Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-02 Cooperative journals: 《计算机应用研究》
Abstract: In order to overcome the shortcomings that SSD (Single Shot MultiBox Detector) can not detect small objects well, this paper proposed an Atrous filter design strategy, which can strengthen the resolution of feature maps. The improved algorithm concatenated the feature maps that generated by the third and fourth convolution layer after normalization, and then improves the resolution of these feature maps by Atrous computed. The concatenated feature maps provide the required features for small objects. In addition, the SSD improved algorithm also add SeLU (Scaled Exponential Linear Units) activation function and designed a data augmented methods in the data preprocessing phase. The experimental results shows that the proposal algorithm has higher detection accuracy and better robustness than the original SSD algorithm. Furthermore, the detection performance obvious better on small target detection.