Publikacje

Śmiałkowski, T., & Czyżewski, A. (2022). Detection of Anomalies in the Operation of a Road Lighting System Based on Data from Smart Electricity Meters. ENERGIES, 15, 9438.

https://doi.org/10.3390/en15249438

Smart meters in road lighting systems create new opportunities for automatic diagnostics of undesirable phenomena such as lamp failures, schedule deviations, or energy theft from the power grid. Such a solution fits into the smart cities concept, where an adaptive lighting system creates new challenges with respect to the monitoring function. This article presents research results indicating the practical feasibility of real‐time detection of anomalies in a road lighting system based on analysis of data from smart energy meters. Short‐term time series forecasting was used first. In addition, two machine learning methods were used: one based on an autoregressive integrating moving average periodic model (SARIMA) and the other based on a recurrent network (RNN) using long short‐term memory (LSTM). The algorithms were tested on real data from an extensive lighting system installation. Both approaches enable the creation of self‐learning, real‐time anomaly detection algorithms. Therefore, it is possible to implement them on edge computing layer devices. A comparison of the algorithms indicated the advantage of the method based on the SARIMA model.

KOTUS, J.; SZWOCH, G.; CZYŻEWSKI, A.; KOSTEK, B. Assessment of road surface state with acoustic vector sensor
1. abstrakt w czasopiśmie JASA
2. referat na kongresie 183rd Meeting of Acoustical Society of America, Nashville, Tennessee, USA 5–9 December 2022.

DOI: 10.1121/10.0015995

A method of determining the road surface state based on the sound intensity analysis is presented. The proposed method is designed for the passive, non-contact assessment of a road surface state, especially in dry/wet conditions. The proposed method is intended for monitoring stations utilizing low-cost hardware. The road surface state is determined from the analysis of sound intensity emitted by road vehicles passing by the sensor and recorded with an acoustic vector sensor (AVS). A frequency domain sound intensity analysis included spatial filtering to reduce the environmental interference using the designed amplitude and phase correction algorithms. A test installation in a real-world scenario, consisting of a small AVS constructed from MEMS microphones and a state-of-art optic-based sensor, was used to evaluate the proposed method. A dataset representing many road vehicles moving at different speeds through the observed road section in varying conditions (dry and wet surface) was collected. Compared with the reference data, an evaluation of the proposed method and its accuracy in determining the road surface state is presented and discussed.The project has been subsidized by the Polish National Centre for Research and Development (NCBR) from the European Regional Development Fund No. POIR.04.01.04/2019 entitled: INFOLIGHT—“Cloud-based lighting system for smart cities.”

CYGERT, S.; CZYŻEWSKI, A. Robust Object Detection with Multi-input Multi-output Faster R-CNN
Conference paper, Lecture Notes in Computer Science, 15 May 2022. DOI: 10.1007/978-3-031-06427-2_48

Recent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. However, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO).

In this work, a generalization of the MIMO approach is applied to the task of object detection using the general-purpose Faster R-CNN model. It was shown that using the MIMO framework allows building strong feature representation and obtains very competitive accuracy when using just two input/output pairs. Furthermore, it adds just 0.5% additional model parameters and increases the inference time by 15.9% when compared to the standard Faster R-CNN. It also works comparably to or outperforms the Deep Ensemble approach in terms of model accuracy, robustness to out-of-distribution setting, and uncertainty calibration when the same number of predictions is used. This work opens up avenues for applying the MIMO approach in other high-level tasks such as semantic segmentation and depth estimation.

KOTUS J, SZWOCH G, Estimation of Average Speed of Road Vehicles by Sound Intensity Analysis, Sensors 2021, 21(16), 5337,
doi:10.3390/s21165337

Constant monitoring of road traffic is important part of modern smart city systems. The proposed method estimates average speed of road vehicles in the observation period, using a passive acoustic vector sensor. Speed estimation based on sound intensity analysis is a novel approach to the described problem. Sound intensity in two orthogonal axes is measured with a sensor placed alongside the road. Position of the apparent sound source when a vehicle passes by the sensor is estimated by means of sound intensity analysis in three frequency bands: 1 kHz, 2 kHz and 4 kHz. The position signals calculated for each vehicle are averaged in the analysis time frames, and the average speed estimate is calculated using a linear regression. The proposed method was validated in two experiments, one with controlled vehicle speed and another with real, unrestricted traffic. The calculated speed estimates were compared with the reference lidar and radar sensors. Average estimation error from all experiment was 1.4% and the maximum error was 3.2%. The results confirm that the proposed method allow for estimation of time-averaged road traffic speed with accuracy sufficient for gathering traffic statistics, e.g., in a smart city monitoring station.

CYGERT S, CZYŻEWSKI A, Robustness in Compressed Neural Networks for Object Detection, IEEE Access, Proc. IJCNN 2021. https://doi.org/10.1109/IJCNN52387.2021.9533773

Model compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models’ safety, especially for object detection in the autonomous driving setting, which is considered in this work.
It was shown in the paper that the sensitivity of compressed models to different distortion types is nuanced, and some of the corruptions are heavily impacted by the compression methods (i.e., additive noise), while others (blur effect) are only slightly affected. A common way to improve the robustness of models is to
use data augmentation, which was confirmed to positively affect models’ robustness, also for highly compressed models. It was further shown that while data imbalance methods brought only a slight increase in accuracy for the baseline model (without compression), the impact was more striking at higher compression
rates for the structured pruning. Finally, methods for handling data imbalance brought a significant improvement of the pruned models’ worst-detected class accuracy.

CYGERT S, WRÓBLEWSKI B, SŁOWIŃSKI R, WOŹNIAK K, CZYŻEWSKI A, Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shift, IEEE Access, Proc. IJCNN 2021.
https://doi.org/10.1109/IJCNN52387.2021.9533330

While recent computer vision algorithms achieve impressive performance on many benchmarks, they lack robustness – presented with an image from a different distribution, (e.g. weather or lighting conditions not considered during training), they may produce an erroneous prediction. Therefore, it is desired that such a model will be able to reliably predict its confidence measure. In this work, uncertainty estimation for the task of semantic segmentation is evaluated under a varying level of domain shift: in a cross-dataset setting and when adapting a model trained on data from the simulation. It was shown that simple color  transformations already provide a strong baseline, comparable to using more sophisticated style-transfer data augmentation. Further, by constructing an ensemble consisting of models using different backbones and/or augmentation methods, it was possible to improve significantly model performance in terms of overall accuracy and uncertainty estimation under the domain shift setting. The Expected Calibration Error (ECE) on challenging GTA to Cityscapes adaptation was reduced from 4.05 to the competitive value of 1.1. Further, an ensemble of models was utilized in the self-training setting to improve the pseudolabels
generation, which resulted in a significant gain in the final model accuracy, compared to the standard fine-tuning (without ensemble).

CYGERT S, CZYŻEWSKI A, Toward Robust Pedestrian Detection With Data
Augmentation. IEEE Access, Vol. 8, pp. 136674-136683, 2020.
doi:10.1109/ACCESS.2020.3011356

In this article, the problem of creating a safe pedestrian detection model that can operate in the real world is tackled. While recent advances have led to significantly improved detection accuracy on various benchmarks, existing deep learning models are vulnerable to invisible to the human eye changes in the input image which raises concerns about its safety. A popular and simple technique for improving robustness is using data augmentation. In this work, the robustness of existing data augmentation techniques is evaluated to propose a new simple augmentation scheme where during training, an image is combined with a patch of a stylized version of that image. Evaluation of pedestrian detection models robustness and uncertainty calibration under naturally occurring corruption and in realistic cross-dataset evaluation setting is conducted to show that our proposed solution improves upon previous work. In this paper, the importance of testing the robustness of recognition models is emphasized and it shows a simple way to improve it, which is a step towards creating robust pedestrian and object detection models.