A multisensor LBS using SIFT-based 3D models

Ruiz-Ruiz, Antonio J.; López-de-Teruel, Pedro E.; Cánovas, Óscar

doi:10.1109/ipin.2012.6418901

Cited by 18 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ruiz [46] tried to find the location of some smartphones using the different sensors available in commodity smartphones. They used accelerometers, digital compasses, and Wi-Fi signals to determine the smartphone position based on motion estimators, probabilistic techniques, and fingerprinting methods.…”

Section: Image Positioning Supported By Wlan Fingerprintingmentioning

confidence: 99%

A Review of Hybrid Indoor Positioning Systems Employing WLAN Fingerprinting and Image Processing

Firdaus

Ahmad

Sahibuddin

2020

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Location-based services (LBS) are a significant permissive technology. One of the main components in indoor LBS is the indoor positioning system (IPS). IPS utilizes many existing technologies such as radio frequency, images, acoustic signals, as well as magnetic sensors, thermal sensors, optical sensors, and other sensors that are usually installed in a mobile device. The radio frequency technologies used in IPS are WLAN, Bluetooth, Zig Bee, RFID, frequency modulation, and ultra-wideband. This paper explores studies that have combined WLAN fingerprinting and image processing to build an IPS. The studies on combined WLAN fingerprinting and image processing techniques are divided based on the methods used. The first part explains the studies that have used WLAN fingerprinting to support image positioning. The second part examines works that have used image processing to support WLAN fingerprinting positioning. Then, image processing and WLAN fingerprinting are used in combination to build IPS in the third part. A new concept is proposed at the end for the future development of indoor positioning models based on WLAN fingerprinting and supported by image processing to solve the effect of people presence around users and the user orientation problem.

show abstract

Section: Image Positioning Supported By Wlan Fingerprintingmentioning

confidence: 99%

A Review of Hybrid Indoor Positioning Systems Employing WLAN Fingerprinting and Image Processing

Firdaus

Ahmad

Sahibuddin

2020

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

show abstract

“…≤ < ℎ ℎ 0.9, ≥ ℎ ℎ (7) Finally, multiply the parameter variation value with the factor weighting coefficient in the weighed form and superpose it to the before-change data to obtain the new parameter value [48], as shown below:…”

Section: Mvbppsmentioning

confidence: 99%

ARPPS: Augmented Reality Pipeline Prospect System

Zhang

Han

Hao

et al. 2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This is the preprint version of our paper on ICONIP. Outdoor augmented reality geographic information system (ARGIS) is the hot application of augmented reality over recent years. This paper concludes the key solutions of ARGIS, designs the mobile augmented reality pipeline prospect system (ARPPS), and respectively realizes the machine vision based pipeline prospect system (MVBPPS) and the sensor based pipeline prospect system (SBPPS). With the MVBPPS's realization, this paper studies the neural network based 3D features matching method. IntroductionSince the human activities are related with the geographic information all the time, it is very natural and extremely important to integrate the augmented reality technology with the GIS. Since its generation, the augmented reality has gone through several development phases: computer indoor augmented reality, helmet-type outdoor augmented reality and mobile based outdoor augmented reality. Its application is gradually converted from the traditional exhibition to the application combined with the industry. This paper studies the mobile based outdoor augmented reality geographic information system (ARGIS) [1-3] and analyzes it by combining the examples for underground pipeline prospect. In the process of the realization of the examples, this paper also studies the neural network based 3D features matching method to optimize the feature matching process.The traditional GIS application is displayed on the map in the form of 2D symbols after analyzing the result based on the 2D maps. However, due to the lack of strong intuition, it is difficult for the user with weak geographic knowledge to distinguish it; even the field experts also have some difficulties in distinguishing in a complicated environment. For recent years, with the 3DGIS and VRGIS development, the 3D virtual model of real environment was established to replace the 2D map [4], which improves the intuition of marker distinguishing and promotes the visualization development of GIS. However, the 3D virtual model has high requirements on hardware while it still has difference with the real world scene.As a matter of fact, the real world scene is a complicated and perfect "3D space map" for itself. If the real world scene is taken as the "map" for GIS application operation and the inquired and analyzed result is displayed on the real world scene via virtual information to achieve the interaction between the virtual space geographic information and the real world scene, so the GIS application experience can be enhanced.Carry out scene augmentation [5,6] for human's visual system by organically integrating the 2D or 3D pictures, text notes and other virtual information generated by the computer into the real world scene which can be seen by the user. The augmented reality has the effect of expressing the sense of reality but Operational resultsOperating environment of application is nexus 5 mobile, and operating system is android 4.4/5.0.1.Data server: i5-3470 CPU, 16G memory, window server 2013.MVBPPS is subjected...

show abstract

“…These solutions mainly rely on external markers [4], others require laborious setups (taking reference frames every 150cm) [2], rely on other modalities like WiFi [7], are computationally intensive (10s per frame) [3].…”

Section: Related Workmentioning

confidence: 99%

Robust vision-based indoor localization

Clark

Trigoni

Markham

2015

Proceedings of the 14th International Conference on Information Processing in Sensor Networks

View full text Add to dashboard Cite

Vision-based positioning has proven to be highly successful and popular in mobile robotics and computer vision applications. These methods have, however, not enjoyed the same popularity in the field of indoor localization.In this work we highlight some of the issues that arise when using vision-based methods for indoor localization. We then propose means of addressing these issues and implement a proof-of-concept visual inertial odometry system for a mobile device.Preliminary experiments have been carried out in a small library where sub-meter positioning accuracy was attained. Based on our proof-of-concept, we believe that visual inertial odometry techniques can provide the levels of positioning accuracy needed for widespread adoption.

show abstract

A multisensor LBS using SIFT-based 3D models

Cited by 18 publications

References 17 publications

A Review of Hybrid Indoor Positioning Systems Employing WLAN Fingerprinting and Image Processing

A Review of Hybrid Indoor Positioning Systems Employing WLAN Fingerprinting and Image Processing

ARPPS: Augmented Reality Pipeline Prospect System

Robust vision-based indoor localization

Contact Info

Product

Resources

About