Search results for: vision

Authors: Mohamed Gazzeh, Bradley Null, Fethi Tlili, Hichem Besbes

Abstract:

The burgeoning global ownership of personal vehicles has posed a significant strain on urban infrastructure, notably parking facilities, leading to traffic congestion and environmental concerns. Effective parking management systems (PMS) are indispensable for optimizing urban traffic flow and reducing emissions. The most commonly deployed systems nowadays rely on computer vision technology. This paper explores the integration of radar sensors and simulation in the context of smart parking management. We concentrate on radar sensors due to their versatility and utility in automotive applications, which extends to PMS. Additionally, radar sensors play a crucial role in driver assistance systems and autonomous vehicle development. However, the resource-intensive nature of radar data collection for algorithm development and testing necessitates innovative solutions. Simulation, particularly the monoDrive simulator, an internal development tool used by NI the Test and Measurement division of Emerson, offers a practical means to overcome this challenge. The primary objectives of this study encompass simulating radar sensors to generate a substantial dataset for algorithm development, testing, and, critically, assessing the transferability of models between simulated and real radar data. We focus on occupancy detection in parking as a practical use case, categorizing each parking space as vacant or occupied. The simulation approach using monoDrive enables algorithm validation and reliability assessment for virtual radar sensors. It meticulously designed various parking scenarios, involving manual measurements of parking spot coordinates, orientations, and the utilization of TI AWR1843 radar. To create a diverse dataset, we generated 4950 scenarios, comprising a total of 455,400 parking spots. This extensive dataset encompasses radar configuration details, ground truth occupancy information, radar detections, and associated object attributes such as range, azimuth, elevation, radar cross-section, and velocity data. The paper also addresses the intricacies and challenges of real-world radar data collection, highlighting the advantages of simulation in producing radar data for parking lot applications. We developed classification models based on Support Vector Machines (SVM) and Density-Based Spatial Clustering of Applications with Noise (DBSCAN), exclusively trained and evaluated on simulated data. Subsequently, we applied these models to real-world data, comparing their performance against the monoDrive dataset. The study demonstrates the feasibility of transferring models from a simulated environment to real-world applications, achieving an impressive accuracy score of 92% using only one radar sensor. This finding underscores the potential of radar sensors and simulation in the development of smart parking management systems, offering significant benefits for improving urban mobility and reducing environmental impact. The integration of radar sensors and simulation represents a promising avenue for enhancing smart parking management systems, addressing the challenges posed by the exponential growth in personal vehicle ownership. This research contributes valuable insights into the practicality of using simulated radar data in real-world applications and underscores the role of radar technology in advancing urban sustainability.

Keywords: autonomous vehicle simulator, FMCW radar sensors, occupancy detection, smart parking management, transferability of models

Procedia PDF Downloads 81

Authors: L. Diogo, A. Legrand, J. Nguyen-Cao, J. Rogeau, S. Bornhofen

Abstract:

Lenia is a system of cellular automata with continuous states, space and time, which surprises not only with the emergence of interesting life-like structures but also with its beauty. This paper reports ongoing research on a GPU implementation of Lenia using CUDA C++ and OpenGL Interoperability. We demonstrate how CUDA as a low-level GPU programming paradigm allows optimizing performance and memory usage of the Lenia algorithm. A comparative analysis through experimental runs with existing implementations shows that the CUDA implementation outperforms the others by one order of magnitude or more. Cellular automata hold significant interest due to their ability to model complex phenomena in systems with simple rules and structures. They allow exploring emergent behavior such as self-organization and adaptation, and find applications in various fields, including computer science, physics, biology, and sociology. Unlike classic cellular automata which rely on discrete cells and values, Lenia generalizes the concept of cellular automata to continuous space, time and states, thus providing additional fluidity and richness in emerging phenomena. In the current literature, there are many implementations of Lenia utilizing various programming languages and visualization libraries. However, each implementation also presents certain drawbacks, which serve as motivation for further research and development. In particular, speed is a critical factor when studying Lenia, for several reasons. Rapid simulation allows researchers to observe the emergence of patterns and behaviors in more configurations, on bigger grids and over longer periods without annoying waiting times. Thereby, they enable the exploration and discovery of new species within the Lenia ecosystem more efficiently. Moreover, faster simulations are beneficial when we include additional time-consuming algorithms such as computer vision or machine learning to evolve and optimize specific Lenia configurations. We developed a Lenia implementation for GPU using the C++ and CUDA programming languages, and CUDA/OpenGL Interoperability for immediate rendering. The goal of our experiment is to benchmark this implementation compared to the existing ones in terms of speed, memory usage, configurability and scalability. In our comparison we focus on the most important Lenia implementations, selected for their prominence, accessibility and widespread use in the scientific community. The implementations include MATLAB, JavaScript, ShaderToy GLSL, Jupyter, Rust and R. The list is not exhaustive but provides a broad view of the principal current approaches and their respective strengths and weaknesses. Our comparison primarily considers computational performance and memory efficiency, as these factors are critical for large-scale simulations, but we also investigate the ease of use and configurability. The experimental runs conducted so far demonstrate that the CUDA C++ implementation outperforms the other implementations by one order of magnitude or more. The benefits of using the GPU become apparent especially with larger grids and convolution kernels. However, our research is still ongoing. We are currently exploring the impact of several software design choices and optimization techniques, such as convolution with Fast Fourier Transforms (FFT), various GPU memory management scenarios, and the trade-off between speed and accuracy using single versus double precision floating point arithmetic. The results will give valuable insights into the practice of parallel programming of the Lenia algorithm, and all conclusions will be thoroughly presented in the conference paper. The final version of our CUDA C++ implementation will be published on github and made freely accessible to the Alife community for further development.

Keywords: artificial life, cellular automaton, GPU optimization, Lenia, comparative analysis.

Procedia PDF Downloads 41

Authors: Reza Nematirad, Anil Pahwa, Balasubramaniam Natarajan

Abstract:

Time series data consist of successive data points collected over a period of time. Accurate prediction of future values is essential for informed decision-making in several real-world applications, including electricity load demand forecasting, lifetime estimation of industrial machinery, traffic planning, weather prediction, and the stock market. Due to their critical relevance and wide application, there has been considerable interest in time series forecasting in recent years. However, the proliferation of sensors and IoT devices, real-time monitoring systems, and high-frequency trading data introduce significant intricate temporal variations, rapid changes, noise, and non-linearities, making time series forecasting more challenging. Classical methods such as Autoregressive integrated moving average (ARIMA) and Exponential Smoothing aim to extract pre-defined temporal variations, such as trends and seasonality. While these methods are effective for capturing well-defined seasonal patterns and trends, they often struggle with more complex, non-linear patterns present in real-world time series data. In recent years, deep learning has made significant contributions to time series forecasting. Recurrent Neural Networks (RNNs) and their variants, such as Long short-term memory (LSTMs) and Gated Recurrent Units (GRUs), have been widely adopted for modeling sequential data. However, they often suffer from the locality, making it difficult to capture local trends and rapid fluctuations. Convolutional Neural Networks (CNNs), particularly Temporal Convolutional Networks (TCNs), leverage convolutional layers to capture temporal dependencies by applying convolutional filters along the temporal dimension. Despite their advantages, TCNs struggle with capturing relationships between distant time points due to the locality of one-dimensional convolution kernels. Transformers have revolutionized time series forecasting with their powerful attention mechanisms, effectively capturing long-term dependencies and relationships between distant time points. However, the attention mechanism may struggle to discern dependencies directly from scattered time points due to intricate temporal patterns. Lastly, Multi-Layer Perceptrons (MLPs) have also been employed, with models like N-BEATS and LightTS demonstrating success. Despite this, MLPs often face high volatility and computational complexity challenges in long-horizon forecasting. To address intricate temporal variations in time series data, this study introduces Times2D, a novel framework that parallelly integrates 2D spectrogram and derivative heatmap techniques. The spectrogram focuses on the frequency domain, capturing periodicity, while the derivative patterns emphasize the time domain, highlighting sharp fluctuations and turning points. This 2D transformation enables the utilization of powerful computer vision techniques to capture various intricate temporal variations. To evaluate the performance of Times2D, extensive experiments were conducted on standard time series datasets and compared with various state-of-the-art algorithms, including DLinear (2023), TimesNet (2023), Non-stationary Transformer (2022), PatchTST (2023), N-HiTS (2023), Crossformer (2023), MICN (2023), LightTS (2022), FEDformer (2022), FiLM (2022), SCINet (2022a), Autoformer (2021), and Informer (2021) under the same modeling conditions. The initial results demonstrated that Times2D achieves consistent state-of-the-art performance in both short-term and long-term forecasting tasks. Furthermore, the generality of the Times2D framework allows it to be applied to various tasks such as time series imputation, clustering, classification, and anomaly detection, offering potential benefits in any domain that involves sequential data analysis.

Keywords: derivative patterns, spectrogram, time series forecasting, times2D, 2D representation

Procedia PDF Downloads 42