Reconstruction of textureless regions using structure from motion and image-based interpolation

Saponaro, Philip; Sorensen, Scott; Rhein, Stephen; Mahoney, Andrew R.; Kambhamettu, Chandra

doi:10.1109/icip.2014.7025370

Cited by 13 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been demonstrated (for instance see [9]) that if the viewpoints are separated by a large baseline, establishing (traditional) feature correspondences is extremely problematic due to local appearance changes or self-occlusions. Moreover, lack of texture on objects and specular reflections also make the feature matching problem very difficult [10,11].…”

Section: Arxiv:160400449v1 [Cscv] 2 Apr 2016mentioning

confidence: 99%

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction

Choy

Gwak

et al. 2016

Lecture Notes in Computer Science

1,244

1,131

View full text Add to dashboard Cite

Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2). The network learns a mapping from images of objects to their underlying 3D shapes from a large collection of synthetic data [1]. Our network takes in one or more images of an object instance from arbitrary viewpoints and outputs a reconstruction of the object in the form of a 3D occupancy grid. Unlike most of the previous works, our network does not require any image annotations or object class labels for training or testing. Our extensive experimental analysis shows that our reconstruction framework i) outperforms the state-of-theart methods for single view reconstruction, and ii) enables the 3D reconstruction of objects in situations when traditional SFM/SLAM methods fail (because of lack of texture and/or wide baseline).

show abstract

Section: Arxiv:160400449v1 [Cscv] 2 Apr 2016mentioning

confidence: 99%

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction

Choy

Gwak

et al. 2016

Lecture Notes in Computer Science

1,244

1,131

View full text Add to dashboard Cite

show abstract

“…Often these methods only return relative depth information that is only accurate in the close range so that it might not be applicable for our purpose. Another approach is depth estimation by structure from motion (e. g., Furukawa et al, 2004, Saponaro et al, 2014, Gallardo et al, 2017, where the structure (depth) is estimated by analyzing the movement of objects. In principle, this is similar to the distance estimation by stereo vision systems (Hamzah & Ibrahim, 2016) because, in both approaches, correspondences between images have to be found and analyzed.…”

Section: Distance Estimationmentioning

confidence: 99%

Provident vehicle detection at night for advanced driver assistance systems

Ewecker¹,

Asan

Ohnemus

et al. 2022

Auton Robot

View full text Add to dashboard Cite

In recent years, computer vision algorithms have become more powerful, which enabled technologies such as autonomous driving to evolve rapidly. However, current algorithms mainly share one limitation: They rely on directly visible objects. This is a significant drawback compared to human behavior, where visual cues caused by objects (e. g., shadows) are already used intuitively to retrieve information or anticipate occurring objects. While driving at night, this performance deficit becomes even more obvious: Humans already process the light artifacts caused by the headlamps of oncoming vehicles to estimate where they appear, whereas current object detection systems require that the oncoming vehicle is directly visible before it can be detected. Based on previous work on this subject, in this paper, we present a complete system that can detect light artifacts caused by the headlights of oncoming vehicles so that it detects that a vehicle is approaching providently (denoted as provident vehicle detection). For that, an entire algorithm architecture is investigated, including the detection in the image space, the three-dimensional localization, and the tracking of light artifacts. To demonstrate the usefulness of such an algorithm, the proposed algorithm is deployed in a test vehicle to use the detected light artifacts to control the glare-free high beam system proactively (react before the oncoming vehicle is directly visible). Using this experimental setting, the provident vehicle detection system’s time benefit compared to an in-production computer vision system is quantified. Additionally, the glare-free high beam use case provides a real-time and real-world visualization interface of the detection results by considering the adaptive headlamps as projectors. With this investigation of provident vehicle detection, we want to put awareness on the unconventional sensing task of detecting objects providently (detection based on observable visual cues the objects cause before they are visible) and further close the performance gap between human behavior and computer vision algorithms to bring autonomous and automated driving a step forward.

show abstract

“…In order to use the light artifact detection results exemplary for the proactive control of the matrix beam headlights of the test car, the artifacts have to be located in the three-dimensional space. For this purpose, several approaches can be used-for example, single image depth estimation [20,21], depth estimation from video [22,23,24], structure from motion [25,26,27], object localization through ground plane [28]. As these methods require the validity of certain assumptions (which are not valid for light artifacts) to provide an accurate estimate, we study a new approach that uses predictive street data in order to locate the light artifacts.…”

Section: Related Workmentioning

confidence: 99%

Provident Vehicle Detection at Night for Advanced Driver Assistance Systems

Ewecker¹,

Asan²,

Ohnemus³

et al. 2021

Preprint

View full text Add to dashboard Cite

In recent years, computer vision algorithms have become more and more powerful, which enabled technologies such as autonomous driving to evolve with rapid pace. However, current algorithms mainly share one limitation: They rely on directly visible objects. This is a major drawback compared to human behavior, where indirect visual cues caused by the actual object (e. g., shadows) are already used intuitively to retrieve information or anticipate occurring objects. While driving at night, this performance deficit becomes even more obvious: Humans already process the light artifacts caused by oncoming vehicles to assume their future appearance, whereas current object detection systems rely on the oncoming vehicle's direct visibility. Based on previous work in this subject, we present with this paper a complete system capable of solving the task to providently detect oncoming vehicles at nighttime based on their caused light artifacts. For that, we outline the full algorithm architecture ranging from the detection of light artifacts in the image space, localizing the objects in the three-dimensional space, and verifying the objects over time. To demonstrate the applicability, we deploy the system in a test vehicle and use the information of providently detected vehicles to control the glare-free high beam system proactively. Using this experimental

show abstract

Reconstruction of textureless regions using structure from motion and image-based interpolation

Cited by 13 publications

References 8 publications

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction

Provident vehicle detection at night for advanced driver assistance systems

Provident Vehicle Detection at Night for Advanced Driver Assistance Systems

Contact Info

Product

Resources

About