.

本文提出了一种面向异构嵌入式设备的高效物体检测系统解决方案，其中包括量化网络和专门的加速器，并采用分组数据流策略将计算密集型的卷积操作映射到加速器中以提高效率。研究结果显示，在 512x512 输入大小的实际监控视频中，该系统的推理速度可以达到 18 FPS，功耗仅为 6.9W，并在 PASCAL VOC 2012 数据集上实现了 66.4 的 mAP。