• / 14
  • 下载费用:29.9 金币  

【精品文档】05中英文双语毕设外文翻译成品:V2V协同环境中对智能车辆进行快速行人检测和动态跟踪

关 键 词:
【精品文档】
资源描述:
此文档是毕业设计外文翻译成品( 含英文原文+中文翻译),无需调整复杂的格式!下载之后直接可用,方便快捷!本文价格不贵,也就几十块钱!一辈子也就一次的事!外文标题:Fast pedestrian detection and dynamic tracking for intelligent vehicles within V2V cooperative environment外文作者:Fuliang Li, Ronghui Zhang , Feng You文献出处:《Iet Image Processing》 , 2018 , 11 (10) :833-840(如觉得年份太老,可改为近2年,毕竟很多毕业生都这样做)英文2203单词, 14998字符(字符就是印刷符),中文3668汉字。原文:Fast pedestrian detection and dynamic tracking for intelligent vehicles within V2V cooperative environmentFuliang Li, Ronghui Zhang , Feng YouAbstract: Pedestrian detection has become one of the hottest topics in intelligent traffic system because of its potential applications in driver assistance and automatic driving. In this study, a fast pedestrian detection and dynamic tracking method within vehicle-to-vehicle (V2V) cooperative environment is proposed. A dynamic tracking-by-detection framework for real-time pedestrian detection is developed. First, a cascade classifiers, based on selected Haar-like features, is trained to detect pedestrian. Then, CamShift algorithm combined with extended Kalman filtering is used to pedestrian dynamic tracking. Finally, with the crowdsourcing detected information, a smartphone-based V2V cooperative warning system is developed to share useful detection results within blind spots. The experiment results show that the proposed method has a real-time and accurate performance, which can provide a reference for road traffic safety monitoring technology.IntroductionIn recent years, pedestrian deaths resulting from the complex traffic environment accounted for 60% of all deaths on the roads [1]. Aiming to reduce collision and danger to pedestrians from traffic, pedestrian active safety analysis has become an international research focus, especially pedestrian detection technology.In general, pedestrian detection methods can be divided into target characteristics template-based and pedestrian-based learning methods. The former type of methods cost less and are relatively simple. However, those methods only work well by detected obvious contour, and their detection effects have a direct relationship with template choice. Davis and Mark [2] proposed a two-step template method based on infrared images. Detection results are correlated with the selected template directly. A pedestrian gait pattern based template detection method is proposed by Bertozzi et al. [3]. The method first calculates human probability template based on pedestrian gait pattern, and then determines whether the object is a pedestrian or not using calculated joint probability. This method is applicable to detect pedestrian with leg visible. Zhuang and Liu [4] put forward a probability template-matching algorithm to realise pedestrian detection. The method uses the local double segmentation threshold to extract candidate targets and traverse the multi-scale probability template. This method requires fewer samples but the error rate is higher in complex urban road environment, and real-time performance is poor.Pedestrian tracking is expected to predict information such as pedestrian's position in the next few frames based on the detection information in the current frame. In general, continuous detection can be replaced by pedestrian tracking for enhancing the pedestrian detection's real-time performance [14]. Probability-based pedestrian tracking method is a research hotspot for solving tracking problems. Without loss of generality, pedestrian tracking can be treated as a state estimation issue. The Kalman filtering and the particle filter tracking method are common methods in this field [15]. Liu et al. [16] proposed a CamShift moving-target tracking algorithm, using the extended Kalman filter to estimate targets’ motion speed and spatial location. Li et al. [17] developed an adaptive Kalman filter tracking algorithm, which modify the statistical model of the filter in real time and apply the least squares SVM to estimate target moving direction. Wang and Tang [18] proposed a particle filter pedestrian tracking method using piecewise Gaussian model, which applies piecewise Gaussianmodel based probability distribution to estimate pedestrian maximum likelihood moving direction directly.The key contributions of this proposed method include: a dynamic tracking-by-detection method for real-time pedestrian detection, which means that selected Haar-like features based cascade classifiers are proposed to detect pedestrian first, and then make a dynamic pedestrian tracking using CamShift algorithm combined with extended Kalman filtering (EKF). A smart phone based V2V cooperative warning system is developed to share useful detection results within blind spots.Selected Haar-like based cascade classifiers for fast pedestrian detectionSelected Haar-like features and weak classifier trainingHaar-like features are defined as the differences in the greyscale sum of black and white rectangles’ corresponding regions in the image sub-window, which can extract image texture features effectively. For pedestrian detection, the most frequent changes of greyscale are in the vertical and horizontal directions. Thus, this paper selects global eight types or local human shape rectangular feature shown in Fig. 1, from which the differences of characteristics in appearance can be highlighted effectively.Haar-like features can be computed rapidly using intermediate representation called the integral image [22]. The integral image at location (x, y), denoted by ii(x, y), contains the sum of the pixel values above and to the left of (x, y) shown in Fig. 2a, which canbe calculated bywhere I(x′, y′) is the original image that can be obtained using following iterative calculations:Thus, the integral image can be computed in just one pass over the original image, which means that we can calculate the value of selected Haar-like features rapidly. Take four array references shown in Fig. 2b as an example, the integral image value at location 1 for the regional grey level A sum is denoted by A. Correspondingly, the values of locations 2, 3, and 4 are A + B, A + C, and A + B + C + D. Finally, the sum within rectangular region D can be expressed as 4 + 1−(2 + 3).During the classifiers training process, an improved Adaboost algorithm was used to process weak classifiers training based on minimum error rate principle, which can reduce the weight of samples with the correct classification, but increase the weight of samples with the wrong classification. More precisely, the weak offline trained classifiers can decrease the error rate and shorten the training time at the same time. Then, strong classifiers can be obtained, which are composed of several weak classifiers using linear superposition. More details about the training process can refer to our previous research work [5].Design of the cascade classifierCascade structure, a kind of degeneration decision tree, focuses on processing the key image region [23]. Each strong classifier search window is moved across the input target and check whether there is pedestrian or not. Only the input target passing through all strong classifiers can be considered as pedestrian. The flowchart of cascade classier is shown in Fig. 3.V2V cooperative warning platformThere are some typical blind spots in urban traffic conditions, such as turning, lane-changing areas at intersection or merging sections, where the above pedestrian detection and tracking methods cannot work effectively. In this case, using V2V communication is one of ways to share pedestrian warning information out of individual vehicle detection range. Based on those timely cooperative warning information, the driver can make more reliable decisions and has a better chance of reacting properly emergency situations. However, there are several challenges during the pedestrian cooperative warning process. The first is position interruption, which is the distance between the locations positioned by global positioning system (GPS) receiver and the actual location. Inaccurate sensor information leads to uncertain vehicle or pedestrian state information that influences the cooperative warning system performance. Another challenge is redundant information, which means that there is the possibility of overloading the driver with too much warning information.To reduce pedestrian collision probability, we propose a novel cooperative warning framework to share pedestrian warning information within V2V cooperative environment. Detected pedestrian warning information, including pedestrian's position, speed, and movement, can be shared to related vehicles in blind spots. The above position interruption and redundant information are two significant issues which this framework has tried to deal with. To reduce the impact of position interruption, the framework develops a double GPS positioning system using carrier phase differential technology to improve positioning accuracy on one hand and make an optimisation for broadcasting interval on the other hand [27]. More details are discussed in Section 5. A tradeoff mechanism is proposed between a successful warning and the risk disturbing drivers to release redundant information. Without loss of generality, we assume that the vehicle traveling route information is known. Thus, the tradeoff issue can be transferred into a cluster optimisation problem. Based on vehicle GPS and pedestrian detection and tracking information, the backstage information processing center (BIPC) first classify all vehicles in blind spots into potential collision and collision-free vehicles. Then, the BIPC make different degree warning information for potential vehicles based on collision probability. The flowchart of the proposed framework is shown in Fig. 6.More precisely, the application scenario description is as follows: a host vehicle detects and tracks pedestrians using the above proposed fast pedestrian detection and dynamic tracking method, which was introduced in Sections 2 and 3. Then its GPS data and pedestrian GPS data estimated by single-frame static image distance model are sent to the BIPC via 4G network [28]. After that, the BIPC determines the pedestrian speed and moving direction through analysing pedestrian GPS data sequences first. Then the BIPC make a cluster of surrounding vehicles in blind spots into potential collision and collision-free vehicles. Further collision probabilities are calculated by potential collision vehicle and pedestrian GPS data. Finally, the BIPC broadcasts different degree timely warning information to potential collision vehicles.ExperimentsTo validate the proposed method, we develop a system using Visual 2010 and Intel OpenCV to test it. Then, it is transplanted to the HUAWEI GlORY mobile phone. It has hardware configurations of Hisilicon Kirin 935 + 3GB RAM + 2000W BSI camera to realise fast pedestrian detection. All test equipments were installed into a Chery Tiggo NCV vehicle shown in Fig. 7.ConclusionIn this paper, we present a fast pedestrian detection and dynamic tracking method for intelligent vehicles within V2V cooperative environment. The key contributions of this proposed method include: a dynamic tracking-by-detection method for real-time pedestrian detection, which means that selected Haar-like features based cascade classifiers are proposed to detect pedestrian first. Then in view of the non-linear characteristics of urban road conditions, a dynamic pedestrian tracking using CamShift algorithm combined with EKF is developed to improve the real- time performance of pedestrian detection. Also, a smartphone-based V2V cooperative warning system is developed to share useful detection results within blind spots, which reduce single vehicle's blind spots and lower accident rates at the intersection area. The road experiment results show that the proposed fast pedestrian detection method has a more robust, higher performance compared with other state-of-the-art methods.However, this paper cannot analyse the effect of bad weather (such as rain, fog day) and vehicle speed on the algorithm's performance and reliability [32] due to experiment environment lmitation. All of those will be the focus of our future research work.References[1] Zhang, S., Christian, B., Armin, B.C.: ‘Efficient pedestrian detection via rectangular features based on a statistical shape model’, IEEE Trans. Intell. Transp. Syst., 2015, 16, (2), pp. 763-775[2] Davis, J.W., Mark, A.K.: ‘A two-stage template approach to person detection in thermal imagery’, IEEE Workshop Motion Video Comput., 2005, 2005, pp. 364-369[3] Bertozzi, M., Broggi, A., Del, R.M., et al.: ‘A pedestrian detector using histograms of oriented gradients and a support vector machine classifier’. IEEE Conf. on Intelligent Transportation Systems, 2007, pp. 143-148[4] Zhuang, J., Liu, Q.: ‘Nighttime pedestrian detection method for driver assistance systems’, J. South China Univ. Technol., 2012, 40, (8), pp. 56-62[5] Li, F., You, F., Zhang, R., et al.: ‘An improved real-time detection and localization scheme for pedestrian based on information fusion’, Int. J. Appl. Math. Stat., 2013, 51, (22), pp. 99-107[6] Can, Y, Li, B., Xu, G.: ‘Particle filter based multi-pedestrian tracking by HOG and HOF’. 4th IEEE Int. Conf. on Information Science and Technology, 2014, pp. 714-717[7] Guo, L., Zhang, M., Li, L., et al.: ‘Body parts features based pedestrian detection for active pedestrian protection system’, Promet — Traffic — Traffico, 2016, 28, (2), pp. 113-142[8] Yao, S., Pan, S., Wang, T., et al.: ‘A new pedestrian detection method based on combined HOG and LSS features’, Neurocomputing, 2015, 151, (2015), pp. 1006-1014[9] Dollar, P, Wojek, C., Schiele, B., et al.: ‘Pedestrian detection: an evaluation of the state of the art’, IEEE Trans. Pattern Anal. Mach Intell., 2012, 34, (4), pp. 743-761[10] Oliveira, L., Urbano, N., Paulo, P.: ‘On exploration of classifier ensemble synergism in pedestrian detection’, IEEE Trans. Intell. Transp. Syst., 2010, 11,(I) ,pp. 16-27[11] Ge, J., Luo, Y., Tei, G.: ‘Real-time pedestrian detection and tracking at nighttime for driver-assistance systems’, IEEE Trans. Intell. Transp. Syst., 2009, 10, (2), pp. 283-298[12] Xu, Y., Xu, D., Lin, S., et al.: ‘Detection of sudden pedestrian crossings for driving assistance systems’, IEEE Trans. Syst. Man Cybern B, Cybern., 2012, 42, (3), pp. 729-739[13] Sun, H., Cheng, W., Wang, B., et al.: ‘Pyramid binary pattern features for real-time pedestrian detection from infrared videos’, Neurocomputing, 2011, 74, (5), pp. 797-804[14] Dollar, P., Wojek, C., Schiele, B., et al.: ‘Pedestrian detection: a benchmark’. IEEE Conf. on Computer Vision and Pattern Recognition, 2009, pp. 304~311[15] Levi, D., Silberstein, S., Bar-Hillel, A.: ‘Fast multiple-part based object detection using kd-ferns’. IEEE Conf. on Co
展开阅读全文
  麦档网所有资源均是用户自行上传分享,仅供网友学习交流,未经上传用户书面授权,请勿作他用。
0条评论

还可以输入200字符

暂无评论,赶快抢占沙发吧。

关于本文
本文标题:【精品文档】05中英文双语毕设外文翻译成品:V2V协同环境中对智能车辆进行快速行人检测和动态跟踪
链接地址:https://www.maidoc.com/p-15592979.html

当前资源信息

从****越

编号: 20191025211927491

类型: 共享资源

格式: DOC

大小: 480.00KB

上传时间: 2019-10-27

相关搜索

关于我们 - 网站声明 - 网站地图 - 资源地图 - 友情链接 - 网站客服 - 联系我们

[email protected] 2018-2020 maidoc.com版权所有  文库上传用户QQ群:3303921 

麦档网为“文档C2C模式”,即用户上传的文档所得金币直接给(下载)用户,本站只是中间服务平台,本站所有文档下载所得的金币归上传人(含作者)所有。
备案号:蜀ICP备17040478号-3  
川公网安备:51019002001290号 

本站提供办公文档学习资料考试资料文档下载


收起
展开