|
|
Deep Neural Networks for Defect Detection
Juřica, Tomáš ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The goal of this work is to bring automatic defect detection to the manufacturing process of plastic cards. A card is considered defective when it is contaminated with a dust particle or a hair. The main challenges I am facing to accomplish this task are a very few training data samples (214 images), small area of target defects in context of an entire card (average defect area is 0.0068 \% of the card) and also very complex background the detection task is performed on. In order to accomplish the task, I decided to use Mask R-CNN detection algorithm combined with augmentation techniques such as synthetic dataset generation. I trained the model on the synthetic dataset consisting of 20 000 images. This way I was able to create a model performing 0.83 AP at 0.1 IoU on the original data test set.
|
|
|
Vehicle Speed Measurement by a Stationary Camera
Juřica, Tomáš ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
This Bachelor's thesis deals with the problematic of car speed measurement from video footage captured by a stationary camera. Development of a tool focused on reaching maximum accuracy of measurements with minimal user effort has been covered in this work. Perception of scene dimensions is acquired by using known points in the scene, which are manually marked. The influence of the way of annotating car position and input video quality on maximal reachable accuracy has also been discussed in this work.
|
|
|
Functional data analysis
Jurica, Tomáš ; Hlávka, Zdeněk (advisor) ; Hlubinka, Daniel (referee)
The aim of the master thesis is to review of reconstruction techniques of func- tional data and existing one-way functional ANOVA (FANOVA) tests. Specif- ically, the work deals with L2 -norm based and F-type mean functions equality tests, L2 -norm based covariance functions equality tests and tests for distri- bution equality. Furthermore, for each type of the test, it is introduced test based on reconstructed functional data, using orthornormal basis functions of L2 space. Finally, simulation study was conducted for comparing properties of tests using orthonormal basis representation of functional data and tests applied on non-reconstructed data. 1
|
|
|
Deep Neural Networks for Defect Detection
Juřica, Tomáš ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The goal of this work is to bring automatic defect detection to the manufacturing process of plastic cards. A card is considered defective when it is contaminated with a dust particle or a hair. The main challenges I am facing to accomplish this task are a very few training data samples (214 images), small area of target defects in context of an entire card (average defect area is 0.0068 \% of the card) and also very complex background the detection task is performed on. In order to accomplish the task, I decided to use Mask R-CNN detection algorithm combined with augmentation techniques such as synthetic dataset generation. I trained the model on the synthetic dataset consisting of 20 000 images. This way I was able to create a model performing 0.83 AP at 0.1 IoU on the original data test set.
|
|
|
Vehicle Speed Measurement by a Stationary Camera
Juřica, Tomáš ; Špaňhel, Jakub (referee) ; Herout, Adam (advisor)
This Bachelor's thesis deals with the problematic of car speed measurement from video footage captured by a stationary camera. Development of a tool focused on reaching maximum accuracy of measurements with minimal user effort has been covered in this work. Perception of scene dimensions is acquired by using known points in the scene, which are manually marked. The influence of the way of annotating car position and input video quality on maximal reachable accuracy has also been discussed in this work.
|
guest ::
RSS feed.