18 research outputs found
Real-time Estimation of Road Surfaces using Fast Monocular Depth Estimation and Normal Vector Clustering
Get PDFEstimating a road surface or planes for applying AR(Augmented Reality) or an autonomous vehicle using a camera requires significant computation. Vision sensors have lower accuracy in distance measurement than other types of sensor, and have the difficulty that additional algorithms for estimating data must be included. However, using a camera has the advantage of being able to extract various information such as weather conditions, sign information, and road markings that are difficult to measure with other sensors. Various methods differing in sensor type and configuration have been applied. Many of the existing studies had generally researched by performing the depth estimation after the feature extraction. However, recent studies have suggested using deep learning to skip multiple processes and use a single DNN(Deep Neural Network). Also, a method using a limited single camera instead of a method using a plurality of sensors has been proposed. This paper presents a single-camera method that performs quickly and efficiently by employing a DNN to extract distance information using a single camera, and proposes a modified method for using a depth map to obtain real-time surface characteristics. First, a DNN is used to estimate the depth map, and then for quick operation, normal vector that can connect similar planes to depth is calculated, and a clustering method that can be connected is provided. An experiment is used to show the validity of our method, and to evaluate the calculation time
Sensor Fusion for Accurate Ego-Motion Estimation in a Moving Platform
Get PDFWith the coming of “Internet of things” (IoT) technology, many studies have sought to apply IoT to mobile platforms, such as smartphones, robots, and moving vehicles. An estimation of ego-motion in a moving platform is an essential and important method to build a map and to understand the surrounding environment. In this paper, we describe an ego-motion estimation method using a vision sensor that is widely used in IoT systems. Then, we propose a new fusion method to improve the accuracy of motion estimation with other sensors in cases where there are limits in using only a vision sensor. Generally, because the dimension numbers of data that can be measured for each sensor are different, by simply adding values or taking averages, there is still a problem in that the answer will be biased to one of the data sources. These problems are the same when using the weighting sum using the covariance of the sensors. To solve this problem, in this paper, using relatively accurate sensor data (unfortunately, low dimension), the proposed method was used to estimate by creating artificial data to improve the accuracy (even of unmeasured dimensions)
Self-Supervised Sensor Learning and Its Application: Building 3D Semantic Maps Using Terrain Classification
No full textAn autonomous robot in an outdoor environment needs to recognize the surrounding environment to move to a desired location safely; that is, a map is needed to classify/perceive the terrain. This paper proposes a method that enables a robot to classify a terrain in various outdoor environments using terrain information that it recognizes without the assistance of a user; then, it creates a three-dimensional (3D) semantic map. The proposed self-supervised learning system stores data on the appearance of the ground data using image features extracted by observing the movement of humans and vehicles while the robot is stopped. It learns about the surrounding environment using a support vector machine with the stored data, which is divided into terrains where people or vehicles have moved and other regions. This makes it possible to learn which terrain an object can travel on using a self-supervised learning and image-processing methods. Then the robot can recognize the current environment and simultaneously build a 3D map using the RGB-D iterative closest point algorithm with a RGB-D sensor (Kinect). To complete the 3D semantic map, it adds semantic terrain information to the map
