油田安防领域基于改进的深度残差网络行人检测模型

Pedestrian Detection Model based on Improved Deep Residual SSD Network in Oilfield security field

摘要:

油田安防中行人目标检测是是当今前沿的一个热门研究课题,针对野外场景采集的图像视频分辨率低,背景复杂等问题,本文在单次多目标检测器(Single Shot MultiBox Detector,SSD)模型的基础上,提出了一种改进的行人检测算法,该算法首先利用聚合通道特征模型对图像或者视频序列进行进行预处理,获得疑似目标区域,大大降低单帧图像检测的时间；然后对SSD的基本网络VGG-16替换为Resnet-50,通过增加恒等映射解决网络层数加深但检测精度下降的问题；最后采用强大而灵活的双参数损失函数来优化训练深度网络,提高网路模型的泛化能力。定性定量实验结果表明本文所提检测算法的性能超过现有的检测算法,在保证行人检测准确率的同时提高检测效率。S

Abstract:

Pedestrian detection in oilfield security is a hot research topic. For the low resolution and complex background in image, this paper is based on the Single Shot MultiBox Detector (SSD), proposed an improved pedestrian detection algorithm. The algorithm firstly uses the aggregate channel feature model to preprocess the image or video sequence to obtain the suspected pedestrian area, which greatly reduces the time of single-frame image detection. The basic network VGG-16 is replaced by Resnet-50, which introduces the identity mapping to solve the problem of reducing the detection accuracy when the number of network layers are increased. Finally, the powerful and flexible two-parameter loss function is used to optimize the training deep network and improve the network model generalization ability. Qualitative and quantitative experiments show that the performance of the proposed detection algorithm exceeds the existing detection algorithm, and the detection efficiency is improved while ensuring the accuracy of pedestrian detection.