顾及轨迹还原与分类的渣土车作业行为提取方法

doi:10.12082/dqxxkx.2023.220414

地球信息科学学报 ›› 2023, Vol. 25 ›› Issue (4): 754-765.doi: 10.12082/dqxxkx.2023.220414

顾及轨迹还原与分类的渣土车作业行为提取方法

庄汉宸¹^,²(), 张亚茹¹^,², 王文轩¹^,², 张书亮¹^,²^,^*()

1.南京师范大学虚拟地理环境教育部重点实验室，南京 210023
2.江苏省地理信息资源开发与利用协同创新中心，南京 210023

收稿日期:2022-06-16 修回日期:2022-08-19 出版日期:2023-04-25 发布日期:2023-04-19
通讯作者: ^*张书亮（1974—），男，河南南阳人，博士，教授，博士生导师，主要从事时空大数据分析、城市内涝地理建模与模拟研究。E-mail: zhangshuliang@njnu.edu.cn
作者简介:庄汉宸（1999—），男，浙江舟山人，本科生，主要从事时空数据挖掘研究。E-mail: zhuanghanchen@163.com
基金资助:
国家自然科学基金项目(42071364)

Extraction of Muck Truck Operation Behavior Considering Trajectory Restoration and Classification

ZHUANG Hanchen¹^,²(), ZHANG Yaru¹^,², WANG Wenxuan¹^,², ZHANG Shuliang¹^,²^,^*()

1. Key Laboratory of VGE of Ministry of Education, Nanjing Normal University, Nanjing 210023, China
2. Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, China

Received:2022-06-16 Revised:2022-08-19 Online:2023-04-25 Published:2023-04-19
Contact: ZHANG Shuliang
Supported by:
National Natural Science Foundation of China(42071364)

摘要/Abstract

摘要：

渣土车轨迹数据蕴含丰富的行为模式信息，包括停车行为、运输路径、异常活动、渣土装载与倾倒OD点等关键特征，已逐渐成为渣土车运行监测与作业行为监管的主要数据来源。但是目前在渣土车作业行为提取中仍主要采用车载GPS数据结合工地电子围栏的传统签到系统，存在电子围栏与道路相互包含、重叠等一系列问题。针对传统渣土车作业行为提取中存在的车辆作业误判问题，本文提出一种顾及轨迹还原与分类的渣土车作业行为提取方法。① 从运动状态和几何形态2个方面理解并识别渣土车作业行为模式；② 利用顾及时间与距离的停留点提取算法提取车辆停留点，处理停留点与轨迹的映射关系，完成基于停留点的轨迹匹配；③ 构建平均相似值函数对轨迹进行语义信息增强；④ 提出SR-LGBM算法，筛选作业轨迹与非作业轨迹，实现渣土车的作业行为提取。采用南京市渣土车轨迹数据进行测试，结果表明，本文方法的准确率达97.29%，相比GaussianNB、Logistic Regression等传统分类算法其准确率与召回率均得到不同程度的提高，有效解决了电子围栏与道路重叠或多个围栏交叉造成的误判问题，可实现准确、高效的作业行为提取。

关键词: 渣土车轨迹数据, 作业行为, 作业行为模式, 停留点, 平均相似值函数, 语义增强, 轨迹特征参数, SR-LGBM算法

Abstract:

The muck truck trajectory data contain rich behavior pattern information, including key features such as parking behavior, transportation paths, abnormal activities, and muck loading and dumping OD points, etc. It has gradually become the main data source for operation monitoring and operation behavior supervision of muck trucks. However, at present, the traditional sign-in system of vehicle-mounted GPS data combined with site electronic fences is still commonly used in extraction of the muck truck operation behavior, which has a series of problems such as mutual inclusion and overlap between the electronic fence and the road. Aiming at the problem of misjudgment of vehicle operation in traditional extraction of muck truck operation behavior, this paper proposes a muck truck operation behavior extraction method considering trajectory restoration and classification. Firstly, the operation behavior pattern of muck trucks is recognized from two aspects: motion state and geometric form. Secondly, the stopping point extraction algorithm taking into account time and distance is used to extract the vehicle stopping point, and the mapping relationship between the stopping point and the trajectory is processed to complete the trajectory matching based on the stopping point. Then, the average similarity function is constructed to enhance the semantic information of the trajectory. Finally, the SR-LGBM algorithm is proposed to filter the operating trajectory and non-operating trajectory and extract the operation behavior of muck trucks. The test results show that the accuracy of the proposed method is 97.29%, which is significantly improved compared with the traditional classification algorithms such as GaussianNB and Logistic Regression. Our proposed methods effectively solve the misjudgment problem caused by the overlap of electronic fences and roads or multiple fences, and can accurately and efficiently extract the operation behavior of muck trucks.

Key words: muck truck trajectory data, operation behavior, operation behavior pattern, stay point, average similarity function, semantic enhancement, trajectory feature parameters, SR-LGBM

庄汉宸, 张亚茹, 王文轩, 张书亮. 顾及轨迹还原与分类的渣土车作业行为提取方法[J]. 地球信息科学学报, 2023, 25(4): 754-765.DOI:10.12082/dqxxkx.2023.220414

ZHUANG Hanchen, ZHANG Yaru, WANG Wenxuan, ZHANG Shuliang. Extraction of Muck Truck Operation Behavior Considering Trajectory Restoration and Classification[J]. Journal of Geo-information Science, 2023, 25(4): 754-765.DOI:10.12082/dqxxkx.2023.220414

图/表 20

图1

图2

图3

图4

图5

图6

表1

匹配轨迹的关键特征描述

视角	变量	单位	特征描述
瞬时速度	$v i m e a n$	m/s	平均瞬时速度
瞬时速度	$v i s t d$	m/s	瞬时速度标准差
加速度	$a m e a n$	m/s²	平均加速度
加速度	$a s t d$	m/s²	加速度标准差
路网距离	$r d m e d$	m	路网距离中值
路网距离	$r d s t d$	m	路网距离标准差
停留时长	$d u r a t i o n$	s	累计停留时长
停留时长	$s t o p R a t i o$		累计停留时长比率
转角	$a n g l e m e a n$	°	平均转角
转角	$a n g l e s t d$	°	转角标准差
轨迹复杂度	$l e n g t h$	m	轨迹长度
	$a r e a$	m²	轨迹覆盖面积
	$s m o o t h R a t i o$		轨迹平滑比率
驶入驶出点差异	$Δ d$	m	两点间距
	$Δ v i$	m/s	速度差
	$Δ a$	m/s²	加速度差
	$Δ r d$	m	路网距离差
	$Δ θ$	°	方位角差

表1

表2

图7

图8

图9

图10

图11

图12

图13

图14

图15

表3

作业轨迹关键特征重要性排序

排序	变量	描述	排序	变量	描述
1	$a s t d$	加速度标准差	10	$Δ a$	加速度差
2	$s m o o t h R a t i o$	轨迹平滑比率	11	$s t o p R a t i o$	累计停留时长比率
3	$v i s t d$	瞬时速度标准差	12	$r d s t d$	路网距离标准差
4	$a m e a n$	平均加速度	13	$l e n g t h$	轨迹长度
5	$Δ v i$	速度差	14	$Δ r d$	路网距离差
6	$a n g l e s t d$	转角标准差	15	$r d m e d$	路网距离中值
7	$a n g l e m e a n$	平均转角	16	$Δ d$	两点间距
8	$v i m e a n$	平均瞬时速度	17	$d u r a t i o n$	累计停留时长
9	$Δ θ$	方位角差	18	$a r e a$	轨迹覆盖面积

表3

表4

表5

参考文献 34

[1]	Gong L, Sato H, Yamamoto T, et al. Identification of activity stop locations in GPS trajectories by density-based clustering method combined with support vector machines[J]. Journal of Modern Transportation, 2015, 23(3):202-213. DOI:10.1007/s40534-015-0079-x doi: 10.1007/s40534-015-0079-x
[2]	向隆刚, 龚健雅, 吴涛, 等. 一种面向Stop/Move抽象的轨迹时空关系[J]. 武汉大学学报·信息科学版, 2014, 39(8):956-962.
	[Xiang L G, Gong J Y, Wu T, et al. Spatio-temporal trajectory relationships based on Stop/Move abstraction[J]. Geomatics and Information Science of Wuhan University, 2014, 39(8):956-962.] DOI:10.13203/j.whugis20130061 doi: 10.13203/j.whugis20130061
[3]	Liu J, Yu X, Xu Z, et al. A cloud-based taxi trace mining framework for smart city[J]. Software: Practice and Experience, 2017, 47(8):1081-1094. DOI:10.1002/spe.2435 doi: 10.1002/spe.2435
[4]	兰志辉, 陈莉, 段治州. 基于时间序列聚类的轨迹停留点检测算法[J]. 计算机应用研究, 2020, 37(12):3557-3560.
	[Lan Z H, Chen L, Duan Z Z. Trajectory stops detection algorithm based on time series clustering[J]. Application Research of Computers, 2020, 37(12):3557-3560.] DOI:10.19734/j.issn.1001-3695.2019.09.0533 doi: 10.19734/j.issn.1001-3695.2019.09.0533
[5]	张健钦, 仇培元, 杜明义. 基于时空轨迹数据的出行特征挖掘方法[J]. 交通运输系统工程与信息, 2014, 14(6):72-78.
	[Zhang J Q, Qiu P Y, Du M Y. Mining method of travel characteristics based on spatio-temporal trajectory data[J]. Journal of Transportation Systems Engineering and Information Technology, 2014, 14(6):72-78.] DOI:10.16097/j.cnki.1009-6744.2014.06.011 doi: 10.16097/j.cnki.1009-6744.2014.06.011
[6]	刘汇慧, 阚子涵, 孙飞, 等. 采用轨迹大数据探测短时非营运行为[J]. 武汉大学学报·信息科学版, 2016, 41(9):1192-1198.
	[Liu H H, Kan Z H, Sun F, et al. Taxis' short-term out-of-service behaviors detection using big trace data[J]. Geomatics and Information Science of Wuhan University, 2016, 41(9):1192-1198.] DOI:10.13203/j.whugis20150569 doi: 10.13203/j.whugis20150569
[7]	向隆刚, 邵晓天. 载体轨迹停留信息提取的核密度法及其可视化[J]. 测绘学报, 2016, 45(9):1122-1131.
	[Xiang L G, Shao X T. Visualization and extraction of trajectory stops based on Kernel-density[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(9): 1122-1131.] DOI:10.11947/j.AGCS.2016.20150347 doi: 10.11947/j.AGCS.2016.20150347
[8]	李思宇, 向隆刚, 张彩丽, 等. 基于低频出租车轨迹的城市路网交叉口提取研究[J]. 地球信息科学学报, 2019, 21(12):1845-1854. doi: 10.12082/dqxxkx.2019.190187
	[Li S Y, Xiang L G, Zhang C L, et al. Extraction of urban road network intersections based on low-frequency taxi trajectory data[J]. Journal of Geo-information Science, 2019, 21(12):1845-1854.]
[9]	Siripirote T, Sumalee A, Ho H W. Statistical estimation of freight activity analytics from Global Positioning System data of trucks[J]. Transportation Research Part E: Logistics and Transportation Review, 2020, 140:101986. DOI:10.1016/j.tre.2020.101986 doi: 10.1016/j.tre.2020.101986
[10]	李军, 解超, 王林, 等. 基于轨迹数据的道路客运班车停留站点位置提取方法[J]. 交通信息与安全, 2021, 39(4):60-67.
	[Li J, Xie C, Wang L, et al. A Method for Extracting Regular Bus Parking Stops of Road Passenger Transport Based on Trajectory Data[J]. Journal of Transport Information and Safety, 2021, 39(4):60-67.] DOI:10.3963/j.jssn.1674-4861.2021.04.008 doi: 10.3963/j.jssn.1674-4861.2021.04.008
[11]	吴华意, 黄蕊, 游兰, 等. 出租车轨迹数据挖掘进展[J]. 测绘学报, 2019, 48(11):1341-1356.
	[Wu H Y, Huang R, You L, et al. Recent progress in taxi trajectory data mining[J]. Acta Geodaetica et Cartographica Sinica, 2019, 48(11):1341-1356.]
[12]	Sheng K, Liu Z, Zhou D C, et al. Research on ship classification based on trajectory features[J]. Journal of Navigation, 2018, 71(1):100-116. DOI:10.1017/s0373463317000546 doi: 10.1017/s0373463317000546
[13]	Xue Q W, Xing Y Y, Lu J. An integrated lane change prediction model incorporating traffic context based on trajectory data[J]. Transportation Research Part C: Emerging Technologies, 2022, 141:103738. DOI:10.1016/j.trc.2022.103738 doi: 10.1016/j.trc.2022.103738
[14]	Khelfa B, Tordeux A. Lane-changing prediction in highway: Comparing empirically rule-based model MOBIL and a naïve Bayes algorithm[C]// 2021 IEEE International Intelligent Transportation Systems Conference. IEEE,: 1598-1603. DOI:10.1109/ITSC48978.2021.9564927 doi: 10.1109/ITSC48978.2021.9564927
[15]	Ma X L, Yu H Y, Wang Y P, et al. Large-scale transportation network congestion evolution prediction using deep learning theory[J]. PLoS One, 2015, 10(3):e0119044. DOI:10.1371/journal.pone.0119044 doi: 10.1371/journal.pone.0119044
[16]	Xu J, Rahmatizadeh R, Bölöni L, et al. Real-time prediction of taxi demand using recurrent neural networks[J]. IEEE Transactions on Intelligent Transportation Systems, 2018, 19(8):2572-2581. DOI:10.1109/TITS.2017.2755684 doi: 10.1109/TITS.2017.2755684
[17]	梁军辉, 林坚, 杜洋. 大数据条件下城市用地类型辨识研究——基于出租车GPS数据的动态感知[J]. 上海国土资源, 2016, 37(1):28-32.
	[Liang J H, Lin J, Du Y. Research on the identification of urban land use under the big data condition: Dynamic awareness based on taxi GPS data[J]. Shanghai Land ＆ Resources, 2016, 37(1):28-32.]
[18]	Yao B Z, Chen C, Cao Q D, et al. Short-term traffic speed prediction for an urban corridor[J]. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(2):154-169. DOI:10.1111/mice.12221 doi: 10.1111/mice.12221
[19]	李秋萍, 刘逸诗, 巩诗瑶, 等. 基于居民出行活动特征的个体经济水平推断方法[J]. 武汉大学学报·信息科学版, 2019, 44(10):1575-1580.
	[Li Q P, Liu Y S, Gong S Y, et al. Individual income level inference method based on travel behavior of urban residents[J]. Geomatics and Information Science of Wuhan University, 2019, 44(10):1575-1580.] DOI:10.13203/j.whugis20170426 doi: 10.13203/j.whugis20170426
[20]	Tu W, Li Q Q, Fang Z X, et al. Optimizing the locations of electric taxi charging stations: A spatial-temporal demand coverage approach[J]. Transportation Research Part C: Emerging Technologies, 2016, 65:172-189. DOI:10.1 016/j.trc.2015.10.004 doi: 10.1 016/j.trc.2015.10.004
[21]	张毅, 朱攀. 电动出租车专用充电场站选址模型研究[J]. 地球信息科学学报, 2021, 23(5):802-811. doi: 10.12082/dqxxkx.2021.200360
	[Zhang Y, Zhu P. Research on site selection model of special charging stations for taxis[J]. Journal of Geo-information Science, 2021, 23(5):802-811.] DOI:10.12082/dqxxkx.2021.200360. doi: 10.12082/dqxxkx.2021.200360
[22]	Wang B J, Wang Y L, Qin K, et al. Detecting transportation modes based on LightGBM classifier from GPS trajectory data[C]// 2018 26th International Conference on Geoinformatics. IEEE,: 1-7. DOI:10.1109/GEOINFORMATICS.2018.8557149 doi: 10.1109/GEOINFORMATICS.2018.8557149
[23]	高强, 张凤荔, 王瑞锦, 等. 轨迹大数据:数据处理关键技术研究综述[J]. 软件学报, 2017, 28(4):959-992.
	[Gao Q, Zhang F L, Wang R J, et al. Trajectory big data: A review of key technologies in data processing[J]. Journal of Software, 2017, 28(4):959-992.] DOI:10.13328/j.cnki.jos.005143 doi: 10.13328/j.cnki.jos.005143
[24]	Zheng Y. Trajectory data mining: An overview[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2015, 6(3):29. DOI:10.1145/2743025 doi: 10.1145/2743025
[25]	Ashbrook D, Starner T. Using GPS to learn significant locations and predict movement across multiple users[J]. Personal and Ubiquitous Computing, 2003, 7(5):275-286. DOI:10.1007/s00779-003-0240-0 doi: 10.1007/s00779-003-0240-0
[26]	Alvares L O, Bogorny V, Kuijpers B, et al. A model for enriching trajectories with semantic geographical information[C]// Proceedings of the 15th annual ACM international symposium on Advances in geographic information systems. Seattle, Washington. New York: ACM, 2007:1-8. DOI:10.1145/1341012.1341041 doi: 10.1145/1341012.1341041
[27]	Zhou C Q, Frankowski D, Ludford P J, et al. Discovering personally meaningful places: An interactive clustering approach[J]. ACM Transactions on Information Systems, 2007, 25(3): 12-es. DOI:10.1145/1247715.1247718 doi: 10.1145/1247715.1247718
[28]	侯颖超, 王盼成, 刘兴权, 等. 基于速度的空间轨迹停留点提取算法[J]. 地理与地理信息科学, 2016, 32(6):63-68,2.
	Wang P C, Liu X Q, et al. Algorithm Study for stay points recognition of spatial trajectory based on velocity[J]. Geography and Geo-information Science, 2016, 32(6):63-68,2.] DOI:10.3969/j.issn.1672-0504.2016.06.011 doi: 10.3969/j.issn.1672-0504.2016.06.011
[29]	姚迪, 张超, 黄建辉, 等. 时空数据语义理解:技术与应用[J]. 软件学报, 2018, 29(7):2018-2045.
	[Yao D, Zhang C, Huang J H, et al. Semantic understanding of spatio-temporal data: Technology & application[J]. Journal of Software, 2018, 29(7):2018-2045.] DOI:10.13328/j.cnki.jos.005576. doi: 10.13328/j.cnki.jos.005576
[30]	Guyon I, Weston J, Barnhill S, et al. Gene selection for cancer classification using support vector machines[J]. Machine Learning, 2002, 46(1/2/3):389-422. DOI:10.102 3/A:1012487302797 doi: 10.102 3/A:1012487302797
[31]	Ke G L, Meng Q, Finley T, et al. LightGBM: A highly efficient gradient boosting decision tree[C]// Proceedings of the 31st Internati onal Conference on Neural Information Processing Systems. New York: ACM, 2017:3149-3157.
[32]	齐凌艳, 陈荣国, 温馨. 基于语义轨迹停留点的位置服务匹配与应用研究[J]. 地球信息科学学报, 2014, 16(5):720-726. doi: 10.3724/SP.J.1047.2014.00720
	[Qi L Y, Chen R G, Wen X. Research on the LBS matching based on stay point of the semantic trajectory[J]. Journal of Geo-information Science, 2014, 16(5):720-726.] DOI:10.3724/SP.J.1047.2014.00720 doi: 10.3724/SP.J.1047.2014.00720
[33]	Visvalingam M, Whyatt J D. Line generalisation by repeated elimination of points[J]. The Cartographic Journal, 1993, 30(1):46-51. DOI:10.1179/000870493786962263 doi: 10.1179/000870493786962263
[34]	郑诗晨, 盛业华, 吕海洋. 基于粒子滤波的行车轨迹路网匹配方法[J]. 地球信息科学学报, 2020, 22(11):2109-2117. doi: 10.12082/dqxxkx.2020.190738
	[Zheng S C, Sheng Y H, Lv H Y. Vehicle trajectory-map matching based on particle filter[J]. Journal of Geo-Information Science, 2020, 22(11):2109-2117.]

参数	值	解释
kernel	linear	SVM核函数类型，本文采用线性核函数
C	0.1	SVM惩罚系数，用于调整准确率和泛化能力
num_leaves	255	每棵树的叶子数量
max_bin	255	表示最大的桶的数量，能根据此值来自动压缩内存
max_depth	no limit	描述了树的最大深度，能够处理模型的过拟合
min_child_samples	20	一片叶子需具有的最小记录数，用来处理过度拟合的问题
feature_fraction	0.8	在每次迭代中随机选择用于构建树的特征的部分
bagging_fraction	0.8	每次迭代要使用的数据，一般用于加快训练和避免过度拟合

特征数	准确率	精确率	召回率	F1值
3	89.74	92.55	93.71	93.13
5	95.00	96.15	97.14	96.65
7	94.91	96.68	96.46	96.57
9	95.00	96.05	97.26	96.65
11	97.29	98.17	98.17	98.17
13	97.03	98.05	97.94	98.00
15	96.78	97.72	97.94	97.83
17	96.86	97.83	97.94	97.89

算法	准确率	精确率	召回率	F1值
GaussianNB	89.40	90.11	96.06	92.99
k-Nearest Neighbors	86.43	92.40	88.76	90.54
Logistic Regression	92.45	95.85	93.74	94.79
Multi-layer Perceptron	92.54	96.86	92.82	94.79
RBF-SVM	88.80	89.17	96.41	92.65
LGBM	96.01	97.43	97.32	97.37
SR-LGBM	97.29	98.17	98.17	98.17

顾及轨迹还原与分类的渣土车作业行为提取方法

Extraction of Muck Truck Operation Behavior Considering Trajectory Restoration and Classification

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 20

参考文献 34

相关文章 3

Metrics

本文评价

推荐阅读 0

[1]	陈传明, 龚杉, 杨峰, 肖振兴, 俞庆英. 基于停留区域识别的子轨迹异常检测方法[J]. 地球信息科学学报, 2023, 25(4): 684-697.
[2]	傅梦颖, 张恒才, 王培晓, 吴升, 陆锋. 基于移动对象轨迹的室内导航网络构建方法[J]. 地球信息科学学报, 2019, 21(5): 631-640.
[3]	齐凌艳, 陈荣国, 温馨. 基于语义轨迹停留点的位置服务匹配与应用研究[J]. 地球信息科学学报, 2014, 16(5): 720-726.