scholarly journals Development and Assessment of a Sensor-Based Orientation and Positioning Approach for Decreasing Variation in Camera Viewpoints and Image Transformations at Construction Sites

2020 ◽  
Vol 10 (7) ◽  
pp. 2305
Author(s):  
Mohsen Foroughi Sabzevar ◽  
Masoud Gheisari ◽  
James Lo
Keyword(s):  
Image Matching ◽  
Three Dimensional ◽  
Scene Recognition ◽  
Video Data ◽  
Image Transformation ◽  
Construction Sites ◽  
3D Objects ◽  
Matching Process ◽  
Matching Techniques ◽  
Image Transformations

Image matching techniques offer valuable opportunities for the construction industry. Image matching, a fundamental process in computer vision, is required for different purposes such as object and scene recognition, video data mining, reconstruction of three-dimensional (3D) objects, etc. During the image matching process, two images that are randomly (i.e., from different position and orientation) captured from a scene are compared using image matching algorithms in order to identify their similarity. However, this process is very complex and error prone, because pictures that are randomly captured from a scene vary in viewpoints. Therefore, some main features in images such as position, orientation, and scale of objects are transformed. Sometimes, these image matching algorithms cannot correctly identify the similarity between these images. Logically, if these features remain unchanged during the picture capturing process, then image transformations are reduced, similarity increases, and consequently, the chances of algorithms successfully conducting the image matching process increase. One way to improve these chances is to hold the camera at a fixed viewpoint. However, in messy, dusty, and temporary locations such as construction sites, holding the camera at a fixed viewpoint is not always feasible. Is there any way to repeat and retrieve the camera’s viewpoints during different captures at locations such as construction sites? This study developed and evaluated an orientation and positioning approach that decreased the variation in camera viewpoints and image transformation on construction sites. The results showed that images captured while using this approach had less image transformation in contrast to images not captured using this approach.

In Vivo Kinematics of Healthy and Osteoarthritic Knees During Stepping Using Density-Based Image-Matching Techniques

2016 ◽  
Vol 32 (6) ◽  
pp. 586-592 ◽  
Author(s):  
Satoshi Hamai ◽  
Ken Okazaki ◽  
Satoru Ikebe ◽  
Koji Murakami ◽  
Hidehiko Higaki ◽  
...  
Keyword(s):  
Image Matching ◽  
Three Dimensional ◽  
Axial Rotation ◽  
Knee Extension ◽  
Knee Joints ◽  
In Vivo Kinematics ◽  
Significant Difference ◽  
Posterior Translation ◽  
Matching Techniques

The purpose of this study was to investigate in vivo kinematics in healthy and osteoarthritic (OA) knees during stepping using image-matching techniques. Six healthy volunteers and 14 patients with a medial OA knee before undergoing total knee arthroplasty performed stepping under periodic anteroposterior radiograph images. We analyzed the three-dimensional kinematic parameters of knee joints using radiograph images and CT-derived digitally reconstructed radiographs. The average extension/flexion angle ranged 6°/53° and 16°/44° in healthy and OA knees, with significant difference in extension (P = .02). The average varus angle was –2° and 6° in healthy and OA knees, with a significant difference (P = .03). OA knees showed 1.7° of significantly larger varus thrust (P = .04) and 4.2 mm of significantly smaller posterior femoral rollback (P = .04) compared with healthy knees. Coronal limb alignment in OA knees significantly correlated with varus thrust (R2 = .36, P = .02) and medial shift of the femur (R2 = .34, P = .03). Both normal and OA knees showed no transverse plane instability, including anteroposterior, mediolateral directions, or axial rotation. In conclusion, OA knees demonstrated different kinematics during stepping from normal knees: less knee extension, larger varus thrust, less posterior translation, and larger medial shift.

scholarly journals Natural Language Description of Videos for Smart Surveillance

2021 ◽  
Vol 11 (9) ◽  
pp. 3730
Author(s):  
Aniqa Dilawari ◽  
Muhammad Usman Ghani Khan ◽  
Yasser D. Al-Otaibi ◽  
Zahoor-ur Rehman ◽  
Atta-ur Rahman ◽  
...  
Keyword(s):  
Natural Language ◽  
Feature Recognition ◽  
Scene Recognition ◽  
Video Data ◽  
Surveillance Video ◽  
Video Footage ◽  
Parallel Pipeline ◽  
September 11 Attacks ◽  
Description Framework ◽  
High Level

After the September 11 attacks, security and surveillance measures have changed across the globe. Now, surveillance cameras are installed almost everywhere to monitor video footage. Though quite handy, these cameras produce videos in a massive size and volume. The major challenge faced by security agencies is the effort of analyzing the surveillance video data collected and generated daily. Problems related to these videos are twofold: (1) understanding the contents of video streams, and (2) conversion of the video contents to condensed formats, such as textual interpretations and summaries, to save storage space. In this paper, we have proposed a video description framework on a surveillance dataset. This framework is based on the multitask learning of high-level features (HLFs) using a convolutional neural network (CNN) and natural language generation (NLG) through bidirectional recurrent networks. For each specific task, a parallel pipeline is derived from the base visual geometry group (VGG)-16 model. Tasks include scene recognition, action recognition, object recognition and human face specific feature recognition. Experimental results on the TRECViD, UET Video Surveillance (UETVS) and AGRIINTRUSION datasets depict that the model outperforms state-of-the-art methods by a METEOR (Metric for Evaluation of Translation with Explicit ORdering) score of 33.9%, 34.3%, and 31.2%, respectively. Our results show that our framework has distinct advantages over traditional rule-based models for the recognition and generation of natural language descriptions.

scholarly journals Effect of buried depth on thermal performance of a vertical U-tube underground heat exchanger

Open Physics ◽  
2021 ◽  
Vol 19 (1) ◽  
pp. 327-330
Author(s):  
Li Yang ◽  
Bo Zhang ◽  
Jiří Jaromír Klemeš ◽  
Jie Liu ◽  
Meiyu Song ◽  
...  
Keyword(s):  
Heat Transfer ◽  
Heat Exchanger ◽  
Fluid Velocity ◽  
Three Dimensional ◽  
Simplified Model ◽  
Two Dimensional ◽  
Construction Sites ◽  
Full Size ◽  
Unit Depth ◽  
Research Show

Abstract Many researchers numerically investigated U-tube underground heat exchanger using a two-dimensional simplified pipe. However, a simplified model results in large errors compared to the data from construction sites. This research is carried out using a three-dimensional full-size model. A model validation is conducted by comparing with experimental data in summer. This article investigates the effects of fluid velocity and buried depth on the heat exchange rate in a vertical U-tube underground heat exchanger based on fluid–structure coupled simulations. Compared with the results at a flow rate of 0.4 m/s, the results of this research show that the heat transfer per buried depth at 1.0 m/s increases by 123.34%. With the increase of the buried depth from 80 to 140 m, the heat transfer per unit depth decreases by 9.72%.

ELEMENT-FREE METHODS VS. MESH-LESS CAE

2006 ◽  
Vol 03 (04) ◽  
pp. 445-464 ◽  
Author(s):  
HIDEYUKI SAKURAI
Keyword(s):  
Mesh Generation ◽  
Flow Analysis ◽  
Three Dimensional ◽  
Generation Task ◽  
3D Objects ◽  
Computer Aided ◽  
Analysis System ◽  
Mesh Less ◽  
Element Free ◽  
Cae System

Element-free methods (EFreeMs) are expected to eliminate the mesh generation task. However, a computer aided engineering (CAE) system by EFreeM for complex three-dimensional (3D) objects has not yet been developed. This paper discusses the obstacles to the CAE and way to solve them. A 3D groundwater flow analysis system with an EFreeM is presented as a practical CAE. In the system, instead of pursuing mesh-less CAE, a unique mesh is employed to achieve the practical CAE. Some 3D examples show the performance and usefulness of the system. Two serious drawbacks of the EFreeM are also discussed from the viewpoint of the practical CAE.

Implementation of Verification and Matching E-KTP with Faster R-CNN and ORB

2021 ◽  
Vol 5 (4) ◽  
pp. 783-793
Author(s):  
Muhammad Muttabi Hudaya ◽  
Siti Saadah ◽  
Hendy Irawan
Keyword(s):  
Image Matching ◽  
Nearest Neighbor ◽  
Feature Matching ◽  
Image Feature ◽  
Brute Force ◽  
K Nearest Neighbor ◽  
Matching Method ◽  
Average Precision ◽  
Detection Model ◽  
Matching Process

needs a solid validation that has verification and matching uploaded images. To solve this problem, this paper implementing a detection model using Faster R-CNN and a matching method using ORB (Oriented FAST and Rotated BRIEF) and KNN-BFM (K-Nearest Neighbor Brute Force Matcher). The goal of the implementations is to reach both an 80% mark of accuracy and prove matching using ORB only can be a replaced OCR technique. The implementation accuracy results in the detection model reach mAP (Mean Average Precision) of 94%. But, the matching process only achieves an accuracy of 43,46%. The matching process using only image feature matching underperforms the previous OCR technique but improves processing time from 4510ms to 60m). Image matching accuracy has proven to increase by using a high-quality dan high quantity dataset, extracting features on the important area of EKTP card images.

scholarly journals Image Matching Process on Images Taken by a Cellular Phone

2003 ◽  
Vol 57 (9) ◽  
pp. 1177-1186 ◽  
Author(s):  
Yi Hu ◽  
Tomoharu Nagao ◽  
Masanori Okazaki ◽  
Taishi Chinone
Keyword(s):  
Image Matching ◽  
Cellular Phone ◽  
Matching Process

scholarly journals OPTIMIZATION ALGORITHM OF TILTED IMAGE MATCHING BASED ON ADAPTIVE INITIAL OBJECT ASPECT

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 547-554
Author(s):  
C. Zhang ◽  
Y. Ge ◽  
Q. Zhang ◽  
B. Guo
Keyword(s):  
Least Squares ◽  
Image Matching ◽  
Normal Vector ◽  
Matching Method ◽  
Initial Value ◽  
Initial State ◽  
Matching Process ◽  
Low Degree ◽  
Verification Process ◽  
Initial Object

Abstract. When adopting the matching method of the least squares image based on object-patch to match tilted images, problems like the low degree of connection points for images with the discontinuity of depth or the discrepancy in elevation or low availability of aerotriangulation points would frequently appear. To address such problems, a tilted-image-matching algorithm based on an adaptive initial object-patch is proposed by this paper. By means of the existing initial values of the interior and exterior orientation elements of the tilted image and the information of object points generated in the matching process, the algorithm takes advantage of the method of multi-patch forward intersection and object variance partition so as to adaptively calculate the elevation of the object-patch and the initial value of the normal vector direction angle. Furthermore, this algorithm aims to solve the problem of difficulties in matching the tilted image with its corresponding points brought about by the low accuracy of the initial value of the tilted image when adopting the matching method of the least squares image based on object-patch to match the tilted image with high discrepancy in elevation. We adopt the algorithm as proposed in this paper and the least squares image matching method in which the initial state of the object-patch is horizontal to the object-patch respectively to conduct the verification process of comparing and matching two groups of tilted images. Finally, the effectiveness of the algorithm as proposed in this paper is verified by the testing results.

A three-dimensional shoulder protector based on ergonomics for workers

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ran-i Eom ◽  
Yejin Lee
Keyword(s):  
Body Shape ◽  
Three Dimensional ◽  
Health And Safety ◽  
The Body ◽  
Construction Sites ◽  
Content Type ◽  
Three Dimensional Printing ◽  
Functional Studies ◽  
Work Posture ◽  
Dimensional Printing

PurposeThe use of shoulder protectors is strongly recommended when carrying objects on the shoulder to ensure the health and safety of workers. Thus, this study aimed to develop and verify an ergonomic shoulder protector that considers human body shape and carrying posture from an ergonomic perspective. Ultimately, this study will present a shoulder protector with enhanced fit and safety for carrying workers at construction sites.Design/methodology/approachThe shoulder protector was designed and printed using three-dimensional printing technology with variable side neck points and shoulder point heights to reflect the human body's shoulder line shape and to position the carried object stably on the shoulder. The developed shoulder protectors were evaluated in terms of their fit according to the work posture of the carrier, adherence upon motion and durability through structural analysis.FindingsThe design of the shoulder protector for carrying workers followed the shoulder line. It is best placed above the side neck point by 1.0 cm and above the shoulder point by 2.0 cm. Its length is slightly shorter than the human shoulder for superior fit and safety.Originality/valueThe final shoulder protector (FSP) for carrying workers reflects the body curvature while enhancing fit and safety by considering activity and protective factors. As functional studies and evaluations on the need for protectors are scarce, this study provides fundamental data in the evaluation of protective gears.

Three-Dimensional Information Retrieval (3DIR)

2018 ◽  
pp. 1016-1029
Author(s):  
Peter Demian ◽  
Kirti Ruikar ◽  
Tarun Sahu ◽  
Anne Morris
Keyword(s):  
Information Retrieval ◽  
3D Visualization ◽  
Three Dimensional ◽  
Relevant Information ◽  
Tight Coupling ◽  
Care Needs ◽  
3D Objects ◽  
Topological Relationships ◽  
3D Geometry ◽  
Other Information

An increasing amount of information is packed into BIMs, with the 3D geometry serving as a central index leading to other information. The 3DIR project investigates information retrieval from such environments. Here, the 3D visualization can be exploited when formulating queries, computing the relevance of information items, or visualizing search results. The need for such a system was specified using workshops with end users. A prototype was built on a commercial BIM platform. Following an evaluation, the system was enhanced to exploit model topology. Relationships between 3D objects are used to widen the search, whereby relevant information items linked to a related 3D object (rather than linked directly to objects selected by the user) are still retrieved but ranked lower. An evaluation of the enhanced prototype demonstrates its effectiveness but highlights its added complexity. Care needs to be taken when exploiting topological relationships, but that a tight coupling between text-based retrieval and the 3D model is generally effective in information retrieval from BIMs.

Sign in / Sign up

Export Citation Format

Share Document