diff --git a/Bachelorarbeit.pdf b/Bachelorarbeit.pdf
index e90698f258c94d456f55bb893abbc2750d58a352..e8c62179aad8b4814d341464e43975a5e819aab1 100644
Binary files a/Bachelorarbeit.pdf and b/Bachelorarbeit.pdf differ
diff --git a/Bachelorarbeit.tex b/Bachelorarbeit.tex
index 9e9f13d1165d05c1f69cfbef5ff50a1642d50ca8..7232a56e739a73c37cf2d2e1c3f912e0b591710d 100644
--- a/Bachelorarbeit.tex
+++ b/Bachelorarbeit.tex
@@ -59,6 +59,8 @@
\todo[inline]{Schreibweise von langen Worten vereinheitlichen. Bindestrichen oder alles zusammen?}
\todo[inline]{Schwarzweißbild zu Grauwertbild und überall einheitlich}
+ \nocite{LaneDetector:driverAssistanceSystems}
+
\include{chap/einleitung}
\include{chap/standdertechnik}
diff --git a/bib/Quellenverzeichnis.bib b/bib/Quellenverzeichnis.bib
index 1b979790cdece34c46c3de14d4d8fe2f649c7c84..19470ec081ab7c22c89a5a98fba26b37079c9e71 100644
--- a/bib/Quellenverzeichnis.bib
+++ b/bib/Quellenverzeichnis.bib
@@ -53,6 +53,17 @@
doi = {10.1007/978-3-8348-8323-0}
}
+@book{szelisk:computerVision-algos+application,
+ author = {Szeliski, Richard},
+ year = {2011},
+ title = {Computer Vision},
+ subtitle = {Algorithms and Applications},
+ publisher = {Springer},
+ language = {eng},
+ location = {London},
+ series = {SpringerLink B{\"u}cher},
+ doi = {10.1007/978-1-84882-935-0}
+}
@inproceedings{paper:Distance_via_InversPerspectiveMapping,
@@ -171,7 +182,7 @@
number = {11}
}
-@article{landeDetectionMethodes:deepLearning,
+@article{review:landeDetectionMethodes-deepLearning,
author = {Tang, Jigang and Li, Songbin and Liu, Peng},
title = {A review of lane detection methods based on deep learning},
journal = {Pattern Recognition},
@@ -185,6 +196,18 @@
abstract = {Lane detection is an application of environmental perception, which aims to detect lane areas or lane lines by camera or lidar. In recent years, gratifying progress has been made in detection accuracy. To the best of our knowledge, this paper is the first attempt to make a comprehensive review of vision-based lane detection methods. First, we introduce the background of lane detection, including traditional lane detection methods and related deep learning methods. Second, we group the existing lane detection methods into two categories: two-step and one-step methods. Around the above summary, we introduce lane detection methods from the following two perspectives: (1) network architectures, including classification and object detection-based methods, end-to-end image-segmentation based methods, and some optimization strategies; (2) related loss functions. For each method, its contributions and weaknesses are introduced. Then, a brief comparison of representative methods is presented. Finally, we conclude this survey with some current challenges, such as expensive computation and the lack of generalization. And we point out some directions to be further explored in the future, that is, semi-supervised learning, meta-learning and neural architecture search, etc.}
}
+@article{survey:deepLeraningInLanemarkerdetection,
+ author = {Zhang, Youcheng and Zongqing, lu and Zhang, Xuechen and Xue, Jing-Hao and Liao, Qingmin},
+ year = {2021},
+ month = {04},
+ pages = {1-17},
+ title = {Deep Learning in Lane Marking Detection: A Survey},
+ volume = {PP},
+ language = {eng},
+ journal = {IEEE Transactions on Intelligent Transportation Systems},
+ doi = {10.1109/TITS.2021.3070111}
+}
+
@article{LaneDetector:driverAssistanceSystems,
author = {S.A. Sivasankari and R. {Agilesh Saravanan} and J. {Bennilo Fernandes} and K.T.P.S. Kumar},
title = {Lane detector for driver assistance systems},
@@ -193,7 +216,7 @@
doi = {10.1016/j.matpr.2021.03.649},
language = {eng},
keywords = {Lane detection, Computer vision, ITS, Driver support system, Machine learning techniques, Python programming, ADAS},
- abstract = {The challenging problem in the traffic system is lane detection. This Lane detection which attracts the computer vision community’s attention. For computer vision and machine learning techniques, the Lane detection which acts as the multi-feature detection problem. Many machine learning techniques are used for lane detection. Driver support system is one of the most important features in the modern vehicles to ensure the safety of the driver and decrease the vehicle accidents on road. Road Lane detection is the most challenging task and complex tasks now-a-days. Road localization and relative position between vehicle and roads which also includes with this. But in this journal, we propose a new method. Here, an on- board camera to be used which is looking outwards are presented here in this work. This proposed technique which can be used for all types of roads like painted, unpainted, curved, straight roads etc in different weather conditions. No need for camera calibration and coordination of the transform, may be any changing illumination situation, shadow effects, various road types. No representation for speed limits. This includes that the system acquires the front view using a camera mounted on the vehicles and detect the Lane by applying the code from the Python Programming process. This proposed system does not require any more information about roads. This system which demonstrates a robust performance for Lane detection.}
+ abstract = {The challenging problem in the traffic system is lane detection. This Lane detection which attracts the computer vision community's attention. For computer vision and machine learning techniques, the Lane detection which acts as the multi-feature detection problem. Many machine learning techniques are used for lane detection. Driver support system is one of the most important features in the modern vehicles to ensure the safety of the driver and decrease the vehicle accidents on road. Road Lane detection is the most challenging task and complex tasks now-a-days. Road localization and relative position between vehicle and roads which also includes with this. But in this journal, we propose a new method. Here, an on- board camera to be used which is looking outwards are presented here in this work. This proposed technique which can be used for all types of roads like painted, unpainted, curved, straight roads etc in different weather conditions. No need for camera calibration and coordination of the transform, may be any changing illumination situation, shadow effects, various road types. No representation for speed limits. This includes that the system acquires the front view using a camera mounted on the vehicles and detect the Lane by applying the code from the Python Programming process. This proposed system does not require any more information about roads. This system which demonstrates a robust performance for Lane detection.}
}
@article{laneDetection:aReview,
diff --git a/chap/standdertechnik.tex b/chap/standdertechnik.tex
index 61597477a6a6796a2853667b89a523a07263dda2..e80bb65fdb3f99ea9220e1c9e653a095a835fde8 100644
--- a/chap/standdertechnik.tex
+++ b/chap/standdertechnik.tex
@@ -14,6 +14,7 @@
Grundlage bilden hierbei verschiedene Operationen, mit welchen sich Bilder verändern lassen. Solche Operationen verknüpfen eine bestimmte
Menge an Pixeln eines Ursprungsbildes mittels einer mathematischen Operation, um ein neues \gls{Pixel} für das Zielbild zu ermitteln. Ein
relativ simples Beispiel hierfür ist das Bilden eines Mittelwertes von jeweils drei Farbpixeln, um ein Schwarzweißbild zu erzeugen.
+ \cite{szelisk:computerVision-algos+application}
% Häufig kommen bei diesen Operationen sogenannten \gls{Kernel} zum Einsatz. Dabei handelt es sich um Matrizen, welche je nach Anwendung
% Werte enthalten. Um nun ein \gls{Pixel} des Zielbildes zu bestimmen, wird ein entsprechender Bildausschnitt im Ursprungsbild ausgewählt und