Název:	Fast Training Data Acquisition for Object Detection and Segmentation using Black Screen Luminance Keying
Autoři:	Pöllabauer, Thomas Knauthe, Volker Boller, André Kuijper, Arjan Fellner, Dieter W.
Citace zdrojového dokumentu:	Journal of WSCG. 2024, vol. 32, no. 1-2, p. 101-110.
Datum vydání:	2024
Nakladatel:	Václav Skala - UNION Agency
Typ dokumentu:	článek article
URI:	http://hdl.handle.net/11025/57349
ISSN:	1213 – 6972 1213 – 6980 (CD-ROM) 1213 – 6964 (on-line)
Klíčová slova:	strojové učení;detekce objektu;segmentace objektů;hluboké neuronové sítě
Klíčová slova v dalším jazyce:	machine learning;object detection;object segmentation;deep neural networks
Abstrakt v dalším jazyce:	Deep Neural Networks (DNNs) require large amounts of annotated training data for a good performance. Often this data is generated using manual labeling (error-prone and time-consuming) or rendering (requiring geometry and material information). Both approaches make it difficult or uneconomic to apply them to many small-scale applications. A fast and straightforward approach of acquiring the necessary training data would allow the adoption of deep learning to even the smallest of applications. Chroma keying is the process of replacing a color (usually blue or green) with another background. Instead of chroma keying, we propose luminance keying for fast and straightforward training image acquisition. We deploy a black screen with high light absorption (99.99%) to record roughly 1-minute long videos of our target objects, circumventing typical problems of chroma keying, such as color bleeding or color overlap between background color and object color. Next we automatically mask our objects using simple brightness thresholding, saving the need for manual annotation. Finally, we automatically place the objects on random backgrounds and train a 2D object detector. We do extensive evaluation of the performance on the widely-used YCB-V object set and compare favourably to other conventional techniques such as rendering, without needing 3D meshes, materials or any other information of our target objects and in a fraction of the time needed for other approaches. Our work demonstrates highly accurate training data acquisition allowing to start training state-of-the-art networks within minutes
Práva:	© Václav Skala - UNION Agency © Václav Skala - UNION Agency
Vyskytuje se v kolekcích:	Volume 32, number 1-2 (2024)

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.