Multiple view geometry in computer vision (2. ed.)

By Andrew Harltey, Andrew Zisserman. 2006

2,262 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/5888d7dad8a2f825be1f573a5a90ef058cf946de

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning visual feature descriptors for dynamic lighting conditions (2014, methodology): “Outliers are rejected by fitting an Essential matrix using random sample consensus [41].”
Sensor and Sensor Fusion Technology in Autonomous Vehicles: A Review (2021, methodology): “In addition, it involves employing the intrinsic parameters (also referred to as the 3x3 intrinsic matrix, K [134]), to transform the 3D camera coordinates into the 2D image coordinates (x, y).”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, methodology): “However, both appearance [215] and geometric [29] approaches have well-known difficulties resolving ambiguities.”
An in-Depth Survey of Visible Light Communication Based Positioning Systems (2016, background): “The geometric relation between the 3D world coordinates of a point in the real world and the 2D image coordinates of its projection on the image sensor is described as [94]:”
Proximal Remote Sensing Buggies and Potential Applications for Field-Based Phenotyping (2014, methodology): “Using a pin-hole model of the camera [118], each point of the disparity map was registered to a real-world coordinate system.”
Head Pose Estimation and Augmented Reality Tracking: An Integrated System and Evaluation for Monitoring Driver Awareness (2010, background): “We refer the reader to [41] for more information.”
Background-oriented schlieren (BOS) techniques (2015, methodology): “One possible solution for this is the application of the epipolar geometry method (Hartley and Zisserman 2003), which imposes geometric constraints on pairs of camera images, as shown in Fig.”
Kimera: From SLAM to spatial perception with 3D dynamic scene graphs (2021, methodology): “At each iSAM2 iteration, the structureless vision model estimates the 3D position of the observed features using DLT (Hartley and Zisserman 2004) and analytically eliminates the corresponding 3D points from the VIO state (Carlone et al. 2014).”
Grape detection, segmentation and tracking using deep neural networks and three-dimensional association (2019, methodology): “Two feature extraction architectures were evaluated: ResNet-101 and the shallower ResNet-50 (He et al., 2016). For the YOLO networks, we employed Darknet, the original implementation developed by Redmon et al. (2016), initialized using pre-trained weights from ImageNet (Deng et al.”
A review of computer vision–based structural health monitoring at local and global levels (2020, methodology): “The detailed parameter estimation procedure is presented in Hartley and Zisserman.21 Xu et al.16 applied the homography matrix method to convert the vibration of a cable-stayed bridge under human crowds from pixel to millimeter.”
A Thermal Infrared Video Benchmark for Visual Analysis (2014, methodology): “For planar motion (Atrium and Lab), a homographybased ground plane was estimated [11].”
Immersive light field video with a layered mesh representation (2020, methodology): “We calibrate the camera extrinsics and intrinsics using standard structure from motion techniques [Hartley and Zisserman 2003].”
Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection (2019, background): “ined within a prescribed estimation error. Consensus maximization is NP-hard [27], [29], and related work investigates both approximations and exact algorithms. RANSAC [30] is a widely used heuristic [31], applicable when a minimal solver exists. But RANSAC provides no optimality guarantees, and its”
Aerodynamic instability of a bridge deck section model: Linear and nonlinear approach to force modeling (2010, methodology): “The marker position reconstruction is defined by the triangulation of the images recorded by a couple of cameras after a calibration procedure allowing for the correction of prospective and geometric aberrations Hartley and Zisserman (2003).”