基于智能驾驶的动态目标跟踪研究
Research on Dynamic Target Tracking Based on Intelligent Driving
查看参考文献15篇
|
文摘
|
针对智能驾驶过程中存在背景变化剧烈、光照变化影响较大且背景颜色不易区分等缺陷,提出一种改进的卡尔曼粒子滤波算法。采用灰度投影算法对车辆视频和图像序列帧进行预处理,通过Harris角点检测在图像区域内的目标和背景提取角点,利用卡尔曼嵌入粒子滤波器对粒子滤波进行二次预测,以保证智能驾驶过程中动态跟踪的有效性和准确性。实验结果表明,与传统KPF算法相比,该算法在不同场景下的动态目标跟踪能力明显增强,在复杂的交通驾驶环境下跟踪准确率为95.7%,且具有较好的实时性。 |
|
其他语种文摘
|
Aiming at the shortcomings such as the dramatic change of background,the influence of illumination change and the indistinguishable background color in the intelligent driving process, an improved Kalman particle filter algorithm is proposed. A gray-scale projection algorithm is used to preprocess vehicle video and image sequence frames. Harris corners dertection is used to extract angles of the target and background in the image region,and Kalman-embedded particle filter is used to make a second prediction of particle filtering. The effectiveness and accuracy of dynamic tracking are ensured during smart driving. Experimental results show that compared with the traditional KPF algorithm,the Moving Object Tracking( MOT) ability of the algorithm in different scenarios is obviously enhanced,the tracking accuracy rate is 95.7% in a complex traffic driving environment, and has good real-time performance. |
|
来源
|
计算机工程
,2018,44(7):14-19 【扩展库】
|
|
DOI
|
10.19678/j.issn.1000-3428.0051084
|
|
关键词
|
目标跟踪
;
智能驾驶
;
Harris角点检测
;
卡尔曼滤波
;
粒子滤波
|
|
地址
|
1.
北京联合大学, 北京市信息服务工程重点实验室, 北京, 100101
2.
北京联合大学机器人学院, 北京, 100101
3.
北京联合大学工科综合实验教学示范中心, 北京, 100101
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
1000-3428 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
国家自然科学基金“视听觉信息的认知计算
;
英国皇家工程院牛顿基金
;
北京联合大学人才强校优选计划项目
|
|
文献收藏号
|
CSCD:6285661
|
参考文献 共
15
共1页
|
|
1.
Li X. Incremental learning of3D-DCT compact representations for robust visual tracking.
IEEE Transactions on Pattern Analysis & Machine Intelligence,2013,35(4):863-881
|
被引
9
次
|
|
|
|
|
2.
张微. 相关滤波目标跟踪进展综述.
中国图象图形学报,2017,22(8):1017-1033
|
被引
43
次
|
|
|
|
|
3.
张聪炫. 单目图像序列光流三维重建技术研究综述.
电子学报,2016,44(12):3044-3052
|
被引
5
次
|
|
|
|
|
4.
Chen Y. Object tracking algorithm based on adaptive learning parameter by online loss detection.
Proceedings of China Academic Conference on Printing & Packaging & Media Technology,2017:125-132
|
被引
1
次
|
|
|
|
|
5.
Basar T.
A new approach to linear filtering and prediction problems,2009:167-179
|
被引
1
次
|
|
|
|
|
6.
叶润. 基于稀疏性理论与子问题耦合的多目标跟踪方法.
计算机工程,2017,43(6):219-224
|
被引
1
次
|
|
|
|
|
7.
Tao R. Siamese instance search for tracking.
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition,2016:1420-1429
|
被引
8
次
|
|
|
|
|
8.
Xu C. Robust visual tracking via online multiple instance learning with Fisher information.
Pattern Recognition,2015,48(12):3917-3926
|
被引
5
次
|
|
|
|
|
9.
Kalal Z. Trackinglearning-detection.
IEEE Transactions on Pattern Analysis & Machine Intelligence,2012,34(7):1409-1422
|
被引
460
次
|
|
|
|
|
10.
Hare S. Struck: structured output tracking with kernels.
IEEE Transactions on Pattern Analysis & Machine Intelligence,2016,38(10):2096-2109
|
被引
144
次
|
|
|
|
|
11.
Henriques J F. Highspeed tracking with kernelized correlation filters.
IEEE Transactions on Pattern Analysis & Machine Intelligence,2014,37(3):583-596
|
被引
883
次
|
|
|
|
|
12.
Khattak A S. Integration of mean-shift and particle filter: a survey.
Proceedings of International Conference on Frontiers of Information Technology,2014:286-291
|
被引
1
次
|
|
|
|
|
13.
亚森·艾则孜. 运动目标检测中基于灰度特征模型的背景消除方法.
计算机工程,2015,41(6):240-246
|
被引
2
次
|
|
|
|
|
14.
Tiwaari R K. A computer vision based framework for visual gun detection using Harris interest point detector.
Procedia Computer Science,2015,54:703-712
|
被引
3
次
|
|
|
|
|
15.
Katalin G. Unscented Kalman filters and particle filter methods for nonlinear state estimation.
Procedia Technology,2014,12(1):65-74
|
被引
8
次
|
|
|
|
|
了解气象卫星更多信息，请访问