Name
Abstract | ||
|---|---|---|
A moving robot or moving camera causes motion blur in the robot's vision and distorts recorded images. We show that motion blur, differing lighting, and other distortions heavily affect the object localization performance of deep learning architectures for RoboCup Humanoid Soccer scenes. The paper proposes deep conditional generative models to apply visual noise filtering. Instead of generating new samples for a specific domain our model is constrained by reconstructing RoboCup soccer images. The conditional DCGAN (deep convolutional generative adversarial network) works semi-supervised. Thus there is no need for labeled training data. We show that object localization architectures significantly drop in accuracy when supplied with noisy input data and that our proposed model can significantly increase the accuracy again. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1007/978-3-030-01424-7_72 | ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2018, PT III |
Keywords | Field | DocType |
TensorFlow, Neural networks, DCGAN, GAN, De-noising, RoboCup, Robotics | Pattern recognition,Computer science,Filter (signal processing),Motion blur,Image noise,Artificial intelligence,Deep learning,Generative grammar,Robot,Artificial neural network,Robotics | Conference |
Volume | ISSN | Citations |
11141 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 5 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel Speck | 1 | 0 | 1.01 |
| Pablo V. A. Barros | 2 | 119 | 22.02 |
| Stefan Wermter | 3 | 1100 | 151.62 |