Comprehensive Data Set for Automatic Single Camera Visual Speed Measurement

Sochor, Jakub; Juránek, Roman; Špaňhel, Jakub; Marsík, Lukás; Široký, Adam; Herout, Adam; Zemčík, Pavel

doi:10.1109/tits.2018.2825609

Cited by 60 publications

(92 citation statements)

References 24 publications

(91 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then we derive two vanishing points in the image space using a least square error method as in [12]. With Algorithm 1 extracted from the supplementary material of the dataset [19], we can derive the road plane in the world space and project image points to world points on the plane.…”

Section: Camera Model and Calibrationmentioning

confidence: 99%

“…For points, lower case represents image coordinates and upper case stands for world coordinates. d is an arbitrary offset of the plane, usually set to 10 as in [19].…”

Section: Object Detection and Trackingmentioning

confidence: 99%

“…The dataset provides the ground truth of distance measurement lines and speed of vehicles from Lidar sensor. It also has calibration results from various systems [19,18].…”

Section: Dataset and Setupmentioning

confidence: 99%

“…Finally, the model can recognize danger based on distances between vehicles and overlaps in the trajectories. We run this model on BrnoCompDataset [19], which contains highway surveillance videos with ground truth speed and distance measurements. We evaluate its performance for different steps and show convincing results.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Traffic Danger Recognition With Surveillance Cameras Without Training Data

Zhang²,

Chen

et al. 2018

2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

We propose a traffic danger recognition model that works with arbitrary traffic surveillance cameras to identify and predict car crashes. There are too many cameras to monitor manually. Therefore, we developed a model to predict and identify car crashes from surveillance cameras based on a 3D reconstruction of the road plane and prediction of trajectories. For normal traffic, it supports realtime proactive safety checks of speeds and distances between vehicles to provide insights about possible high-risk areas. We achieve good prediction and recognition of car crashes without using any labeled training data of crashes. Experiments on the BrnoCompSpeed dataset show that our model can accurately monitor the road, with mean errors of 1.80% for distance measurement, 2.77 km/h for speed measurement, 0.24 m for car position prediction, and 2.53 km/h for speed prediction.

show abstract

Section: Camera Model and Calibrationmentioning

confidence: 99%

“…For points, lower case represents image coordinates and upper case stands for world coordinates. d is an arbitrary offset of the plane, usually set to 10 as in [19].…”

Section: Object Detection and Trackingmentioning

confidence: 99%

“…The dataset provides the ground truth of distance measurement lines and speed of vehicles from Lidar sensor. It also has calibration results from various systems [19,18].…”

Section: Dataset and Setupmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Traffic Danger Recognition With Surveillance Cameras Without Training Data

Zhang²,

Chen

et al. 2018

2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)

View full text Add to dashboard Cite

show abstract

“…In summary, methods based on camera calibration are highly dependent on external conditions and the effectiveness of detection and tracking algorithms [23]. Most of them require manual intervention and the camera can not be placed at any position above the road.…”

mentioning

confidence: 99%

Vehicle Speed Estimation Based on 3D ConvNets and Non-Local Blocks

2019

View full text Add to dashboard Cite

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 2.71 km/h and mean square error (MSE) as 14.62 .

show abstract