深度学习下智能驾驶道路目标检测算法设计,软件工程硕士论文.docx
![资源得分’ title=](/images/score_1.gif)
![资源得分’ title=](/images/score_1.gif)
![资源得分’ title=](/images/score_1.gif)
![资源得分’ title=](/images/score_1.gif)
![资源得分’ title=](/images/score_05.gif)
《深度学习下智能驾驶道路目标检测算法设计,软件工程硕士论文.docx》由会员分享,可在线阅读,更多相关《深度学习下智能驾驶道路目标检测算法设计,软件工程硕士论文.docx(10页珍藏版)》请在淘文阁 - 分享文档赚钱的网站上搜索。
1、深度学习下智能驾驶道路目标检测算法设计,软件工程硕士论文随着经济的发展和鼓励政策的出台,我们国家的汽车产业呈高速发展趋势。国内汽车保有量不断增加,汽车出行在给人们带来便利的同时,也带来了极大的安全威胁。近年来人工智能兴起,智能驾驶的概念也随之被提出。目的检测模块作为智能驾驶的首要环节,需要准确辨别道路前方的汽车、非机动车和行人等目的。在实际应用场景中道路状况复杂,光照的变化、目的姿态的多样性和遮挡等多重因素,都会影响目的检测系统的精到准确度,进而影响智能驾驶的安全性。 基于深度学习的目的检测算法依托深层卷积神经网络,具有强大的学习能力和场景分析能力,当前主流的深度学习目的检测算法包括以 Fas
2、ter-RCNN 为代表的基于区域提取的两阶段检测算法和以 SSD、YOLO 为代表的基于回归的单阶段检测算法。考虑智能驾驶场景中对检测算法的实时性有较高要求,本文以单阶段检测算法为基础进行研究。详细如下: 1. 研究了目的检测相关的基础工作,分析了传统目的检测算法和基于深度学习的目的检测方式方法及其原理,梳理了卷积神经网络的模型构造。传统卷积层的几何构造固定,卷积核感受野受限,缺乏内部变化机制,无法适应目的的尺度变换和形变。除此之外,深度神经网络模型的训练中常存在内部协变量变化问题,为了解决此问题,目的检测算法中一般使用批规范化操作来调整数据的分布,然而该方式方法只保存了单个样本间的区别,使
3、得网络易受外观变化的影响。 2. 针对单阶段目的检测算法中的典型算法 YOLO 及 YOLOv2,深切进入分析了该算法的网络构造和优缺点,通过改良 YOLOv2 算法的基础网络来提升算法的精度。本文将计算量和性能较为适宜的 Resnet101 特征提取网络与 YOLOv2 算法进行融合,通过在 KITTI 数据集上的比照,证明了融合方式方法的有效性,融合后网络在精度上有所提升。 3. 本文在 YOLOv2 融合网络的基础上改良了卷积层的构造和规范化的方式。使用可调制变形卷积代替深度网络中的上层卷积,使用规范化方式 IBN 对网络的底层进行特征规范化。改良后的算法在 KITTI 数据集上效果良好
4、,提升了非机动车和行人等形变较大的目的的检测精度。将本文的算法在自行采集的驾驶视频中进行实验,结果显示该算法能够适应雾霾、隧道等光线条件较差的场景。 本文关键词语: 深度学习,目的检测,道路场景,可调制变形卷积,IBN。 Abstract Research on Road Scenes Object Detection Based on Deep Learning With the development of economy and the promulgation of encouragement policies, China s automobile industry has been
5、 developing at a high speed. With thenumber of domestic car ownership increasing, traveling by car not only brings convenience to people, but also brings great security threats. In recent years, artificial intelligence has been arisen and the concept of intelligent driving has also been proposed. As
6、 the first step of intelligent driving, object detection needs to identify the targets such as vehicle, non-motor vehicle and pedestrian in front of the road accurately. But in practical application scenarios, road conditions are complex,factors which variant to the illumination, poses and truncatio
7、n will affect the precision of object detection system, and then it will affect the safety of intelligent driving. Object detection algorithm based on deep learning depend on a deep Convolutional neural networks, and has a strong learning and scenario analysis ability. At present, the main object de
8、tection algorithm based on deep learning includes two-stage detection with region proposals represented by Faster-RCNN and asingle-stage detection with regression represented by SSD and YOLO. Considering the high-speed requirements of the detection algorithm in the intelligent driving scene, this pa
9、per studies on a single-stage detection. The details are as follows: 1. I have studied on the basic work related to object detection, and analyzed the traditional object detection algorithm and the object detection method based on deep learning, and sorted out the model structure of convolutional ne
10、ural network. The geometric structure of the traditional convolutional layer is fixed, the receptive field of the convolution kernel is limited, lacking the internal change mechanism, so it cannot adapt to the scale variation and part deformation. In order to solve the problem of internal covariate
- 配套讲稿:
如PPT文件的首页显示word图标,表示该PPT已包含配套word讲稿。双击word图标可打开word文档。
- 特殊限制:
部分文档作品中含有的国旗、国徽等图片,仅作为作品整体效果示例展示,禁止商用。设计者仅对作品中独创性部分享有著作权。
- 关 键 词:
- 文化交流
![提示](https://www.taowenge.com/images/bang_tan.gif)
限制150内