Figure 3 - uploaded by Niels Henze
Content may be subject to copyright.
Source publication
Connecting the physical and the digital world is an upcom-ing trend that enables numberless use-cases. The mobile phone as the most pervasive digital device is often used to establish such a connection. The phone enables users to re-trieve, use, and share digital information and services con-nected to physical objects. Recognizing physical objects...
Context in source publication
Citations
... The addressed problem here looks for a mobile visual computing solution directly on the mobile device itself. Examples of systems that provide such solutions, on a low to mid-end smart phone, are like [24], [30], [34], [13], that are mainly image recognition and retrieval works. ...
Abstract In this paper, we design and implement a humanmachine interaction application, which enables a visually challenged person to locate and manipulate personal objects in her/his neighbourhood. In this setting, we need to develop a tool (embedded in a mobile phone) which is capable of sensing, computing, and guiding the human arm towards
the object. This involves solving the following two sub-problems: (i) recognition of objects in the input images, and (ii) generating control signals, to guide the human for navigation, to reach the desired destination. For the former subproblem, we adapt the Bag ofWords framework for recognition and matching on mobile phones. For the latter subproblem,
we have developed a moment-based human servoing algorithm which is able to generate commands that help the visually impaired human to localize his hand with respect
to the object of interest. All necessary computations take place on the mobile phone. The proposed object recognition and vision based control design is deployed on a low/mid
end mobile phone. This can lead to a wide range of applications.
With our proposed design and implementation, we demonstrate that our application is effective and accurate, with a high reliability of convergence for different experimental settings.
... Dalam pembuatan Augmented Reality dengan Android, Tobias menggunakan Andar Tool sebagai alat bantu dan open GL untuk pemodelannya dan marker untuk mengenali dan menampilkan objek [4]. Menurut referensi di [6], ada berbagai macam metode yang dapat digunakan untuk mengenali dan mendeteksi objek, salah satunya dengan metode markerless pendeteksian titik atau pola pada marker. Menurut referensi di [7], metode yang tepat untuk mendeteksi objek nyata adalah metode markerless untuk mengenali objek. ...
Intisari - Provinsi Riau terletak di lokasi yang strategis dan memiliki kekayaan keindahan alam dan budaya yang unik, Riau menawarkan banyak tempat wisata baik alam dan budaya. Tujuan dari penelitian ini untuk membuat aplikasi yang membantu masyarakat untuk mendapatkan informasi objek wisata unggulan di Provinsi Riau. Salah satu faktor yang menyebabkan kurang berkembangnya sektor pariwisata di Provinsi Riau saat ini adalah karena pengelolaan informasi yang bersifat promosi dan belum mampu memaksimalkan ketersediaan teknologi informasi yang tersedia. Penggunaan teknologi augmented reality adalah teknologi yang menggabungkan benda maya tiga dimensi ke dalam sebuah lingkungan tiga-dimensi nyata dan kemudian memproyeksikan benda-benda maya secara real time. Markerless objek wisata unggulan adalah bono surfing, balap alur, tongkang bahan bakar, pantai Rupat, istana siak dan Candi Muara Takus. pembuatan obyek dan membaca penanda scan dari kamera menggunakan teknik markerbase dan Markerless dengan objek Pelacakan metode 3D dan algoritma SIFT (Skala Fitur invarian Transform). Proses yang terkandung dalam deteksi obyek membaca gambar, mempertajam gambar dengan memanfaatkan High Pass Filter; membaca gambar dari metode SIFT bahwa proses akan menghasilkan deteksi titik. Hasil pengujian untuk melihat efek dari jarak antara smartphone kamera dengan spidol, jarak yang diperoleh sangat ideal untuk menampilkan objek 3D, sampai 40 cm. pengujian aplikasi ARRiauTouris mampu mendeteksi penanda dengan jarak dekat 10 cm dan jarak maksimum 67 cm, dan memperoleh waktu rata-rata untuk objek (mean) antara 0,80 detik menjadi 0,93 detik. Kata kunci: obyek wisata, augmented reality, 3D pelacakan objek, provinsi riau
... The purpose of these methods is to estimate camera pose and track objects to set an anchor for Augmented Reality applications. In [6] a simplified SIFT (Scale Invariant Feature Transform) and a scalable vocabulary tree is utilized for recognition. Mobile phone implementation aimed to recognize poster segments. ...
The purpose of our demo is to show the application and performance of some low-complexity image descriptors in object recognition under realistic circumstances. We built a client-server system where several image retrieval methods and image segmentation approaches can be tested with the help of a network connected Android device (mobile phone, table or head mounted computer). A modified version of the CEDD (Color and Edge Directivity Descriptor) is proposed, as the most robust lightweight descriptor found in our tests, and manual or saliency based object selection are also included. The main purpose of the demo is to show the possibilities of lightweight object recognition with the modified descriptor and different object segmentation.
... The purpose of these methods is to estimate camera pose and track objects to set an anchor for Augmented Reality applications. In [6] a simplified SIFT (Scale Invariant Feature Transform) and a scalable vocabulary tree is utilized for recognition. Mobile phone implementation aimed to recognize poster segments. ...
The purpose of our demo is to show the application and performance of some low-complexity image descriptors in object recognition under realistic circumstances. We built a client-server system where several image retrieval methods and image segmentation approaches can be tested with the help of a network connected Android device (mobile phone, tablet or head mounted computer). A modified version of the CEDD (Color and Edge Directivity Descriptor) is proposed, as the most robust lightweight descriptor found in our tests, and manual or automatic object segmentations are also included.
... However, if the mobile network itself is weak for a stable internet data connection, the method fails. The other approach is where the client downloads the necessary data from the server beforehand, and all vision algorithms are run on the handheld device [11,20,21,13]. With the necessary data loaded for on-device processing, it can run a standalone app. ...
... This approach overcomes the network bandwidth issues that posed a major bottleneck in the former approach, but is bound to use the limited computing resources on the mobile device. Henze et al. [13] and Fockler et al. [11] demonstrate such mobile apps for efficient object recognition and work with dataset sizes of the order of hundreds of images. In this paper, we demonstrate a mobile visual search app that works with thousands of images. ...
In this paper, we demonstrate a computer vision application on mobile phones. One can take a picture at a heritage site/monument and obtain associated annotations on a mid-end mobile phone instantly. This does not require any communication of images or features with a remote server, and all the necessary computations take place on the phone itself. We demonstrate the app on two Indian heritage sites: Golkonda Fort and Hampi Temples. Underlying our application, we have a Bag of visual Words (BoW) image retrieval system, and an annotated database of images.
In the process of developing this mobile app, we extend the performance, scope and applicability of computer vision techniques: (i) we do a BoW-based image retrieval on mobile phones from a database of 10K images within 50 MB of storage and 10 MB of RAM. (ii) we introduce a vocabulary pruning method for reducing the vocabulary size. (iii) we design a simple method of database pruning, that helps in reducing the size of the inverted index by removing semantically similar images. In (ii) and (iii), we demonstrate how memory(RAM) and computational speed can be optimized without any loss in performance.
... Continuous Pointing can be implemented by transmitting the stream of camera images to a server or by analysing the images on the phone (as in e.g. [3]). ...
... Using this pose the system transforms the augmenting overlay into the reference system of the physical scene and renders the augmentation. To realize handheld AR for a number of CDs we used an approach proposed in [3]. In the pre-processing phase, images of CD covers are analysed to extract simplified SIFT features [7]. ...
A number of mobile applications enable users to take photos of physical objects to receive related information and services. Commercial implementations such as Google Goggles use a Point & Shoot interaction technique that requires to explicitly taking a photo to trigger the object recognition. In this paper we investigate alternative interaction techniques to receive information about physical objects. For the study we try to rule out all aspects but the basic interaction. We compare Point & Shoot with two other techniques to access information about music CDs and show that using handheld Augmented Reality is preferred by users and leads to a lower perceived task load. Our findings confirm that research and development effort towards handheld Augmented Reality is well invested.
... The modified feature is used for efficient nature tracking with interactive speed on current-generation phones. Henze et al. [6] combines the simplified SIFT with a scalable vocabulary tree to achieve interactive object recognition on mobile phones. The simplified features consume less computational cost which is necessary for mobile applications. ...
We present a recognition-based user tracking and augmented reality system that works in extreme large scale areas. The system will provide a user who captures an image of a building facade with precise location of the building and augmented information about the building. While GPS cannot provide information about camera poses, it is needed to aid reducing the searching ranges in image database. A patch-retrieval method is used for efficient computations and real-time camera pose recovery. With the patch matching as the prior information, the whole image matching can be done through propagations in an efficient way so that a more stable camera pose can be generated. Augmented information such as building names and locations are then delivered to the user. The proposed system mainly contains two parts, offline database building and online user tracking. The database is composed of images for different locations of interests. The locations are clustered into groups according to their UTM coordinates. An overlapped clustering method is used to cluster these locations in order to restrict the retrieval range and avoid ping pong effects. For each cluster, a vocabulary tree is built for searching the most similar view. On the tracking part, the rough location of the user is obtained from the GPS and the exact location and camera pose are calculated by querying patches of the captured image. The patch property makes the tracking robust to occlusions and dynamics in the scenes. Moreover, due to the overlapped clusters, the system simulates the "soft handoff" feature and avoid frequent swaps in memory resource. Experiments show that the proposed tracking and augmented reality system is efficient and robust in many cases.
... These interactions are now not just limited between the user and his phone, but also extended to the user, the phone and the real world. In other words, the user uses his phone as an intermediate device to interact with the real world [8], [18], [5], [9], [2], [13]. For example, in [8], [13], where users interact with a poster through a mobile phone. ...
... In other words, the user uses his phone as an intermediate device to interact with the real world [8], [18], [5], [9], [2], [13]. For example, in [8], [13], where users interact with a poster through a mobile phone. Another example is in [18]. ...
Applications with street navigation have been recently introduced on mobile phone devices. A major part of existing systems use integrated GPS as input for indicating the location. However, these systems often fail or make abrupt shifts in urban environment due to occlusion of satellites. Furthermore, they only give the position of a person and not the object of his attention, which is just as important for localization based services. In this paper we introduce a system using mobile phones built-in cameras for navigation and localization using visual information in accordance with the way we as humans navigate. The introduced method uses local features for extraction of natural feature points from images which are compared to a database for localization. The system is tested and evaluated in a real urban environment and the result shows very high success rate.
... Revising recent work on object recognition for mobile phones (e.g. [9,10]) we assume that recognizing any 2D object (such as physical CDs) and estimate its pose to present an aligned augmentation will be feasible in the very near future. ...
Interacting with physical CDs can be a very tangible and explorative experience. However, physical objects can't provide access to the digital services we are used to when using with digital music collections. In this paper we develop user interfaces for mobile phones that augment physical CDs to provide access to digital services. The most important functionalities of the music player are derived from a user study. Design sketches for the augmentation shown on the phone's display are collected from 10 participants. Participants' ideas are subsumed by four concepts that are implemented as prototypes for the Android platform.
