Traffic State Identification of Intersection Based on Semi-supervised Hash Algorithm

Abstract

Abstract:

Accurate identification of traffic conditions at intersections is a prerequisite for implementing effective traffic control strategies. Traditional traffic state identification method, the state identification is realized by using statistical data design indicators such as occupancy rate and queuing. The traffic state can only describe the traffic demand of the intersection from a single angle. This paper proposes a traffic state recognition method based on semi-supervised hash algorithm. Firstly, starting from the rich features of the original data, the image model of the effective detection area of the intersection is constructed. Secondly, the traffic state recognition of the intersection is transformed into the image search problem, and the supervised hash algorithm is used to realize the image search based on the partial label information. The traffic state of the intersection is obtained. Finally, the method is verified by simulation. The results show that the proposed method is feasible and effective in recognition accuracy and speed.

Key words: intelligent transportation, traffic status recognition, intersection image, semi-supervised hash

摘要：

准确辨识交叉口交通状态是实施有效交通控制策略的前提. 传统交通状态识别方法是利用占有率、排队等统计数据设计指标实现状态识别，存在只能从单一角度刻画交叉口交通需求的问题. 对此，提出基于半监督哈希算法的交叉口交通状态识别方法. 从原始数据丰富特征入手，构建交叉口有效检测区域的图像化模型；将交叉口交通状态识别转化为图像搜索问题，利用监督哈希算法实现基于部分标签信息的图像搜索，进而得到交叉口的交通状态；最后，利用仿真对该方法进行了验证. 结果表明，所提方法在识别精度和速度上具有可行性和有效性.

关键词: 智能交通, 交通状态识别, 交叉口图像化, 半监督哈希

CLC Number:

U491.3

ZHANG Li-li,WANG Li, ZHAO Qi, ZHANG Ling-yu. Traffic State Identification of Intersection Based on Semi-supervised Hash Algorithm[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(1): 75-82.

张立立，王力，赵琦，张玲玉. 基于半监督哈希算法的交叉口交通状态识别[J]. 交通运输系统工程与信息, 2020, 20(1): 75-82.

Add to citation manager EndNote|Ris|BibTeX

URL: http://www.tseit.org.cn/EN/abstract/abstract19978.shtml

http://www.tseit.org.cn/EN/Y2020/V20/I1/75

References

[1] GAZIS D C. Optimum control of a system of oversaturated intersections[J]. Operations Research, 1964, 12(6): 815-831.

[2] DION F, RAKHA H, KANG Y S. Comparison of delay estimates at under- saturated and over- saturated pretimed signalized intersections[J]. Transportation Research: Part B, 2004, 38(2): 99-122.

[3] 陈兆盟, 刘小明, 吴文祥, 等. 结合信号控制的交通状态及其真实性识别方法[J]. 重庆交通大学学报(自然科学版), 2016, 35(6): 95-100. [CHEN Z M, LIU X M, WU W X, et al. Identification method of traffic state and its authenticity combined with signal control[J]. Journal of Chongqing Jiaotong University(Natural Science), 2016, 35(6): 95-100]

[4] 吴志勇, 丁香乾, 鞠传香. 一种基于深度学习的离散化交通状态识别方法[J]. 交通运输系统工程与信息, 2017, 17(5): 129-136. [WU Z Y, DING X Q, JU C X. A method of discrete traffic state identification based on deep learning[J]. Journal of Transportation Systems Engineering and Information Technology, 2017, 17(5): 129-136.]

[5] 王力, 张立立, 李敏, 等. 交叉口交通状态精细化识别方法研究[J]. 科学技术与工程, 2016, 16(3-4): 290- 295. [WANG L, ZHANG L L, LI M , et al. Precise judging method study of intersection traffic state[J]. Science Technology and Engineering, 2016, 16(3- 4): 290-295.]

[6] 张立立, 王力, 潘科, 等. 基于综合投影的交叉口交通状态识别方法[J]. 交通运输系统工程与信息, 2016, 16 (2): 83- 91. [ZHANG L L, WANG L, PAN K, et al. Intersection traffic state distinguish method based on comprehensive projection[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(2): 83-91.]

[7] LIU H X, WU X, MA W, et al. Real-time queue length estimation for congested signalized intersections[J]. Transportation Research Part C, 2009, 17(4): 412-427.

[8] 钱喆, 徐建闽. 基于线圈检测的过饱和交通状态识别 [J]. 华南理工大学学报(自然科学版), 2013, 41(8): 93- 98. [QIAN Z, XU J M. Identification of oversaturated traffic conditions based on loop detection[J]. Journal of South China University of Technology(Natural Science Edition), 2013, 41(8): 93-98.]

[9] BAN X, HAO P, SUN Z. Real time queue length estimation for signalized intersections using travel times from mobile sensors[J]. Transportation Research Part C, 2011, 19(6): 1133-1156.

[10] LI F, TANG K, YAO J, et al. Real-time queue length estimation for signalized intersections using vehicle trajectory data[J]. Transportation Research Record Journal of the Transportation Research Board, 2017, 2623: 49-59.

[11] ANTONIOU C, KOUTSOPOULOS H N, YANNIS G. Dynamic data-driven local traffic state estimation and prediction[J]. Transportation Research Part C, 2013, 34 (9): 89-107.

[12] WANG Z, CAI Q, WU B, et al. Cycle-by-cycle queue length estimation for signalized intersections using multi- source data[J]. Journal of Harbin Institute of Technology (New Series), 2015, 22(2): 86-93.

[13] WU A, YANG X. Real-time queue length estimation of signalized intersections based on RFID data ☆ [C]// International Conference on Transportation Information and Safety, 2013: 1061-1067.

[14] 刘云翔, 贾璐, 朱萍. 基于车载电子标签数据的单交叉口状态判别研究[J]. 计算机测量与控制, 2016, 24(1): 277- 280. [LIU Y X, JIA L, ZHU P. Study on single intersection state identification based on vehicle electronic tag data[J]. Computer Measurement & Control, 2016, 24(1): 277-280.]

[15] 唐少虎, 刘小明, 陈兆盟. 基于视频数据的交叉口状态识别及排队长度估计[J]. 交通工程, 2015(1): 58-64. [TANG S H, LIU X M, CHEN Z M. State discriminant and queue length estimation of an intersection based on video data[J]. Road Traffic and Security, 2015(1): 58- 64.]

[16] 黄文成, 帅斌, 左静, 等. 基于修正熵权的未成网城市轨道交通绩效评价[J]. 交通运输系统工程与信息, 2016, 16(6): 115-121. [HUANG W C, SHUAI B, ZUO J, et al. Correct entropy based operation performance evaluation about urban rail transportation non-networks system[J]. Journal of Transportation Systems Engineering and Information Technology, 2016, 16(6): 115-121.]

[17] WANG J, KUMAR S, CHANG S F. Semi- supervised hashing for large-scale search[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34 (12): 2393-2406.

[18] 周建辉. 基于半监督哈希算法的图像检索方法研究 [D]. 大连: 大连理工大学, 2011. [ZHOU J H. Research on image retrieval algorithm based on semi-supervised hashing algorithm[D]. Dalian: Dalian University of Technology, 2011.] 82