3D Distance Measurement from a Camera to a Mobile Vehicle, Using Monocular Vision

Abstract

Estimation of distance from objects in real-world scenes is an important topic in several applications such as navigation of autonomous robots, simultaneous localization and mapping (SLAM), and augmented reality (AR). Even though there is a technology for this purpose, in some cases, this technology has some disadvantages. For example, GPS systems are susceptible to interference, especially in places surrounded by buildings, under bridges or indoors; alternatively, RGBD sensors can be used, but they are expensive, and their operational range is limited. Monocular vision is a low-cost suitable alternative that can be used indoor and outdoor. However, monocular odometry is challenging because the object location can be known up a scale factor. Moreover, when objects are moving, it is necessary to estimate the location from consecutive images accumulating error. This paper introduces a new method to compute the distance from a single image of the desired object, with known dimensions, captured with a monocular calibrated vision system. This method is less restrictive than other proposals in the state-of-the-art literature. For the detection of interest points, a Region-based Convolutional Neural Network combined with a corner detector were used. The proposed method was tested on a standard dataset and images acquired by a low-cost and low-resolution webcam, under noncontrolled conditions. The system was tested and compared with a calibrated stereo vision system. Results showed the similar performance of both systems, but the monocular system accomplished the task in less time.

Height-Variable Monocular Vision Ranging Technology for Smart Agriculture

“…The distance to the measured point is obtained by bringing the distortion-reduced physical coordinates and a fixed focal length value to the distance measurement model. 2) The distance measurement method proposed by Saúl Martínez-Díaz [19]. As the method requires the input of the distance between any three feature points on the surface of the target, the experiment will first mark the feature points on the target and obtain the distance between them.…”

“…The disadvantage of this method is that the object needs to be perpendicular to the ground, and the approximate solution can show higher accuracy when the object distance is much larger than the camera height, or the camera height is much larger than the object height. The ranging model proposed by Saúl Martínez-Díaz [19] does not need to consider the camera pose, but needs to know the relative distance between the three points in the image including the measured point, so the application scenario is limited. Most of the current ranging methods based on geometric ranging models do not take into account the impact of camera nonlinear imaging on the model, and require known spatial information such as the height of the object being measured or the distance between feature points during the ranging process.…”

A Reconfigurable Framework for Vehicle Localization in Urban Areas

“…More recently, local positioning has also been addressed by analyzing and processing camera images. This technique has been named visual odometry (VO) [ 6 , 7 ]. A similar approach, which some authors name LiDaR odometry [ 8 ], can be implemented using the data cloud provided by LiDAR sensors.…”