改进的R-SSD全景视频图像车辆检测算法
Improved R-SSD Panoramic Video Image Vehicle Detection Algorithm
查看参考文献21篇
|
文摘
|
针对SSD算法在检测全景视频图像车辆目标时存在准确率低、漏检率高的问题,构建了一种改进的SSD网络,命名为R-SSD,并提出了一种基于R-SSD的全景视频图像中车辆目标检测算法。在原SSD网络之前增加了一个RPN*网络,目的在于过滤负样本先验框并粗略调整先验框的位置和大小,为后续回归提供好的初始条件。在原SSD和RPN*网络之间构建了传输转换模块,实现两个网络间的特征融合,并增加低层特征信息,从而提高目标的检测效果。在同时兼顾了RPN*网络和SSD*网络损失函数的基础上提出了新的损失函数,应用了二分类和多分类的方法,使回归操作更加精确。将采集的全景视频图像数据分为训练集和测试集,通过对比实验,表明提出的R-SSD算法检测精度可达90.78%,明显优于SSD算法,可较好地解决全景目标车辆检测中误检率较高、漏检率较高等问题。 |
|
其他语种文摘
|
To address the issue that the performance of the Single Shot Multi-Box Detector(SSD) algorithm is suffering from low accuracy and high missed detection rate when detecting vehicle targets in panoramic video images,this paper constructs an improved SSD network architecture named R-SSD,and proposes a vehicle target detection algorithm in panoramic video image based on the proposed R-SSD.An RPN* network is added before the original SSD network,which can filter the prior box of negative samples,and roughly adjust the position and size of the prior box to provide good initial conditions for subsequent regression.A transmission conversion module is constructed between the original SSD and RPN* network to realize feature fusion between these two networks,and increase the low-level feature information,so as to improve the detection effect of the target.The comparative experiment results on panorama video image data set show that the proposed algorithm has a detection accuracy of 90.78%,which is significantly better than the SSD algorithm,and has higher detection rate and lower missing detection rate than the traditional SSD network in panoramic target vehicle detection. |
|
来源
|
计算机工程与应用
,2021,57(3):189-195 【扩展库】
|
|
DOI
|
10.3778/j.issn.1002-8331.1911-0163
|
|
关键词
|
全景车辆检测
;
SSD算法
;
特征融合
;
传输转换模块
|
|
地址
|
1.
西安邮电大学通信与信息工程学院, 西安, 710121
2.
中国科学院西安光学精密机械研究所, 西安, 710119
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
1002-8331 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
公安部科技强警基础工作专项
;
陕西省自然科学基金
;
西安邮电大学创新创业项目
;
西安邮电大学研究生创新基金
|
|
文献收藏号
|
CSCD:6924353
|
参考文献 共
21
共2页
|
|
1.
Ye Tao. Automatic railway traffic object detection system using feature fusion refine neural network under shunting mode.
Sensors (Basel,Switzerland),2018,18(6):1916-1934
|
CSCD被引
7
次
|
|
|
|
|
2.
林泉. 全景摄像机的原理与进展.
自然杂志,2017,39(2):131-136
|
CSCD被引
2
次
|
|
|
|
|
3.
高文. 目标跟踪技术综述.
中国光学,2014,7(3):365-375
|
CSCD被引
38
次
|
|
|
|
|
4.
Wang X. An HOG-LBP human detector with partial occlusion handling.
International Conference on Computer Vision,2010:32-39
|
CSCD被引
3
次
|
|
|
|
|
5.
王宪. 基于改进的LBP人脸识别算法.
光电工程,2012,39(7):109-114
|
CSCD被引
14
次
|
|
|
|
|
6.
宋焕生. 基于深度学习方法的复杂场景下车辆目标检测.
计算机应用研究,2018(4):1206-1211
|
CSCD被引
1
次
|
|
|
|
|
7.
Kong T. HyperNet:towards accurate region proposal generation and joint object detection.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:845-853
|
CSCD被引
14
次
|
|
|
|
|
8.
Han J. Advanced deep-learning techniques for salient and category-specific object detection:a survey.
IEEE Signal Processing Magazine,2018,35(1):84-100
|
CSCD被引
25
次
|
|
|
|
|
9.
周俊宇. 卷积神经网络在图像分类和目标检测应用综述.
计算机工程与应用,2017,53(13):34-41
|
CSCD被引
44
次
|
|
|
|
|
10.
Huan Y L. An end-to-end network for panoptic segmentation.
The IEEE Conference on Computer Vision and Pattern Recognition,2019:6172-6181
|
CSCD被引
1
次
|
|
|
|
|
11.
Girshick R. Rich feature hierarchies for object detection and semantic segmentation.
IEEE Conference on Computer Vision and Pattern Recognition,2014:580-587
|
CSCD被引
185
次
|
|
|
|
|
12.
He K. Spatial pyramid pooling in deep convolutional networks for visual recognition.
IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,37(9):1904-1916
|
CSCD被引
1392
次
|
|
|
|
|
13.
Bojarski M. End to end learning for self-driving cars.
IEEE Intelligent Vehicles Symposium(IV),2017:1856-1860
|
CSCD被引
1
次
|
|
|
|
|
14.
Ren S. Faster R-CNN:towards real-time object detection with region proposal networks.
29th Annual Conference on Neural Information Processing Systems,2015:91-99
|
CSCD被引
2
次
|
|
|
|
|
15.
Girshick R. Fast R-CNN.
Proceedings of the IEEE International Conference on Computer Vision,2015:1440-1448
|
CSCD被引
689
次
|
|
|
|
|
16.
Redmon J. You only look once:unified,real-time object detection.
IEEE Conference on Computer Vision and Pattern Recognition,2016:779-788
|
CSCD被引
211
次
|
|
|
|
|
17.
Alqizwini M. Deep learning algorithm for autonomous driving using GoogLeNet.
2017 IEEE Intelligent Vehicles Symposium,2017:89-96
|
CSCD被引
1
次
|
|
|
|
|
18.
Liu W. SSD:single shot multibox detector.
European Conference on Computer Vision,2016:21-37
|
CSCD被引
968
次
|
|
|
|
|
19.
Zhang S. Single-shot refinementneural network for object detection.
IEEE Conference on Computer Vision and Pattern Recognition,2018:4203-4212
|
CSCD被引
4
次
|
|
|
|
|
20.
Shi G. Visualization and pruning of SSD with the base network VGG16.
International Conference on Deep Learning Technologies,2017:90-94
|
CSCD被引
2
次
|
|
|
|
|
了解气象卫星更多信息，请访问