Summary
Tracking a moving camera’s position and orientation can be tricky when using just one camera, especially if parts of the scene are blocked or lack details. The researchers developed a system called MFVINS that uses several wide-angle fisheye cameras instead of just one to better see the environment, which helps avoid errors from confused or missing visual information. They also introduced smarter ways to find good matching points across images and to check the math behind combining camera and sensor data, making the system faster and more reliable. This approach helps the system keep track of movement in real time even in challenging environments. They showed that their system works better than older methods that use only a single camera.
simultaneous localization and mapping (SLAM)visual-inertial system (VINS)fisheye camerainertial measurement unit (IMU)feature trackingbundle adjustmentdepth estimationreprojection errorocclusiontextureless regions
Authors
Eunseong Jang, YuJin Chung, Sang Jun Lee, Jihyun Yoon, HyungGi Jo
Abstract
A simultaneous localization and mapping (SLAM) method using a monocular camera and a low-cost inertial measurement unit (IMU) sensor is an effective way to fulfill a low-cost sensor configuration. Using this sensor configuration, visual-inertial system (VINS) focuses on fusing data from a camera and an IMU sensor to estimate the six degrees-of-freedom (DOF) of the sensor pose. Typically, VINS uses only a single camera as visual input, which lead to problems such as error accumulation due to occlusion, various illumination, and textureless environments. In this paper, we propose a new multiple fisheye camera-based visual-inertial system called MFVINS. We present an IMU-aided FAST feature tracker for multiple cameras that enables efficient extraction and robust matching of local features. Then, the proposed method filters out outliers caused by fisheye distortion on the normalized image plane. Subsequently, a new reprojection error with physical validity constraints is proposed for bundle adjustment using learning-based depth estimation. The proposed method is applied to various scenarios, and its effectiveness is demonstrated by comparing previous VINS methods. In particular, MFVINS is implemented in real-time process to leverage the advantages of using multiple cameras -- robustness against occlusion and textureless regions -- while reducing the computational burden.