Accurate and occlusion-robust multi-view stereo

Zhu, Zhaokun; Stamatopoulos, Christos; Fraser, Clive S.

doi:10.1016/j.isprsjprs.2015.08.008

Cited by 27 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many mature methods have been designed based on this concept, and there are many slight differences in the proven application and actual effect of various methods. Here, Zhu’s robust high-precision and occlusion multiview stereovision method [ 17 ] is selected to rebuild the dense point cloud of the soil collection area because of its high performance and ability to overcome occlusion effects. It can be seen from Figure 4 a that there are slight occlusions at the bottom of some small stones at some angles, but this is unavoidable.…”

Section: Multiview Reconstruction For the Soil Collection Areamentioning

confidence: 99%

A Volume Measurement Method for Lunar Soil Collection Based on a Single Monitoring Camera

Ding

Zhang

et al. 2018

Sensors

View full text Add to dashboard Cite

In the task of lunar soil collection, estimating the volume of the collected soil is an important part of the sampling control of the lander. Due to the design constraints of the lander, there is no additional installation position for volume measurement equipment. To fully use the sensors already installed, a collected soil volume measurement method is designed in this paper based only on a single monitoring camera. This method uses a sequence of images of the collection area captured by the camera mounted on the acquisition arm to accurately reconstruct the terrain of the collection area surface before and after soil acquisition. Additionally, bi-temporal dense point clouds are reconstructed. Based on the area of change associated with soil collection, the constructed dense point clouds are compared according to the topographic characteristics of the area to estimate the volume of soil collected. Experiments show that the method is stable and reliable and can meet the requirements of actual measurement tasks.

show abstract

Section: Multiview Reconstruction For the Soil Collection Areamentioning

confidence: 99%

A Volume Measurement Method for Lunar Soil Collection Based on a Single Monitoring Camera

Ding

Zhang

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…[16,31]. The second is geometric approaches, which explicitly detect occlusion and predict visibility in order to improve photo-consistency measure [17,32]. The first type is simple, but has relatively poor result.…”

Section: Improved Semi-global Aggregation With Guidance Of True-orthomentioning

confidence: 99%

Direct Digital Surface Model Generation by Semi-Global Vertical Line Locus Matching

Zhang

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Abstract:As the core issue for Digital Surface Model (DSM) generation, image matching is often implemented in photo space to get disparity or depth map. However, DSM is generated in object space with additional processes such as reference image selection, disparity maps fusion or depth maps merging, and interpolation. This difference between photo space and object space leads to process complexity and computation redundancy. We propose a direct DSM generation approach called the semi-global vertical line locus matching (SGVLL), to generate DSM with dense matching in the object space directly. First, we designed a cost function, robust to the pre-set elevation step and projection distortion, and detected occlusion during cost calculation to achieve a sound photo-consistency measurement. Then, we proposed an improved semi-global cost aggregation with guidance of true-orthophoto to obtain superior results at weak texture regions and slanted planes. The proposed method achieves performance very close to the state-of-the-art with less time consumption, which was experimentally evaluated and verified using nadir aerial images and reference data.

show abstract

“…In Reference [31] the authors presented the results of multi-camera scene reconstruction based on the stereo matching approach. In References [32,33] the authors proposed an accurate multi-view stereo method for image-based 3D reconstruction. However, depth map-based methods require the proper selection of reference images and merging of depth maps in order to obtain good results [34,35].…”

Section: Introductionmentioning

confidence: 99%

Accuracy Analysis of a 3D Model of Excavation, Created from Images Acquired with an Action Camera from Low Altitudes

Wierzbicki

Nienaltowski

2019

IJGI

View full text Add to dashboard Cite

In the last few years, Unmanned Aerial Vehicles (UAVs) equipped with compact digital cameras, have become a cheap and efficient alternative to classic aerial photogrammetry and close-range photogrammetry. Low-altitude photogrammetry has great potential not only in the development of orthophoto maps but is also increasingly used in surveying and rapid mapping. This paper presents a practical aspect of the application of the custom homemade low-cost UAV, equipped with an action camera, to obtain images from low altitudes and develop a digital elevation model of the excavation. The conducted analyses examine the possibilities of using low-cost UAVs to deliver useful photogrammetric products. The experiments were carried out on a closed excavation in the town of Mince (north-eastern Poland). The flight over the examined area was carried out autonomously. A photogrammetric network was designed, and the reference areas in the mine were measured using the Global Navigation Satellite System-Real Time Kinematic (GNSS-RTK) method to perform accuracy analyses of the excavation 3D model. Representation of the created numerical terrain model was a dense point cloud. The average height difference between the generated dense point cloud and the reference model was within the range of 0.01–0.13 m. The difference between the volume of the excavation measured by the GNSS kinematic method and the volume measured on the basis of a dense point cloud was less than 1%. The obtained results show that the application of the low-cost UAV equipped with an action camera with a wide-angle lens, allows for obtaining high-accuracy images comparable to classic, compact digital cameras.

show abstract

Accurate and occlusion-robust multi-view stereo

Cited by 27 publications

References 9 publications

A Volume Measurement Method for Lunar Soil Collection Based on a Single Monitoring Camera

A Volume Measurement Method for Lunar Soil Collection Based on a Single Monitoring Camera

Direct Digital Surface Model Generation by Semi-Global Vertical Line Locus Matching

Accuracy Analysis of a 3D Model of Excavation, Created from Images Acquired with an Action Camera from Low Altitudes

Contact Info

Product

Resources

About