Vehicle Speed Estimation Based on 3D ConvNets and Non-Local Blocks
Open Access
- 30 May 2019
- journal article
- research article
- Published by MDPI AG in Future Internet
- Vol. 11 (6) , 123
Abstract
Vehicle speed estimation is an important problem in traffic surveillance. Many existing approaches to this problem are based on camera calibration. Two shortcomings exist for camera calibration-based methods. First, camera calibration methods are sensitive to the environment, which means the accuracy of the results are compromised in some situations where the environmental condition is not satisfied. Furthermore, camera calibration-based methods rely on vehicle trajectories acquired by a two-stage tracking and detection process. In an effort to overcome these shortcomings, we propose an alternate end-to-end method based on 3-dimensional convolutional networks (3D ConvNets). The proposed method bases average vehicle speed estimation on information from video footage. Our methods are characterized by the following three features. First, we use non-local blocks in our model to better capture spatial–temporal long-range dependency. Second, we use optical flow as an input in the model. Optical flow includes the information on the speed and direction of pixel motion in an image. Third, we construct a multi-scale convolutional network. This network extracts information on various characteristics of vehicles in motion. The proposed method showcases promising experimental results on commonly used dataset with mean absolute error (MAE) as km/h and mean square error (MSE) as .
Keywords
This publication has 23 references indexed in Scilit:
- A Video-Based System for Vehicle Speed Measurement in Urban RoadwaysIEEE Transactions on Intelligent Transportation Systems, 2016
- An accurate and practical calibration method for roadside camera using two vanishing pointsNeurocomputing, 2016
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- A novel work zone short-term vehicle-type specific traffic speed prediction model through the hybrid EMD–ARIMA frameworkTransportmetrica B: Transport Dynamics, 2015
- Vehicle speed measurement based on gray constraint optical flow algorithmOptik, 2014
- 3D Convolutional Neural Networks for Human Action RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Toward reducing failure risk in an integrated vehicle health maintenance system: A fuzzy multi-sensor data fusion Kalman filter approach for IVHMSExpert Systems with Applications, 2012
- Image Denoising by Sparse 3-D Transform-Domain Collaborative FilteringIEEE Transactions on Image Processing, 2007
- New method for overcoming ill-conditioning in vanishing-point-based camera calibrationOptical Engineering, 2007
- An algorithm to estimate mean traffic speed using uncalibrated camerasIEEE Transactions on Intelligent Transportation Systems, 2000