AR technology is rapidly growing direction. Nevertheless, mobile and embedded AR still faces a lot of real-life problems and challenges. The talk will be devoted to review of AR principles and applications. The key part will contain the analysis of available technical solutions for mobile AR. Indeed, quite a lot of software engineers use the 3rd part frameworks (ARkit, ARcore, Vuforia, etc.) without putting enough attention into algorithmic and implementation details. In the presentation, we will consider the state-of-the-art algorithms for marker detection and recognition. Moreover, several fresh methods for real-time marker tracking will be discussed. In addition, such hot topics as markerless tracking, sensor fusion and SLAM will be covered as well. Finally, several real demos from custom mobile AR SDK will be shown.
Author: admin
Positioning Algorithms for Indoor Navigation Using Sensors Fusion
It is known, that nowadays almost every indoor positioning and navigation system (IPNS) consists of a radio signals part (Wi-Fi or BLE) and a part based on smartphone inertial sensors. Both parts contain a number of challenges complicating a precise user positioning using mobile phones or tablets. In the paper, we describe several contributions. Firstly, a problem of BLE packets recovering is considered. A specific version of a Kalman filter for received signal strength indicator (RSSI) data analysis is developed. The proposed modification allows recovering lost data as well as providing sufficient signal smoothing. Secondly, a custom step detection procedure based on an inertial navigation system (INS) is developed. Unlike to a common solution based on the thresholding of linear acceleration amplitude, an advanced version of the detector is highlighted. Finally, a hybrid indoor localization and navigation (HILN) system developed on the basis of a particle filter (PF) and the proposed modifications for BLE and INS parts is described. Experimental results are provided.
Data Stream Mining & Processing Conference – 2018
Meet us at the IEEE Second International Conferеnce on Data Stream Mining & Processing (DSMP-2018) and listen to:
- Ievgen Gorovyi with at a panel presentation “Custom augmented reality SDK: concepts, technical solutions and deployment to mobile platforms”
- Vitalii Vovk with a presentation on Embedded Vision Modules for Text Recognition and Fiducial Markers Tracking
- Yevhen Chervoniak with a presentation Data Processing Methods for Mobile Indoor Navigation.
See you there!
9th International Conference on Indoor Positioning and Indoor Navigation
Ievgen Gorovyi will attend the 9th International Conference on Indoor Positioning and Indoor Navigation (IPIN-2018) with the demonstration of our indoor positioning engine based on BLE and IMU. Find out more about the technical details on what he will be presenting there in this paper.
AI Ukraine – 2018
We are attending the biggest AI & data science event in Ukraine – AI Ukraine! Ievgen Gorovyi will also be a speaker at this conference. Don’t miss his presentation on Augmented Reality: Modern Trends and Technical Applications on October 14 at 12:55 (Stream A).
Update: now you can watch Ievgen’s presentation here. Enjoy!
6th DataScienceUA Conference
Data Science UA Conference brings together leaders in machine learning, analytics, BI, data science, AI for a day-long exploration of how data trans-forms the World today and what is going to be tomorrow.
ProfIT Conference – 2019
Ievgen Gorovyi, the CEO of It-Jim, will join the open session “IT: Industry view” of the II International scientific and practical conference of IT professionals and analysts of computer systems “ProfIT Conference 2019” with the talk on Application of artificial intelligence in tasks of visual information processing.
Conference on Computer Vision and Pattern Recognition – 2019
First held in Washington DC in 1983, today CVPR is regarded as the world’s premier computer vision conference. In 2018, CVPR received 3300 main conference paper submissions and accepted 979. In 2019, its submissions spiked to 5165, a 56% increase over 2018. The submission and acceptance totals both set records as the conference had never before accepted more than 1000 papers. The list of all 1300 research papers accepted for CVPR 2019 is available here: http://openaccess.thecvf.com/CVPR2019.py. Given you spend 1 hour to read 1 article and the rate of 8 articles per day, it will take you about 6 months to read all of them. You’d better start right now 🙃
CVPR 2019 in numbers:
- over 6k attendees
- 25 tutorials
- 88 workshops
- 181 exhibitors including Adobe Systems Inc., Amazon, Apple, Boston Dynamics, Facebook, Google, Hitachi, IBM Research, Intel, Microsoft, Qualcomm, Samsung Electronics, Tesla, Uber. And this is just to name a few!
- countless job offers [machine learning researchers and software engineers, check this out: http://cvpr2019.thecvf.com/jobs].
It’s going to be nothing but incredible! And we are extremely happy to attend this conference. Stay tuned for our CTO’s live reports from California on our social media!
