
Sensing Vehicle Conditions for Detecting Driving Behaviors
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
This SpringerBrief begins by introducing the concept of smartphone sensing and summarizing the main tasks of applying smartphone sensing in vehicles. Chapter 2 describes the vehicle dynamics sensing model that exploits the raw data of motion sensors (i.e., accelerometer and gyroscope) to give the dynamic of vehicles, including stopping, turning, changing lanes, driving on uneven road, etc. Chapter 3 detects the abnormal driving behaviors based on sensing vehicle dynamics. Specifically, this brief proposes a machine learning-based fine-grained abnormal driving behavior detection and identification system, D3, to perform real-time high-accurate abnormal driving behaviors monitoring using the built-in motion sensors in smartphones.
As more vehicles taking part in the transportation system in recent years, driving or taking vehicles have become an inseparable part of our daily life. However, increasing vehicles on the roads bring more traffic issues including crashes and congestions, which make it necessary to sense vehicle dynamics and detect driving behaviors for drivers. For example, sensing lane information of vehicles in real time can be assisted with the navigators to avoid unnecessary detours, and acquiring instant vehicle speed is desirable to many important vehicular applications. Moreover, if the driving behaviors of drivers, like inattentive and drunk driver, can be detected and warned in time, a large part of traffic accidents can be prevented. However, for sensing vehicle dynamics and detecting driving behaviors, traditional approaches are grounded on the built-in infrastructure in vehicles such as infrared sensors and radars, or additional hardware like EEG devices and alcohol sensors, which involves high cost. The authors illustrate that smartphone sensing technology, which involves sensors embedded in smartphones (including the accelerometer, gyroscope, speaker, microphone, etc.), can be applied in sensing vehicle dynamics and driving behaviors.
Chapter 4 exploits the feasibility to recognize abnormal driving events of drivers at early stage. Specifically, the authors develop an Early Recognition system, ER, which recognize inattentive driving events at an early stage and alert drivers timely leveraging built-in audio devices on smartphones. An overview of the state-of-the-art research is presented in chapter 5. Finally, the conclusions and future directions are provided in Chapter 6.
More details
Other editions
Additional editions

Content
2 - Contents [Seite 8]
3 - 1 Overview [Seite 10]
3.1 - 1.1 Brief Introduction of Smartphone Sensing [Seite 10]
3.1.1 - 1.1.1 Representative Sensors Embedded in Smartphones [Seite 10]
3.1.2 - 1.1.2 Development of Smartphone Sensing [Seite 11]
3.2 - 1.2 Smartphone Sensing in Vehicles [Seite 12]
3.3 - 1.3 Overview of the Book [Seite 13]
4 - 2 Sensing Vehicle Dynamics with Smartphones [Seite 15]
4.1 - 2.1 Introduction [Seite 15]
4.2 - 2.2 Pre-processing Sensor Readings [Seite 16]
4.2.1 - 2.2.1 Coordinate Alignment [Seite 16]
4.2.2 - 2.2.2 Data Filtering [Seite 18]
4.3 - 2.3 Sensing Basic Vehicle Dynamics [Seite 19]
4.3.1 - 2.3.1 Sensing Movement of Vehicles [Seite 19]
4.3.2 - 2.3.2 Sensing Driving on Uneven Road [Seite 20]
4.3.3 - 2.3.3 Sensing Turning of Vehicles [Seite 21]
4.3.4 - 2.3.4 Sensing Lane-Changes of Vehicles [Seite 22]
4.3.4.1 - 2.3.4.1 Identifying Single Lane-Change [Seite 22]
4.3.4.2 - 2.3.4.2 Identifying Sequential Lane-Change [Seite 23]
4.3.5 - 2.3.5 Estimating Instant Speed of Vehicles [Seite 25]
4.4 - 2.4 Evaluation [Seite 28]
4.4.1 - 2.4.1 Setup [Seite 28]
4.4.2 - 2.4.2 Metrics [Seite 28]
4.4.3 - 2.4.3 Performance of Sensing Vehicle Dynamics [Seite 29]
4.4.4 - 2.4.4 Performance of Sensing Lane-Change [Seite 29]
4.4.5 - 2.4.5 Performance of Sensing Instance Speed [Seite 30]
4.5 - 2.5 Conclusion [Seite 31]
5 - 3 Sensing Vehicle Dynamics for Abnormal Driving Detection [Seite 32]
5.1 - 3.1 Introduction [Seite 32]
5.2 - 3.2 Driving Behavior Characterization [Seite 35]
5.2.1 - 3.2.1 Collecting Data from Smartphone Sensors [Seite 35]
5.2.2 - 3.2.2 Analyzing Patterns of Abnormal Driving Behaviors [Seite 36]
5.3 - 3.3 System Design [Seite 37]
5.3.1 - 3.3.1 Overview [Seite 37]
5.3.2 - 3.3.2 Extracting and Selecting Effective Features [Seite 39]
5.3.2.1 - 3.3.2.1 Feature Extraction [Seite 39]
5.3.2.2 - 3.3.2.2 Feature Selection [Seite 39]
5.3.3 - 3.3.3 Training a Fine-Grained Classifier Model to Identify Abnormal Driving Behaviors [Seite 40]
5.3.4 - 3.3.4 Detecting and Identifying Abnormal Driving Behaviors [Seite 42]
5.4 - 3.4 Evaluations [Seite 44]
5.4.1 - 3.4.1 Setup [Seite 44]
5.4.2 - 3.4.2 Metrics [Seite 45]
5.4.3 - 3.4.3 Overall Performance [Seite 45]
5.4.3.1 - 3.4.3.1 Total Accuracy [Seite 45]
5.4.3.2 - 3.4.3.2 Detecting the Abnormal vs. the Normal [Seite 46]
5.4.3.3 - 3.4.3.3 Identifying Abnormal Driving Behaviors [Seite 46]
5.4.4 - 3.4.4 Impact of Training Set Size [Seite 47]
5.4.5 - 3.4.5 Impact of Traffic Conditions [Seite 48]
5.4.6 - 3.4.6 Impact of Road Type [Seite 48]
5.4.7 - 3.4.7 Impact of Smartphone Placement [Seite 49]
5.5 - 3.5 Conclusion [Seite 50]
6 - 4 Sensing Driver Behaviors for Early Recognition of Inattentive Driving [Seite 51]
6.1 - 4.1 Introduction [Seite 51]
6.2 - 4.2 Inattentive Driving Events Analysis [Seite 52]
6.2.1 - 4.2.1 Defining Inattentive Driving Events [Seite 53]
6.2.2 - 4.2.2 Analyzing Patterns of Inattentive Driving Events [Seite 54]
6.3 - 4.3 System Design [Seite 56]
6.3.1 - 4.3.1 System Overview [Seite 56]
6.3.2 - 4.3.2 Model Training at Offline Stage [Seite 57]
6.3.2.1 - 4.3.2.1 Establishing Training Dataset [Seite 57]
6.3.2.2 - 4.3.2.2 Extracting Effective Features [Seite 57]
6.3.2.3 - 4.3.2.3 Training a Multi-Classifier [Seite 58]
6.3.2.4 - 4.3.2.4 Setting Up Gradient Model Forest for Early Recognition [Seite 60]
6.3.3 - 4.3.3 Recognizing Inattentive Driving Events at Online Stage [Seite 62]
6.3.3.1 - 4.3.3.1 Segmenting Frames Through Sliding Window [Seite 62]
6.3.3.2 - 4.3.3.2 Detecting Inattentive Driving Events at Early Stage [Seite 63]
6.4 - 4.4 Evaluation [Seite 64]
6.4.1 - 4.4.1 Setup [Seite 64]
6.4.2 - 4.4.2 Metrics [Seite 64]
6.4.3 - 4.4.3 Overall Performance [Seite 65]
6.4.3.1 - 4.4.3.1 Total Accuracy [Seite 65]
6.4.3.2 - 4.4.3.2 Recognizing Inattentive Driving Events [Seite 66]
6.4.3.3 - 4.4.3.3 Realizing Early Recognition [Seite 66]
6.4.4 - 4.4.4 Impact of Training Set Size [Seite 67]
6.4.5 - 4.4.5 Impact of Road Types and Traffic Conditions [Seite 68]
6.4.6 - 4.4.6 Impact of Smartphone Placement [Seite 69]
6.5 - 4.5 Conclusion [Seite 69]
7 - 5 State-of-Art Researches [Seite 71]
7.1 - 5.1 Smartphone Sensing Researches [Seite 71]
7.2 - 5.2 Vehicle Dynamics Sensing Researches [Seite 72]
7.3 - 5.3 Driver Behaviors Detection Researches [Seite 73]
7.4 - 5.4 Common Issues [Seite 74]
8 - 6 Summary [Seite 75]
8.1 - 6.1 Conclusion of the Book [Seite 75]
8.2 - 6.2 Future Directions [Seite 76]
9 - References [Seite 77]
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.