Search

This paper investigates the use of two detectors and descriptors on image pyramids for automatic image orientation and generation of 3D models. The detectors and descriptors replace manual measurements and are used to detect, extract and match features across multiple imagery. The Scale-Invariant Feature Transform (SIFT) and the Speeded Up Robust Features (SURF) will be assessed based on speed, number of features, matched features, and precision in image and object space depending on the adopted hierarchical matching scheme. The influence of applying in addition Area Based Matching (ABM) with normalised cross-correlation (NCC) and least squares matching (LSM) is also investigated. The pipeline makes use of photogrammetric and computer vision algorithms aiming minimum interaction and maximum accuracy from a calibrated camera. Both the exterior orientation parameters and the 3D coordinates in object space are sequentially estimated combining relative orientation, single space resection and bundle adjustment. The fully automatic image-based pipeline presented herein to automate the image orientation step of a sequence of terrestrial markerless imagery is compared with manual bundle block adjustment and terrestrial laser scanning (TLS) which serves as ground truth. The benefits of applying ABM after FBM will be assessed both in image and object space for the 3D modelling of a complex rock art shelter. © 2012 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS).

This paper investigates the use of two detectors and descriptors on image pyramids for automatic image orientation and generation of 3D models. The detectors and descriptors replace manual measurements and are used to detect, extract and match features across multiple imagery. The Scale-Invariant Feature Transform (SIFT) and the Speeded Up Robust Features (SURF) will be assessed based on speed, number of features, matched features, and precision in image and object space depending on the adopted hierarchical matching scheme. The influence of applying in addition Area Based Matching (ABM) with normalised cross-correlation (NCC) and least squares matching (LSM) is also investigated. The pipeline makes use of photogrammetric and computer vision algorithms aiming minimum interaction and maximum accuracy from a calibrated camera. Both the exterior orientation parameters and the 3D coordinates in object space are sequentially estimated combining relative orientation, single space resection and bundle adjustment. The fully automatic image-based pipeline presented herein to automate the image orientation step of a sequence of terrestrial markerless imagery is compared with manual bundle block adjustment and terrestrial laser scanning (TLS) which serves as ground truth. The benefits of applying ABM after FBM will be assessed both in image and object space for the 3D modelling of a complex rock art shelter. © 2012 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS).

This paper presents a new robust approach to integrate intensity and visible images which have been acquired with a terrestrial laser scanner and a calibrated digital camera, respectively. In particular, an automatic and hierarchical method for the co-registration of both sensors is developed. The approach integrates several existing solutions to improve the performance of the co-registration between range-based and visible images: the Affine Scale-Invariant Feature Transform (A-SIFT), the epipolar geometry, the collinearity equations, the Groebner basis solution and the RANdom SAmple Consensus (RANSAC), integrating a voting scheme. The approach presented herein improves the existing co-registration approaches in automation, robustness, reliability and accuracy. © 2012 Elsevier Ltd. All rights reserved.

This paper presents a new robust approach to integrate intensity and visible images which have been acquired with a terrestrial laser scanner and a calibrated digital camera, respectively. In particular, an automatic and hierarchical method for the co-registration of both sensors is developed. The approach integrates several existing solutions to improve the performance of the co-registration between range-based and visible images: the Affine Scale-Invariant Feature Transform (A-SIFT), the epipolar geometry, the collinearity equations, the Groebner basis solution and the RANdom SAmple Consensus (RANSAC), integrating a voting scheme. The approach presented herein improves the existing co-registration approaches in automation, robustness, reliability and accuracy. © 2012 Elsevier Ltd. All rights reserved.

A large amount of cultural heritage monuments and sites exist distributed worldwide that require easy to use, cheap and fast sensor orientation tools for recording, georeferencing, surveying and mapping. Ground control points are usually required on site for close range photogrammetry to achieve accurate surveys, limiting both the involvement of non-experts and the chance to know the right place of the monuments unless a ground reference system is considered. This paper presents the system calibration of an image-based multi-sensor system that integrates two consumer-grade cameras, one global navigation satellite system (GNSS) and one low-cost inertial system, i.e., a micro-electro-mechanical system (MEMS) based inertial measurement unit (IMU). The multi-sensor system is calibrated indoor regarding both the camera orientation parameters and the boresight (rotations and offsets) parameters of the two digital cameras. The boresight parameters will be used to correct the direct approach estimates. The performance of the system calibration is tested outdoor on an upside down pyramidal sculpture to deliver both accurate 3D points and high resolution 3D models. Both scenarios are considered free of magnetic anomalies. The results achieved with the GNSS/MEMS-IMU direct approach are compared with the indirect approach based on bundle block adjustment. Further extrapolations to object space through digital surface models are also determined. The testing of the system shows that GNSS/MEMS-IMU data are good enough to provide approximate exterior orientation parameters of the cameras but not to yield accurate 3D models (<1 - 2 cm) for cultural heritage applications.

A large amount of cultural heritage monuments and sites exist distributed worldwide that require easy to use, cheap and fast sensor orientation tools for recording, georeferencing, surveying and mapping. Ground control points are usually required on site for close range photogrammetry to achieve accurate surveys, limiting both the involvement of non-experts and the chance to know the right place of the monuments unless a ground reference system is considered. This paper presents the system calibration of an image-based multi-sensor system that integrates two consumer-grade cameras, one global navigation satellite system (GNSS) and one low-cost inertial system, i.e., a micro-electro-mechanical system (MEMS) based inertial measurement unit (IMU). The multi-sensor system is calibrated indoor regarding both the camera orientation parameters and the boresight (rotations and offsets) parameters of the two digital cameras. The boresight parameters will be used to correct the direct approach estimates. The performance of the system calibration is tested outdoor on an upside down pyramidal sculpture to deliver both accurate 3D points and high resolution 3D models. Both scenarios are considered free of magnetic anomalies. The results achieved with the GNSS/MEMS-IMU direct approach are compared with the indirect approach based on bundle block adjustment. Further extrapolations to object space through digital surface models are also determined. The testing of the system shows that GNSS/MEMS-IMU data are good enough to provide approximate exterior orientation parameters of the cameras but not to yield accurate 3D models (<1 - 2 cm) for cultural heritage applications.