基于差异性区域预测的行人与骑车人联合检测

doi:10.19562/j.chinasae.qcgc.2021.01.010

摘要/Abstract

摘要：

本文中针对自动驾驶车辆在环境感知过程中易将行人与骑车人混淆的问题，提出一种有效区分行人与骑车人的联合检测方法，并基于快速区域卷积神经网络Faster R?CNN进行改进。首先，通过增加一个子网络提取图像形状特征通道，将其与主干网络生成的特征图进行聚合，额外的形状语义通道用以辅助检测器区分行人与骑车人的特征；接着，通过构建差异性区域预测单元，以区分行人与骑车人差异部位，将建议区域划分为多个部件并计算其置信度，根据该置信度对部件特征进行加权；最后，将主体特征与加权后的部件特征聚合后送至分类器进行分类。在本文中构建的行人-骑车人数据集和公开的Caltech数据集中进行测试的结果表明，改进后的检测方法能有效减少将骑车人误检为行人的情况，具有较高的检测精度。

关键词: Faster R?CNN, 通道聚合, 差异性区域预测, 行人检测, 骑车人检测

Abstract:

Aiming at the problem that autonomous vehicles tend to confuse pedestrians and riders in the process of environmental perception， a joint detection method to effectively distinguish pedestrians and riders is proposed in this paper， with an improvement made based on faster region convolutional neural networks. Firstly， a subnetwork is added to extract the shape feature channel of images， which is then aggregated with the feature map generated by the backbone network， and the additional shape semantic channels are used for assisting the detector to distinguish the pedestrian and rider features. Then， a diversity region prediction unit is constructed to distinguish the distinct parts between pedestrians and riders and the suggested regions are divided into several parts with their confidence calculated， which is then used to determine the weight of part feature. Finally， the part features are aggregated with main?body feature and are sent to classifier for classification. The results of test on both pedestrian - rider data set built in this paper and open Caltech data set show that the improved detection method has relatively high detection accuracy， and the situations of the rider being mis?detected as pedestrian are effectively reduced.

Key words: Faster R?CNN, channel aggregation, diversity region prediction, pedestrian detection, rider detection

肖艳秋,周坤,崔光珍,房占鹏,孙启迪,刘燕旗. 基于差异性区域预测的行人与骑车人联合检测[J]. 汽车工程, 2021, 43(1): 77-85.

Yanqiu Xiao,Kun Zhou,Guangzhen Cui,Zhanpeng Fang,Qidi Liu Yanqi Sun. Joint Detection of Pedestrian and Rider Based on Diversity Region Prediction[J]. Automotive Engineering, 2021, 43(1): 77-85.

图/表 14

图1

图2

图3

图4

图5

图6

图7

表1

图8

图9

图10

图11

表2

图12

参考文献 27

1	SCHRODER E， BRAUN S， MAHLISCH M， et al. Feature map transformation for multi⁃sensor fusion in object detection networks for autonomous driving［C］. Science and Information Conference， 2019：118-131.
2	CHOI J， CHUN D， KIM H， et al. Gaussian YOLOv3：an accurate and fast object detector using localization uncertainty for autonomous driving［C］. International Conference on Computer Vision， 2019：502-511.
3	ZHANG L， LIN L， LIANG X， et al. Is faster R⁃CNN doing well for pedestrian detection？［C］. European Conference on Computer Vision， 2016：443-457.
4	REN S ， HE K ， GIRSHICK R ， et al. Faster R⁃CNN：towards real⁃time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017， 39（6）：1137-1149.
5	DOLLA P. Pedestrian detection：a benchmark［C］. Proceedings / CVPR， IEEE Computer Society Conference on Computer Vision and Pattern Recognition， 2009：304-311.
6	MAO J， XIAO T， JIANG Y， et al. What can help pedestrian detection［C］. Computer Vision and Pattern Recognition， 2017：6034-6043.
7	李晓飞，许庆，熊辉，等. 基于候选区域选择及深度网络模型的骑车人识别［J］. 清华大学学报（自然科学版）， 2017， 57（5）：491-496.
	LI X F， XU Q， XIONG H， et al. Cyclist identification based on candidate area selection and deep network model ［J］. Journal of Tsinghua University （Natural Science edition）， 2017， 57（5）：491-496.
8	陈文强，熊辉，李克强，等.基于深度神经网络的行人及骑车人联合检测［J］.汽车工程，2018，40（6）：726-732，725.
	CHEN W Q， XIONG H， LI K Q， et al. Joint detection of pedestrians and cyclists based on deep neural network ［J］. Automotive Engineering， 2018，40（6）：726-732，725.
9	LIU C， GUO Y， LI S， et al. ACF based region proposal extraction for YOLOv3 network towards high⁃performance cyclist detection in high resolution images［J］. Sensors， 2019， 19（12）.
10	REDMON J， DIWALA S K， GIRSHICK R， et al. You only look once：unified， real⁃time object detection［C］. Computer Vision and Pattern Recognition， 2016：779-788.
11	GIRSHICK R. Fast R⁃CNN［C］. International Journal of Computer Vision， 2015：1440-1448.
12	UIJLINGS J， SANDE K E， GEVERS T， et al. Selective search for object recognition［J］. International Journal of Computer Vision， 2013， 104（2）：154-171.
13	LIU W ， ANGUELOV D ， ERHAN D ， et al. SSD：single shot multibox detector［C］. European Conference on Computer Vision， 2016：21-37.
14	SIMONYAN K ， ZISSERMAN A. Very deep convolutional networks for large⁃scale image recognition［J］. Computer Science， 2014.
15	LIU W ， LIAO S ， REN W ， et al. High⁃level semantic feature detection：a new perspective for pedestrian detection［J］. Computer Vision and Pattern Recognition， 2019.
16	FELZENSZWALB P F， MCALLESTER D， RAMANAN D， et al. A discriminatively trained， multiscale， deformable part model［C］. Computer Vision and Pattern Recognition， 2008：1-8.
17	XIE S ， TU Z. Holistically⁃nested edge detection［J］. Interna⁃tional Journal of Computer Vision， 2017， 125（5）：3-18.
18	HUANG G ， LIU Z ， LAURENS V D M ， et al. Densely connected convolutional networks［J］. IEEE Computer Society， 2017：2261-2269.
19	CAO G， XIE X， YANG W， et al. Feature⁃fused SSD：fast detection for small objects［J］. arXiv：Computer Vision and Pattern Recognition， 2018.
20	BRAZIL G， YIN X， LIU X， et al. Illuminating pedestrians via simultaneous detection and segmentation［C］. International Conference on Computer Vision， 2017：4960-4969.
21	OUYANG W， ZHOU H， LI H， et al. Jointly learning deep features， deformable parts， occlusion and classification for pedestrian detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2018， 40（8）：1874-1887.
22	DALAL N， TRIGGS B. Histograms of oriented gradients for hu⁃man detection［C］. Computer Vision and Pattern Recognition， 2005：886-893.
23	DOLLAR P， APPEL R， BELONGIE S，et al. Fast feature pyramids for object detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2014， 36（8）：1532-1545.
24	NAM W， DOLLAR P， HAN J H， et al. Local decorrelation for improved pedestrian detection［C］. Neural Information Processing Systems， 2014：424-432.
25	ZHANG S ， YANG J ， SCHIELE B. Occluded pedestrian detection through guided attention in CNNs［C］. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. IEEE， 2018：6995-7003.
26	OUYANG W， WANG X. Joint deep learning for pedestrian detection［C］. International Conference on Computer Vision， 2013：2056-2063.
27	TIAN Y， LUO P， WANG X， et al. Pedestrian detection aided by deep learning semantic tasks［C］. Computer Vision and Pattern Recognition， 2015：5079-5087.

[1]	吴桐,王宇宁,关艺搏,田韶鹏. 基于改进门控上下文聚合网络的雾天实时行人检测方法[J]. 汽车工程, 2023, 45(5): 796-806.
[2]	朱波, 黄茂飞, 谈东奎, 胡旭东, 顾家鑫. 基于神经网络与数据融合的行人检测方法^*[J]. 汽车工程, 2020, 42(11): 1482-1489.
[3]	白中浩, 李智强, 蒋彬辉, 王鹏辉. 基于改进YOLOv2模型的驾驶辅助系统实时行人检测^*[J]. 汽车工程, 2019, 41(12): 1416-1423.
[4]	陈文强,熊辉,李克强,李晓飞,张德兆. 基于深度神经网络的行人及骑车人联合检测[J]. 汽车工程, 2018, 40(6): 726-.