Highly accurate 3D reconstruction based on a precise and robust binocular camera calibration method

Hu, Guoliang; Zhou, Zhiguang; Cao, Jianzhong; Huang, Huimin

doi:10.1049/iet-ipr.2019.1525

Cited by 4 publications

(4 citation statements)

References 15 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Binocular or stereo vision, used in diverse areas like autonomous driving [1,2], robot navigation [3,4], 3D reconstruction [5][6][7], and industrial inspection [8,9], employs two identical cameras to capture two images of the same target from different vantage points. The disparity between these images enables 3D reconstruction and measurement, the accuracy of which is heavily dependent on the precision of the camera calibration and stereo matching methods, thus making these processes key research subjects in stereo vision.…”

Section: Introductionmentioning

confidence: 99%

“…Camera calibration techniques mainly fall into two categories: self-calibration and photogrammetric calibration [11]. Self-calibration methods, though not needing a calibration object, rely on sequences of images from an uncalibrated scene and often entail complex computations [12][13][14] and low in accuracy [5,15]. Conversely, photogrammetric methods, including the popular methods such as Zhang's [16], Tsai's [17], Bouguet's [18], and Heikkila and Silven's [19] methods utilize geometric information from a calibration object, such as a checkered board with known geometry, to determine camera parameters.…”

Section: Introductionmentioning

confidence: 99%

“…Although their results are slightly less accurate than those calibrated by Zhang's method alone, their work demonstrates its potential for real-time applications where extremely high calibration accuracy is not required. Hu et al, 2020, introduced a calibration approach for binocular cameras that begins with Zhang's technique to obtain an initial guess of the rotation and translation matrix [5]. This guess is then refined using singular value decomposition and solved via the Frobenius norm, and is further refined through maximum likelihood estimation, generating a new calculation for the relative position matrix of the binocular cameras.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Systematic Stereo Camera Calibration Strategy: Leveraging Latin Hypercube Sampling and 2k Full-Factorial Design of Experiment Methods

Hao,

Tai,

Tan

2023

Sensors

View full text Add to dashboard Cite

This research aimed to optimize the camera calibration process by identifying the optimal distance and angle for capturing checkered board images, with a specific focus on understanding the factors that influence the reprojection error (ϵRP). The objective was to improve calibration efficiency by exploring the impacts of distance and orientation factors and the feasibility of independently manipulating these factors. The study employed Zhang’s camera calibration method, along with the 2k full-factorial analysis method and the Latin Hypercube Sampling (LHS) method, to identify the optimal calibration parameters. Three calibration methods were devised: calibration with distance factors (D, H, V), orientation factors (R, P, Y), and the combined two influential factors from both sets of factors. The calibration study was carried out with three different stereo cameras. The results indicate that D is the most influential factor, while H and V are nearly equally influential for method A; P and R are the two most influential orientation factors for method B. Compared to Zhang’s method alone, on average, methods A, B, and C reduce ϵRP by 25%, 24%, and 34%, respectively. However, method C requires about 10% more calibration images than methods A and B combined. For applications where lower value of ϵRP is required, method C is recommended. This study provides valuable insights into the factors affecting ϵRP in calibration processes. The proposed methods can be used to improve the calibration accuracy for stereo cameras for the applications in object detection and ranging. The findings expand our understanding of camera calibration, particularly the influence of distance and orientation factors, making significant contributions to camera calibration procedures.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Systematic Stereo Camera Calibration Strategy: Leveraging Latin Hypercube Sampling and 2k Full-Factorial Design of Experiment Methods

Hao,

Tai,

Tan

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The irregular, nonuniform, and disordered 3D point clouds data makes automatic and accurate point clouds segmentation challenging [6], [7]. In the field of computer vision and remote sensing, there are three main technologies to obtain point cloud, such as binocular camera [8]. Based on light detection distance and ranging systems such as LiDAR [9], there is also point cloud acquisition based on RGB-D camera [10].…”

Section: Introductionmentioning

confidence: 99%

A Deep Neural Network Using Double Self-Attention Mechanism for ALS Point Cloud Segmentation

Yang

2022

IEEE Access

View full text Add to dashboard Cite

Airborne laser scanning (ALS) point cloud segmentation is an essential procedure for 3D data understanding and applications. This task is challenging due to the unstructured, disordered, and sparse distribution of the point cloud. PointNet++ is a well known end-to-end learning network for point cloud segmentation without fully exploring the local and contextual features, which are less efficient and accurate in capturing the complexity of point clouds. On this basis, we design a novel encoder-decoder network architecture to obtain the semantic features of the ALS point cloud at different levels and achieve a better segmentation effect. The improved local feature aggregation module can merge the deep feature of the point cloud, combining local and global self-attention convolutional networks. It can adaptively explore the inherent semantics feature of points and capture more extensive context information of ALS point cloud, termed DSPNet++. Finally, the conditional random field optimization model can be used to refine the segmentation results. We evaluated the performance of our method on the Vaihingen dataset of the International Society for Photogrammetry and Remote Sensing (ISPRS) and the GML(B) 3D dataset. Experimental results show that our method fully exploits the semantic feature of the ALS point cloud and can achieve higher accuracy. A comparative study with established deep learning models also confirms that our proposed method has outstanding performance in the ALS point cloud segmentation task.

show abstract

Advanced pavement distress recognition and 3D reconstruction by using GA-DenseNet and binocular stereo vision

Liu

Wang

2022

Measurement

View full text Add to dashboard Cite

Highly accurate 3D reconstruction based on a precise and robust binocular camera calibration method

Cited by 4 publications

References 15 publications

A Systematic Stereo Camera Calibration Strategy: Leveraging Latin Hypercube Sampling and 2k Full-Factorial Design of Experiment Methods

A Systematic Stereo Camera Calibration Strategy: Leveraging Latin Hypercube Sampling and 2k Full-Factorial Design of Experiment Methods

A Deep Neural Network Using Double Self-Attention Mechanism for ALS Point Cloud Segmentation

Advanced pavement distress recognition and 3D reconstruction by using GA-DenseNet and binocular stereo vision

Contact Info

Product

Resources

About