-High tracking accuracy (1mm-1cm) / High speed / Low CPU consumption (bellow 5%) / Robustness-
TOKYO — (BUSINESS WIRE) — August 14, 2017 — Kudan, Inc. has succeeded to develop real time 3D mapping and position tracking via camera, called “KudanSLAM*1”, and started to provide its technology to the market such as Autonomous car, ADAS*2, Drone, Industrial and Personal Robots in addition to the existing AR/VR industries.
SLAM, is the software technology, which is capable of 3D mapping and position tracking. It provides computers the ability of “computer vision” to acquire, process, analyse and understand digital images as well as the ability to map its 3D environment, objects, and understand its location within it. This “Computer Vision” technology can be used for any industries such as Autonomous car and Robotics.
Kudan has been developing tracking space and object technology through AR. As a result, Kudan succeeded to develop practicable and next generation algorithm, which would replace the existing SLAM such as ORB and PTAM*3 SLAM base, and apply those technology to be ready for the market.
Kudan, as a SLAM’s leading company, aims to spread use of KudanSLAM which is to be embedded on all image-related devices with camera, in any fields such as Autonomous car, ADAS, Drone and Robotics in addition to the existing AR/VR area.
Key features of KudanSLAM
- Hardware friendly: flexible with camera setup including monocular, rolling shutter, and other sensors. Ready to be embedded on processor any other tech architecture
- High speed / Low consumption: less than 5% of mobile CPU consumption
- High tracking accuracy: 1mm-1cm*4
- Robustness: Capable to work under severe lighting condition and with unpredictable movement
1 SLAM: Simultaneous Localization and Mapping, enables
real-time 3D mapping and position tracking
2 ADAS : Advanced Driver Assistance System
3 ORB,PTAM SLAM : The existing open source SLAM algorithms
4 Kudan research: The accuracy is proportional to the distance between the camera and the recognition target. 1mm to 1cm accuracy in 1m distance by smartphone spec camera.
=== KudanSLAM Use scene ===
1) Autonomous car / ADAS
-KudanSLAM is ready to be also combined with internal sensor and LiDAR
and that leads to realize further robustness and more precise position
-It would be useful for monitoring both front and back, which is not to be effected by environmental noise, also useful for parking assistant, which needs precise position tracking with a few centimeters difference.
(demo) KudanSLAM building a 3D map using a car camera
-Despite low-end camera of Drone, it enables to recognize object and
position tracking precisely with 1mm to 1cm accuracy.
-Robust with severe lighting condition, occlusion and unpredictable movement.
(demo) KudanSLAM building a 3D map using a drone camera
-Even without outside sensor, KudanSLAM enables robot to work independently, which makes the robot work freely, without any specific facility and environment.
-Even without marker, KudanSLAM enables to display absolute position
tracking. It enables to display the specific AR at the specific place,
and share the same AR image with the other person.
-Navigation without GPS is available, such as indoor and inside of the factory.
-KudanSLAM enables to track the headset holder’s position and eye tracking, which would be utilized as data analysis of the effective operation.
Comparison chart of SLAM specification
Technical Strength: Practicality
KudanSLAM performs with high speed/low consumption, high accuracy
|Performance comparison with open source algorithms*1|
(ms for a single tracking frame)
(minimum % of fields of view
*1: Original evaluation using 2014 Macbook Pro and Duo3D