摘要
现有的高精度目标检测算法依赖于超深的主干网络(如ResNet和Inception),无法满足实时目标检测场景的需要,相反采用轻量级主干网络(如VGG-16和MobileNet)能达到实时目标检测的目的,但会导致检测精度的损失,对小目标的检测效果变差。SSD(Single Shot Multi-Box Detector)算法具有高精度、实时检测的特点。本文以SSD算法的网络结构为基础,通过添加感受野模块增强轻量级主干网络的特征提取能力,同时引入特征融合模块,充分利用深层网络提取语义信息,达到实时目标检测的目的,同时提高算法整体的检测精度和对小目标的检测能力。为进一步验证引入新模块的有效性,本文算法模型在PASCAL VOC2007数据集上进行测试,准确率达到80.5%,相比于原始SSD算法有3.3个百分点的提升,检测速度达到75frame/s,整体性能优于目前大多数目标检测算法。
Existing high precision object detection algorithms mostly rely on super deep backbone networks,such as ResNet and Inception,making it difficult to meet real-time detection requirements.On the contrary,some lightweight backbone networks,such as VGG-16 and MobileNet,fulfill real-time processing but their accuracies are often criticized,especially when the targets are small.In this study,we explore an alternative to build a fast and accurate detector by strengthening the feature extraction ability of lightweight backbone networks,using a new receptive field block based on a single shot multi-box detector(SSD).Simultaneously,to make full use of the semantic information extracted from deep networks,a feature fusion module is designed and added,thereby improving the overall accuracy and enhancing the detection effect of the model for small targets,while still achieving real-time detection.To further verify the validity of introducing new modules,we have tested our model on the PASCAL VOC2007 data set and achieved an accuracy of 80.5% which is 3.3 percentage points higher than that of the original SSD model.In addition,the detection speed of the proposed model reaches 75 frame/s,and its overall performance is better than that of most of the current models.
作者
王伟锋
金杰
陈景明
Wang Weifeng;Jin Jie;Chen Jingming(School of Electrical and Information Engineering,Tianjin University,Tianjin 300072 China)
出处
《激光与光电子学进展》
CSCD
北大核心
2020年第2期242-247,共6页
Laser & Optoelectronics Progress
基金
国家自然科学基金(61571320)。
关键词
机器视觉
目标检测
感受野
特征融合
machine vision
object detection
receptive field block
feature fusion
