Estimating Vehicle Speed on Roadways Using RNNs and Transformers: A Video-based Approach

TL;DR

This paper investigates the use of advanced neural network architectures, including LSTM, GRU, and Transformers, for vehicle speed estimation from video data, aiming to improve accuracy, scalability, and real-time applicability over traditional methods.

Contribution

It introduces a novel application of LSTM, GRU, and Transformer models for video-based vehicle speed estimation, demonstrating superior performance and robustness compared to basic RNNs.

Findings

Transformers outperform RNNs and GRUs in speed estimation accuracy.

Increasing sequence length improves model performance.

Transformers show robustness across diverse traffic conditions.

Abstract

This project explores the application of advanced machine learning models, specifically Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and Transformers, to the task of vehicle speed estimation using video data. Traditional methods of speed estimation, such as radar and manual systems, are often constrained by high costs, limited coverage, and potential disruptions. In contrast, leveraging existing surveillance infrastructure and cutting-edge neural network architectures presents a non-intrusive, scalable solution. Our approach utilizes LSTM and GRU to effectively manage long-term dependencies within the temporal sequence of video frames, while Transformers are employed to harness their self-attention mechanisms, enabling the processing of entire sequences in parallel and focusing on the most informative segments of the data. This study demonstrates that both LSTM and GRU outperform basic Recurrent Neural Networks (RNNs) due to their advanced gating mechanisms. Furthermore, increasing the sequence length of input data consistently improves model accuracy, highlighting the importance of contextual information in dynamic environments. Transformers, in particular, show exceptional adaptability and robustness across varied sequence lengths and complexities, making them highly suitable for real-time applications in diverse traffic conditions. The findings suggest that integrating these sophisticated neural network models can significantly enhance the accuracy and reliability of automated speed detection systems, thus promising to revolutionize traffic management and road safety.