基于双阈值-非极大值抑制的Faster R-CNN改进算法

Improved algorithm of Faster R-CNN based on double threshold-non-maximum suppression

根据目标检测算法中出现的目标漏检和重复检测问题,本文提出了一种基于双阈值-非极大值抑制的Faster R-CNN改进算法。算法首先利用深层卷积网络架构提取目标的多层卷积特征,然后通过提出的双阈值-非极大值抑制(DT-NMS)算法在RPN阶段提取目标候选区域的深层信息,最后使用了双线性插值方法来改进原Ro I pooling层中的最近邻插值法,使算法在检测数据集上对目标的定位更加准确。实验结果表明,DT-NMS算法既有效地平衡了单阈值算法对目标漏检问题和目标误检问题的关系,又针对性地减小了同一目标被多次检测的概率。与soft-NMS算法相比,本文算法在PASCAL VOC2007上的重复检测率降低了2.4%,多次检测的目标错分率降低了2%。与Faster R-CNN算法相比,本文算法在PASCAL VOC2007上检测精度达到74.7%,性能提升了1.5%。在MSCOCO数据集上性能提升了1.4%。同时本文算法具有较快的检测速度,达到16 FPS。

According to the problems of target missed detection and repeated detection in the object detection algorithm, this paper proposes an improved Faster R-CNN algorithm based on dual threshold-non-maximum suppression. The algorithm first uses the deep convolutional network architecture to extract the multi-layer convolution features of the targets, and then proposes the dual threshold-non-maximum suppression(DT-NMS) algorithm in the RPN(region proposal network). The phase extracts the deep information of the target candidate regions, and finally uses the bilinear interpolation method to improve the nearest neighbor interpolation method in the original RoI pooling layer, so that the algorithm can more accurately locate the target on the detection dataset. The experimental results show that the DT-NMS algorithm effectively balances the relationship between the single-threshold algorithm and the target missed detection problem, and reduces the probability of repeated detection. Compared with the soft-NMS algorithm, the repeated detection rate of the DT-NMS algorithm in PASCAL VOC2007 is reduced by 2.4%, and the target error rate of multiple detection is reduced by 2%. Compared with the Faster R-CNN algorithm, the detection accuracy of this algorithm on the PASCAL VOC2007 is 74.7%, the performance is improved by 1.5%, and the performance on the MSCOCO dataset is improved by 1.4%. At the same time, the algorithm has a fast detection speed, reaching 16 FPS.