Soichiro Horimi

Bio: Soichiro Horimi is an academic researcher from Ritsumeikan University. The author has contributed to research in topics: Interface (computing) & Template matching. The author has an hindex of 2, co-authored 2 publications receiving 17 citations.

Pano UMECHIKA: A Crowded Underground City Panoramic View System

Abstract: Toward a really useful navigation system, utilizing spherical panoramic photos with maps like Google Street View is efficient. Users expect the system to be available in all areas they go. Conventional shooting methods obtain the shot position from GPS sensor. However, indoor areas are out of GPS range. Furthermore, most urban public indoor areas are crowded with pedestrians. Even if we blur the pedestrians in a photo, the photos with blurring are not useful for scenic information. Thus, we propose a method which simultaneously subtracts pedestrians based on background subtraction method and generates location metadata by manually input from maps. Using these methods, we achieved an underground panoramic view system which displays no pedestrians.

Wi-Foto 2: Heterogeneous device controller using Wi-Fi positioning and template matching

Abstract: Improving usability of heterogeneous devices is important in pervasive computing. We have developed Wi-Foto, which enables users to control such devices by using a tablet PC as a client. Wi-Foto has a user-friendly interface which has device controllers overlaid on a photo depicting the interior of the room where the user is. In order to find the most appropriate photo, Wi-Foto automatically locates the user by Wi-Fi positioning but the localization would often fail because of in- adequate accuracy. To solve this problem, we propose Wi-Foto 2, which combines the Wi-Fi positioning with template matching based on a SIFT algorithm. We confirm that the proposed method realizes accurate and fast positioning. Wi-Foto 2 also enables users to seamlessly select photos through hierarchical and panoramic views.

Probabilistic Multi-Sensor Fusion Based Indoor Positioning System on a Mobile Device

Abstract: Nowadays, smart mobile devices include more and more sensors on board, such as motion sensors (accelerometer, gyroscope, magnetometer), wireless signal strength indicators (WiFi, Bluetooth, Zigbee), and visual sensors (LiDAR, camera). People have developed various indoor positioning techniques based on these sensors. In this paper, the probabilistic fusion of multiple sensors is investigated in a hidden Markov model (HMM) framework for mobile-device user-positioning. We propose a graph structure to store the model constructed by multiple sensors during the offline training phase, and a multimodal particle filter to seamlessly fuse the information during the online tracking phase. Based on our algorithm, we develop an indoor positioning system on the iOS platform. The experiments carried out in a typical indoor environment have shown promising results for our proposed algorithm and system design.

WiFi Sensing System for Monitoring Public Transportation Ridership: A Case Study

Abstract: Public transportation system as an essential mode of travel has been investigated by local governments and transportation agencies to capture passengers’ travel behaviors. Despite their efforts, agencies especially in small to medium sized cities could not afford to collect such behaviors data due to significant costs associated with the data collection system. In this study, we presented a WiFi sensing system which makes such data collection feasible with low-cost devices. We demonstrated the WiFi sensing system’s applicability in estimating passengers’ origin-destination (O/D) travel and passengers’ bus stop waiting times via video validation. In addition, WiFi signal strength was analyzed to further improve accuracy of the system. To this end, sliding window algorithm was adopted to mitigate the randomness of mobile devices’ signals. Our small-scale proof of concept experiment was conducted at four bus stops along the main transit corridor in Charlottesville, Virginia. Results indicated that the system was able to re-identify 91% of bus passengers and passengers bus stop waiting time error was as small as 7 seconds. It is expected that the system can be a viable low-cost Internet of Things (IoT) solution for monitoring public transit system performance.

A multisensor LBS using SIFT-based 3D models

Abstract: This paper introduces an LBS multisensor system that acquires data from different sensors available in commodity smartphones to provide accurate location estimations. Our approach is based on the use of visual structure from motion techniques to run off-line 3D reconstructions of the environment from the correspondences among the SIFT descriptors of the training images. We present several solutions to reduce the deployment cost, in terms of time, and to minimize the interference degree within the environment, but also pursuing a good balance between accuracy and performance. To determine the position of the smartphones, we first obtain a coarse-grained estimation based on WiFi signals, digital compasses, and built-in accelerometers, making use of fingerprinting methods, probabilistic techniques, and motion estimators. Then, using images captured by the camera, we perform a matching process to determine correspondences between 2D pixels and model 3D points, but only analyzing a subset of the 3D model delimited by the coarse-grained estimation. We implement a resection process providing high localization accuracy when the camera has been previously calibrated, that is, we know intrinsic parameters like focal length, but it is also accurate if an auto-calibration process is required. Furthermore, our experimental tests show promising results, since we are able to provide high accuracy with an average error down to 15 cm in less than 0.5 seconds of response time, making this proposal suitable for applications combining location-services and augmented reality.

Using SIFT and WiFi Signals to Provide Location-Based Services for Smartphones

Abstract: This paper introduces how to fuse the data acquired from different sensors available in commodity smartphones to build accurate location-based services, pursuing a good balance between accuracy and performance. Using scale invariant features from the images captured using the smartphone camera, we perform a matching process against previously obtained images to determine the current location of the device. Several refinements are introduced to improve the performance and the scalability of our proposal. Location fingerprinting, based on IEEE 802.11, will be used to determine a cluster of physical points, or zone, where the device seems to be according to the received signal strength. In this way, we will reduce the number of images to analyze to those contained in the tentative zone. Additionally, accelerometers will be also considered in order to improve the system performance, by means of a motion estimator. This set of techniques enables a wide range of new location-based applications.

Mobile AR using pre-captured omnidirectional images

Abstract: In the field of augmented reality (AR), geometric and photometric registration is routinely achieved in real time. However, real-time geometric registration often leads to misalignment (e.g., jitter and drift) due to the error from camera pose estimation. Due to limited resources on mobile devices, it is also difficult to implement state-of-the-art techniques for photometric registration on mobile AR systems. In order to solve these problems, we developed a mobile AR system in a significantly different way from conventional systems. In this system, captured omnidirectional images and virtual objects are registered geometrically and photometrically in an offline rendering process. The appropriate part of the prerendered omnidirectional AR image is shown to a user through a mobile device with online registration between the real world and the pre-captured image. In order to investigate the validity of our new framework for mobile AR, we conducted experiments using the prototype system on a real site in Todai-ji Temple, a famous world cultural heritage site in Japan.