| 1. |
- Arnelid, Henrik, et al.
(författare)
-
Recurrent Conditional Generative Adversarial Networks forAutonomous Driving Sensor Modelling
- 2019
-
Konferensbidrag (refereegranskat)abstract
- Simulation of the real world is a widely researchedtopic in various fields. The automotive industry in particular isvery dependent on real world simulations, since these simulations are needed in order to prove the safety of advance driverassistance systems (ADAS) and autonomous driving (AD). Inthis paper we propose a deep learning based model for simulating the outputs from production sensors used in autonomousvehicles. We introduce an improved Recurrent ConditionalGenerative Adversarial Network (RC-GAN) consisting of Recurrent Neural Networks (RNNs) that use Long Short-TermMemory (LSTM) in both the generator and the discriminatornetworks in order to generate production sensor errors thatexhibit long-term temporal correlations. The network is trainedin a sequence-to-sequence fashion where we condition theoutput from the model on sequences describing the surroundingenvironment. This enables the model to capture spatial andtemporal dependencies, and the model is used to generatesynthetic time series describing the errors in a productionsensor which can be used for more realistic simulations. Themodel is trained on a data set collected from real roads withvarious traffic settings, and yields significantly better results ascompared to previous works.
|
|
| 2. |
- Hongmei, Hu, et al.
(författare)
-
Sparsity level in a non-negative matrix factorization based speech strategy in cochlear implants
- 2012
-
Ingår i: 2012 Proceedings Of The 20th European Signal Processing Conference (EUSIPCO). - : IEEE Computer Society. - 9781467310680 ; , s. 2432-2436
-
Konferensbidrag (refereegranskat)abstract
- Non-negative matrix factorization (NMF) has increasinglybeen used as a tool in signal processing in the last years, butit has not been used in the cochlear implants (CIs). Toimprove the performance of CIs in noisy environments, anovel sparse strategy is proposed by applying NMF onenvelops of 22 channels. In the new algorithm, the noisyspeech is first transferred to the time-frequency domain viaa 22- channel filter bank and the envelope in each frequencychannel is extracted; secondly, NMF is applied to theenvelope matrix (envelopegram); finally, the sparsitycondition is applied to the coefficient matrix to get moresparse representation. Speech reception threshold (SRT)subjective experiment was performed in combination withfive objective measurements in order to choose the properparameters for the sparse NMF model.
|
|
| 3. |
- Hu, H., et al.
(författare)
-
Speech enhancement via combination of Wiener filter and blind source separation
- 2011
-
Ingår i: Proceedings of the Sixth International Conference on Intelligent Systems and Knowledge Engineering, Shanghai, China (ISKE2011). - Berlin, Heidelberg : Springer Berlin Heidelberg. - 9783642256578 ; , s. 485-494
-
Konferensbidrag (refereegranskat)abstract
- Automatic speech recognition (ASR) often fails in acoustically noisy environments. Aimed to improve speech recognition scores of an ASR in a real-life like acoustical environment, a speech pre-processing system is proposed in this paper, which consists of several stages: First, a convolutive blind source separation (BSS) is applied to the spectrogram of the signals that are pre-processed by binaural Wiener filtering (BWF). Secondly, the target speech is detected by an ASR system recognition rate based on a Hidden Markov Model (HMM). To evaluate the performance of the proposed algorithm, the signal-to-interference ratio (SIR), the improvement signal-to-noise ratio (ISNR) and the speech recognition rates of the output signals were calculated using the signal corpus of the CHiME database. The results show an improvement in SIR and ISNR, but no obvious improvement of speech recognition scores. Improvements for future research are suggested.
|
|
| 4. |
- Innocenti, Christopher, et al.
(författare)
-
Imitation Learning for Vision-based Lane Keeping Assistance
- 2017
-
Ingår i: IEEE International Conference on Intelligent Transportation Systems-ITSC. - 2153-0009. - 9781538615263 ; 2018-March
-
Konferensbidrag (refereegranskat)abstract
- This paper aims to investigate direct imitation learning from human drivers for the task of lane keeping assistance in highway and country roads using grayscale images from a single front view camera. The employed method utilizes convolutional neural networks (CNN) to act as a policy that is driving a vehicle. The policy is successfully learned via imitation learning using real-world data collected from human drivers and is evaluated in closed-loop simulated environments, demonstrating good driving behaviour and a robustness for domain changes. Evaluation is based on two proposed performance metrics measuring how well the vehicle is positioned in a lane and the smoothness of the driven trajectory.
|
|
| 5. |
- Listo Zec, Edvin, et al.
(författare)
-
Statistical Sensor Modelling for Autonomous Driving Using Autoregressive Input-Output HMMs
- 2018
-
Ingår i: 21st International Conference on Intelligent Transportation Systems, {ITSC} 2018. - : IEEE. - 2153-0017. - 9781728103211
-
Konferensbidrag (refereegranskat)abstract
- Advanced driver assistance systems (ADAS) are standard features in many vehicles today and they have been proven to significantly increase the traffic safety. This paved way for development of autonomous driving (AD). To enable this, the vehicles are equipped with many sensors such as cameras and radars in order to scan the surrounding environment. The sensor outputs are used to implement decision and control modules. Verification of AD is a challenging task and requires collecting data from at least hundreds of millions of autonomously driven miles. We are therefore interested in virtual verification methods that simulate interesting and relevant situations, so that many scenarios can be tested in parallel. Realistic simulations require accurate sensor models, and in this paper we propose a probabilistic model based on the hidden Markov model (HMM) for modelling the sequential data produced by the sensors used in ADAS and AD. Moreover, we propose an efficient way to estimate parameters that scales well to big data sets. The results show that extending the HMM to use autoregression and input dependent transition probabilities is important in order to model the sensor characteristics and substantially improves the performance.
|
|
| 6. |
- Mallozzi, Piergiuseppe, 1990, et al.
(författare)
-
Autonomous vehicles: state of art, future trends, and challenges
- 2019
-
Ingår i: Automotive Systems and Software Engineering: State of the Art and Future Trends. - Cham : Springer International Publishing. - 9783030121570 ; , s. 347-367
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract
- Autonomous vehicles are considered to be the next big thing. Several companies are racing to put self-driving vehicles on the road by 2020. Regulations and standards are not ready for such a change. New technologies, such as the intensive use of machine learning, are bringing new solutions but also opening new challenges. This paper reports the state of the art, future trends, and challenges of autonomous vehicles, with a special focus on software. One of the major challenges we further elaborate on is using machine learning techniques in order to deal with uncertainties that characterize the environments in which autonomous vehicles will need to operate while guaranteeing safety properties.auto
|
|
| 7. |
- Martinsson, John, et al.
(författare)
-
Clustering Vehicle Maneuver Trajectories Using Mixtures of Hidden Markov Models
- 2018
-
Ingår i: 2018 21st International Conference on Intelligent Transportation Systems (ITSC). - : IEEE. - 2153-0017. - 9781728103235 ; 2018-November, s. 3698-3705
-
Konferensbidrag (refereegranskat)abstract
- The safety of autonomous vehicles needs to be verified and validated by rigorous testing. It is expensive to test autonomous vehicles in the field, and therefore virtual testing methods are needed. Generative models of maneuvers such as cut-ins, overtakes, and lane-keeping are needed to thoroughly test the autonomous vehicle in a virtual environment. To train such models we need ground truth maneuver labels and obtaining such labels can be time-consuming and costly. In this work, we use a mixture of hidden Markov models to find clusters in maneuver trajectories, which can be used to speed up the labeling process. The maneuver trajectories are noisy, asynchronous and of uneven length, which make hidden Markov models a good fit for the data. The method is evaluated on labeled data from a test track consisting of cut-ins and overtakes with favorable results. Further, it is applied to natural data where many of the clusters found can be interpreted as driver maneuvers under reasonable assumptions. We show that mixtures of hidden Markov models can be used to find motion patterns in driver maneuver data from highways and country roads.
|
|
| 8. |
|
|
| 9. |
- Mohammadiha, Nasser, et al.
(författare)
-
A New Approach for Speech Enhancement Based on a Constrained Nonnegative Matrix Factorization
- 2011
-
Ingår i: IEEE International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2011. - : IEEE.
-
Konferensbidrag (refereegranskat)abstract
- In this paper, a new approach is presented for singlechannelspeech enhancement which is based on NonnegativeMatrix Factorization (NMF). The proposed scheme combinesthe noise Power Spectral Density (PSD) estimation based ona constrained NMF and Wiener filtering to enhance the noisyspeech. The imposed constraint is motivated by the time correlationof the underlying observations and enforces the NMF togive smoother estimates of the nonnegative factors. Comparedto the standard NMF approach and Wiener filtering based ona recently developed noise PSD estimator, Source to DistortionRatio (SDR) is
|
|
| 10. |
- Mohammadiha, Nasser, et al.
(författare)
-
A New Linear MMSE Filter for Single Channel Speech Enhancement Based on Nonnegative Matrix Factorization
- 2011
-
Ingår i: IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2011. - : IEEE.
-
Konferensbidrag (refereegranskat)abstract
- In this paper, a linear MMSE filter is derived for single-channelspeech enhancement which is based on Nonnegative Matrix Factorization(NMF). Assuming an additive model for the noisy observation,an estimator is obtained by minimizing the mean square errorbetween the clean speech and the estimated speech components inthe frequency domain. In addition, the noise power spectral density(PSD) is estimated using NMF and the obtained noise PSD is usedin a Wiener filtering framework to enhance the noisy speech. Theresults of the both algorithms are compared to the result of the sameWiener filtering framework in which the noise PSD is estimatedusing a recently developed MMSE-based method. NMF based approachesoutperform the Wiener filter with the MMSE-based noisePSD tracker for different measures. Compared to the NMF-basedWiener filtering approach, Source to Distortion Ratio (SDR) is improvedfor the evaluated noise types for different input SNRs usingthe proposed linear MMSE filter.
|
|
