Automatic extrinsic camera parameters calibration using convolutional neural networks

Itu, Razvan; Borza, Diana; Danescu, Radu

doi:10.1109/iccp.2017.8117016

Cited by 11 publications

(15 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Inspired by DeepVP [14] and the method [30], we explore a CNN-based method for automatically calibrating monocular cameras in expressway scenes and accurately locating vehicles on curved roads. The schematic of the proposed approach is illustrated in Figure 1.…”

Section: Methodsmentioning

confidence: 99%

“…We evaluate the performance of DeepCN on the proposed dataset and other two well-known vanishing point datasets [14,30] and compare it with the corresponding methods [14,30]. This is because they represent state-of-the-art achievements in vanishing point detection using CNNs.…”

Section: Vanishing Point Detectionmentioning

confidence: 99%

“…The image space is discretised into grids and predicts the probability of a vanishing point in a certain grid by a softmax classifier. Although another approach [30] considers vanishing point detection as a regression task, the authors design a multi-layer CNN to extract image features and leverage the fully connected layer to output the vanishing point's location directly. Moreover, the predicted vanishing point and the initial rotation angles of the camera are combined to estimate the pitch and yaw angles relative to the road.…”

Section: Automatic Camera Calibrationmentioning

confidence: 99%

See 2 more Smart Citations

Vehicle localisation and deep model for automatic calibration of monocular camera in expressway scenes

Zhang

Song

Liu

et al. 2021

IET Intelligent Trans Sys

View full text Add to dashboard Cite

The authors present a fully automatic method for camera calibration in expressway scenes and vehicle localisation on curved roads. Our approach does not depend on specific targets or a priori information and adapts to a wide range of variations in road appearances and camera views. We make three main contributions to automatic camera calibration. Firstly, we propose a Deep Calibration Network to estimate the vanishing point and camera extrinsic parameters from an RGB image in an end-to-end manner. The vanishing point and camera rotation angles are then used to calculate the camera focal length according to the perspective projection geometry, thus constructing the complete camera matrix. Secondly, we introduce a Multi-View Camera Calibration Dataset, which contains a total of 32,712 images for 17 expressway scenes. The dataset covers a wide range of camera views and expressway types, which is challenging. Thirdly, we present a novel Curved Reference Line System adapted to the expressway shape to locate vehicles on curved roads accurately. This coordinate system can effectively transform the vehicle coordinates from a Cartesian system to the vehicle's mileage and horizontal distance relative to the lane line. A comprehensive evaluation on Multi-View Camera Calibration Dataset shows that our technique can automatically calibrate a single camera at about 40fps on an NVIDIA GTX1060 processor and accurately locate vehicles on curved roads, making it suitable for deployment in expressway surveillance systems.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Vanishing Point Detectionmentioning

confidence: 99%

Section: Automatic Camera Calibrationmentioning

confidence: 99%

See 1 more Smart Citation

Vehicle localisation and deep model for automatic calibration of monocular camera in expressway scenes

Zhang

Song

Liu

et al. 2021

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…There is very little literature on using deep learning for the tasks discussed in this section, with some exceptions. An example is the work of Itu et al [21] which uses CNN to estimate vanishing point for obtaining extrinsic calibration, and Sakaridis et al [22] on foggy scene understanding. However, in principle, these tasks should be feasible within the unified NeurAll framework.…”

Section: Other Tasksmentioning

confidence: 99%

NeurAll: Towards a Unified Visual Perception Model for Automated Driving

Sistu

Leang

Chennupati

et al. 2019

2019 IEEE Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) are successfully used for the important automotive visual perception tasks including object recognition, motion and depth estimation, visual SLAM, etc. However, these tasks are typically independently explored and modeled. In this paper, we propose a joint multi-task network design for learning several tasks simultaneously. Our main motivation is the computational efficiency achieved by sharing the expensive initial convolutional layers between all tasks. Indeed, the main bottleneck in automated driving systems is the limited processing power available on deployment hardware. There is also some evidence for other benefits in improving accuracy for some tasks and easing development effort. It also offers scalability to add more tasks leveraging existing features and achieving better generalization. We survey various CNN based solutions for visual perception tasks in automated driving. Then we propose a unified CNN model for the important tasks and discuss several advanced optimization and architecture design techniques to improve the baseline model. The paper is partly review and partly positional with demonstration of several preliminary results promising for future research. We first demonstrate results of multi-stream learning and auxiliary learning which are important ingredients to scale to a large multi-task model. Finally, we implement a two-stream three-task network which performs better in many cases compared to their corresponding single-task models, while maintaining network size.

show abstract

“…Recently, deep learning methods have been utilized in automatic camera calibration for intelligent vehicles [ 22 , 23 , 24 ]. However, many original equipment manufacturers (OEMs) and Tier 1 component companies require conventional computer vision methods to guarantee the safety and reliability of the camera calibration function.…”

Section: Introductionmentioning

confidence: 99%

Constrained Multiple Planar Reconstruction for Automatic Camera Calibration of Intelligent Vehicles

Lee

et al. 2021

Sensors

View full text Add to dashboard Cite

In intelligent vehicles, extrinsic camera calibration is preferable to be conducted on a regular basis to deal with unpredictable mechanical changes or variations on weight load distribution. Specifically, high-precision extrinsic parameters between the camera coordinate and the world coordinate are essential to implement high-level functions in intelligent vehicles such as distance estimation and lane departure warning. However, conventional calibration methods, which solve a Perspective-n-Point problem, require laborious work to measure the positions of 3D points in the world coordinate. To reduce this inconvenience, this paper proposes an automatic camera calibration method based on 3D reconstruction. The main contribution of this paper is a novel reconstruction method to recover 3D points on planes perpendicular to the ground. The proposed method jointly optimizes reprojection errors of image features projected from multiple planar surfaces, and finally, it significantly reduces errors in camera extrinsic parameters. Experiments were conducted in synthetic simulation and real calibration environments to demonstrate the effectiveness of the proposed method.

show abstract

Automatic extrinsic camera parameters calibration using convolutional neural networks

Cited by 11 publications

References 4 publications

Vehicle localisation and deep model for automatic calibration of monocular camera in expressway scenes

Vehicle localisation and deep model for automatic calibration of monocular camera in expressway scenes

NeurAll: Towards a Unified Visual Perception Model for Automated Driving

Constrained Multiple Planar Reconstruction for Automatic Camera Calibration of Intelligent Vehicles

Contact Info

Product

Resources

About