深度可分离卷积和标准卷积相结合的高效行人检测器

行人检测器对算法的速度和精确度有很高的要求.虽然基于深度卷积神经网络(DCNN)的行人检测器具有较高的检测精度,但是这类检测器对硬件设备的计算能力要求较高,因此,这类行人检测器无法很好地部署到诸如移动设备、嵌入式设备和自动驾驶系统等轻量化系统中.基于此,提出了一种更好地平衡速度和精度的轻量级行人检测器(EPDNet)....

Efficient pedestrian detector combining depthwise separable convolution and standard convolution

Pedestrian detectors require the algorithm to be fast and accurate. Although pedestrian detectors based on deepconvolutional neural networks (DCNN) have high detection accuracy, such detectors require higher capacity ofcalculation. Therefore, such pedestrian detectors cannot be deployed well on lightweight systems, such as mobile devices,embedded devices, and autonomous driving systems. Considering these problems, a lightweight and effective pedestrian detector (EPDNet) was proposed, which can better balance speed and accuracy. First, the shallow convolution layers of the backbone network employed depthwise separable convolution to compress the parameters of model, and the deeper convolution layers utilized standard convolution to extract high-level semantic features. In addition, in order to further improve the performance of the model, the backbone network adopted a feature fusion method to enhance the expression ability of its output features. Through comparative experiments, EPDNet has shown superior performance on twochallenging pedestrian datasets, Caltech and CityPersons. Compared with the benchmark model, EPDNet has obtained abetter trade-off between speed and accuracy, improving the speed and accuracy of EPDNet at the same time.