Image Inpainting and Deep Learning to Forecast Short-Term Train Loads

Bapaume, Thomas; Côme, Étienne; Roos, Jérémy; Ameli, Mostafa; Oukhellou, Latifa

doi:10.1109/access.2021.3093987

Cited by 9 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, a highly complex model is required to obtain good results. Bapaume et al [57] proposed an inpainting image-oriented approach by encoding the transportation network information in images. The model is based on a convolutional neural network (CNN) called U-net and demonstrated high accuracy for predicting typical passenger occupancy.…”

Section: A Forecasting Models For Passenger Load Predictionmentioning

confidence: 99%

Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data

Hoppe

Schwinger

Haeger

et al. 2023

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

Passengers of public transportation nowadays expect reliable and accurate travel information. The need for occupancy information is becoming more prevalent in intelligent public transport systems as people started avoiding overcrowded vehicles during the COVID-19 pandemic. Furthermore, public transportation companies require accurate occupancy forecasts to improve service quality. We present a novel approach to improve the prediction of passenger numbers that enhances a day-ahead prediction with real-time data. We first train a baseline predictor on historical automatic passenger counting data. Next, we train a realtime model on the deviations between baseline prediction and observed values, thus capturing events not addressed by the baseline. For the forecast, we attempt to detect emerging patterns in real time and adjust the baseline prediction with deviations from the patterns. Our experiments with data from Germany show that the proposed model improves the forecast of the baseline model and is only outperformed by artificial neural networks in some instances. If the training sets only cover a limited period of up to four months, our approach outperforms competing methods. For larger training sets, there are mixed results in the sense that for some test cases, certain types of neural networks yield slightly better results, but our method still performs well with less training effort, is explainable along the whole prediction process and can be applied to existing prediction methods.

show abstract

Section: A Forecasting Models For Passenger Load Predictionmentioning

confidence: 99%

Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data

Hoppe

Schwinger

Haeger

et al. 2023

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

show abstract

“…Baupame et al [38] introduced a U-NET-based technique for portraying metro traffic by creating an image that displays the geographical data of trains traveling on a metro line while accounting for the sporadic temporal sampling of train loads for improved precision and reliability. Lee et al [39] presented the Copy-and-Paste Networks architecture for video inpainting, which takes advantage of extra data in other frames of the video.…”

Section: B General Inpainting Oriented Deep Learning Architecturesmentioning

confidence: 99%

Pareto Optimized Large Mask Approach for Efficient and Background Humanoid Shape Removal

et al. 2023

View full text Add to dashboard Cite

We introduce deep learning-based methodology for removing unwanted human-like shapes in videos. The method uses Pareto-optimized Generative Adversarial Networks (GANs) technology, which is a novel contribution. The system automatically selects the Region of Interest (ROI) for each humanoid shape and uses a skeleton detection module to determine which humanoid shape to retain. The semantic masks of human like shapes are created using a semantic-aware occlusion-robust model that has four primary components: feature extraction, and local, global, and semantic branches. The global branch encodes occlusion-aware information to make the extracted features resistant to occlusion, while the local branch retrieves fine-grained local characteristics. A modified big mask inpainting approach is employed to eliminate a person from the image, leveraging Fast Fourier convolutions and utilizing polygonal chains and rectangles with unpredictable aspect ratios. The inpainter network takes the input image and the mask to create an output image excluding the background humanoid shapes. The generator uses an encoder-decoder structure with included skip connections to recover spatial information and dilated convolution and squeeze and excitation blocks to make the regions behind the humanoid shapes consistent with their surroundings. The discriminator avoids dissimilar structure at the patch scale, and the refiner network catches features around the boundaries of each background humanoid shape. The method is evaluated on two video object segmentation datasets (DAVIS and YouTube-VOS) and a database of 66 distinct video sequences of people behind a desk in an office environment. The efficiency was assessed using the Structural Similarity Index Measure (SSIM), Frechet Inception Distance (FID), and Learned Perceptual Image Patch Similarity (LPIPS) metrics and showed promising results in fully automated background person removal task.

show abstract

“…Another stream of research uses image-processing methods for transport problems. Recently, Bapaume et al (2021) utilized a GCN approach to forecast metro train loads. The line loadings of the metro system are represented as an image based on the time-space diagram of the trains with colors representing loads at a station for specific run.…”

Section: Introductionmentioning

confidence: 99%

Explaining a century of Swiss regional development by deep learning and SHAP values

Lai

Sun

Schmöcker

et al. 2022

Environment and Planning B: Urban Analytics and City Science

View full text Add to dashboard Cite

We use a graph convolutional neural network (GCN) for regional development prediction with population, railway network density, and road network density of each municipality as development indicators. By structuring the long-term time series data from 2833 municipalities in Switzerland during the years 1910–2000 as graphs over time, the GCN model interprets the indicators as node features and produces an acceptable prediction accuracy on their future values. Moreover, SHapley Additive exPlanations (SHAPs) are used to make the results of this approach explainable. We develop an algorithm to obtain SHAP values for the GCN and a sensitivity indicator to quantify the marginal contributions of the node features. This explainable GCN with SHAP decomposes the indicator into the contribution by the previous status of the municipality itself and the influence from other municipalities. We show that this provides valuable insights into understanding the history of regional development. Specifically, the results demonstrate that the impacts of geographical and economic constraints and urban sprawl on regional development vary significantly between municipalities and that the constraints are more important in the early 20th century. The model is able to include more information and can be applied to other regions and countries.

show abstract

Image Inpainting and Deep Learning to Forecast Short-Term Train Loads

Cited by 9 publications

References 29 publications

Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data

Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-Term Forecasts With Real-Time Occupancy Data

Pareto Optimized Large Mask Approach for Efficient and Background Humanoid Shape Removal

Explaining a century of Swiss regional development by deep learning and SHAP values

Contact Info

Product

Resources

About