|
|
Lane detection for autonomous vehicles
Holík, Štěpán ; Píštěk, Václav (referee) ; Kučera, Pavel (advisor)
This thesis focuses on the design and experimental verification of a system for lane detection, trajectory estimation and vehicle position. The goal was to develop a system composed of algorithms with its respective functions. Data collected with ZED 2 camera, the U-Net neural network model, and computer vision were used to reduce false positive predictions using a temporal window. Trigonometric calculations and camera parameters were used to estimate the vehicle’s position relative to the trajectory. One of the outcomes of this thesis is TuSimple dataset extension with the data captured with ZED 2 camera. Experimental verification demonstrated the system's functionality with high detection reliability in simple model situations, such as driving on a straight road segment. As the complexity of the model situations increased, the system's reliability decreases. Despite these shortcomings, the experiments showed that the system is able to detect lane boundaries and estimate an optimal vehicle trajectory. The algorithms for trajectory and vehicle position determination depend on the initial prediction of the lane boundaries, but they are functional and effective.
|
|
|
Recognition of Driving Lane Borders in Video from On-Board Camera
Fridrich, David ; Kohút, Jan (referee) ; Herout, Adam (advisor)
This paper talks about lane detection. Specifically custom generator of synthetic images, usage during training of neural networks, testing on convolutional neural network (CNN) UNet model and possibilities of extension of this model to SALMnet (Structure-Aware Lane Marking Detection Network) via addding SGCA module (semantic-guided channel attention) and PDC module (pyramid deformable convolution). Training results from synthetic datasets show very accurate results, reaching around 95\,\% in accuracy (even 99\,\% for easier images). Trainings with real datasets show lower accuracy, depending on the difficulty of the dataset itself. TuSimple has easier and clearer images and reaches about 62\,\%. CuLane is much more complex and results show accuracy around 37\,\%.
|
|
|
Warning system to keep the vehicle in the lane
Fendrich, Vítězslav ; Říha, Kamil (referee) ; Poměnková, Jitka (advisor)
This thesis adresses designing a device that detects lane departure of a vehicle via a video feed from a camera module. This device is intended to be attached onto the windshield of the vehicle. The initial part of the thesis will cover the current methods of lane departure detection through a video feed. In the following part the selection of suitable hardware, specifically the latest model of a Raspberry Pi, has been made. Afterwards a suitable container for the aforementioned hardware has been designed and created using a 3D printer. Subsequently an appropriate LDWS algorithm is chosen and designed. In the next part, the range and parameters of a testing database through which the proper functionality of the device will be tested on are chosen. The final part of the thesis contains evaluation of the success rate of detection via the acquired database.
|
|
|
Preprocessing of 1D gel electrophoresis image
Hlavatý, Matej ; Harabiš, Vratislav (referee) ; Vítek, Martin (advisor)
The aim of this project is an automatic analysis of 1D gel electrophoresis results. Basic principles of gel electrophoresis and types of errors and signal noise influencing the result are studied. The proposed algorithm serves for automatic detection of lanes in the image. Summation projection on the horizontal axis is created from black-and-white digital pictures of electrophoresis. Local minima of the profile are located after smoothing the profile. In the location of these minima borders between lanes are established.
|
|
|
Autonomous control of the vehicle through image processing
Fronc, Leoš ; Píštěk, Václav (referee) ; Kučera, Pavel (advisor)
This diploma thesis deals with the topic of autonomous vehicles and especially lane detection. The paper describes and compares two main approaches to the lane detection - using traditional methods of computer vision and convolutional neural networks. The aim of the work was to create a system that would be able to recognize road lanes in a real time. The proposed system consisted of a Jetson Nano computer, a ZED stereo camera and a programmed algorithm. In total, two algorithms have been developed that use completely different approaches. Finally, the whole system was tested in terms of functionality and lane recognition.
|
|
|
Computer Vision for Autonomous Vehicles
Lečbych, Michal ; Škrabánek, Pavel (referee) ; Shehadeh, Mhd Ali (advisor)
Percepční systémy v autonomních vozech jsou v dnešní době intenzivně zkoumaným tématem a nezbytnou součástí potřebnou k vytvoření plně autonomních vozidel. Nejprve, stručně shrneme vývoj takových systémů, vysvětlíme si různé přístupy potřebné k vytvoření percepčních systémů a zaměříme se na detekci objektů, protože to bude naše hlavní část pro námi vytvořená systém. Nový model pro detekci objektů je , spolu s několika dalšími částmi jako odhad vzdálenosti a detekce jízdních pruhů.
|
|
|
Recognition of Driving Lane Borders in Video from On-Board Camera
Fridrich, David ; Kohút, Jan (referee) ; Herout, Adam (advisor)
This paper talks about lane detection. Specifically custom generator of synthetic images, usage during training of neural networks, testing on convolutional neural network (CNN) UNet model and possibilities of extension of this model to SALMnet (Structure-Aware Lane Marking Detection Network) via addding SGCA module (semantic-guided channel attention) and PDC module (pyramid deformable convolution). Training results from synthetic datasets show very accurate results, reaching around 95\,\% in accuracy (even 99\,\% for easier images). Trainings with real datasets show lower accuracy, depending on the difficulty of the dataset itself. TuSimple has easier and clearer images and reaches about 62\,\%. CuLane is much more complex and results show accuracy around 37\,\%.
|
|
|
Autonomous control of the vehicle through image processing
Fronc, Leoš ; Píštěk, Václav (referee) ; Kučera, Pavel (advisor)
This diploma thesis deals with the topic of autonomous vehicles and especially lane detection. The paper describes and compares two main approaches to the lane detection - using traditional methods of computer vision and convolutional neural networks. The aim of the work was to create a system that would be able to recognize road lanes in a real time. The proposed system consisted of a Jetson Nano computer, a ZED stereo camera and a programmed algorithm. In total, two algorithms have been developed that use completely different approaches. Finally, the whole system was tested in terms of functionality and lane recognition.
|
|
|
Warning system to keep the vehicle in the lane
Fendrich, Vítězslav ; Říha, Kamil (referee) ; Poměnková, Jitka (advisor)
This thesis adresses designing a device that detects lane departure of a vehicle via a video feed from a camera module. This device is intended to be attached onto the windshield of the vehicle. The initial part of the thesis will cover the current methods of lane departure detection through a video feed. In the following part the selection of suitable hardware, specifically the latest model of a Raspberry Pi, has been made. Afterwards a suitable container for the aforementioned hardware has been designed and created using a 3D printer. Subsequently an appropriate LDWS algorithm is chosen and designed. In the next part, the range and parameters of a testing database through which the proper functionality of the device will be tested on are chosen. The final part of the thesis contains evaluation of the success rate of detection via the acquired database.
|
|
|
Preprocessing of 1D gel electrophoresis image
Hlavatý, Matej ; Harabiš, Vratislav (referee) ; Vítek, Martin (advisor)
The aim of this project is an automatic analysis of 1D gel electrophoresis results. Basic principles of gel electrophoresis and types of errors and signal noise influencing the result are studied. The proposed algorithm serves for automatic detection of lanes in the image. Summation projection on the horizontal axis is created from black-and-white digital pictures of electrophoresis. Local minima of the profile are located after smoothing the profile. In the location of these minima borders between lanes are established.
|
guest ::
