Semantic Evidential Grid Mapping Using Monocular and Stereo Cameras

Abstract

Accurately estimating the current state of local traffic scenes is one of the key problems in the development of software components for automated vehicles. In addition to details on free space and drivability, static and dynamic traffic participants and information on the semantics may also be included in the desired representation. Multi-layer grid maps allow the inclusion of all of this information in a common representation. However, most existing grid mapping approaches only process range sensor measurements such as Lidar and Radar and solely model occupancy without semantic states. In order to add sensor redundancy and diversity, it is desired to add vision-based sensor setups in a common grid map representation. In this work, we present a semantic evidential grid mapping pipeline, including estimates for eight semantic classes, that is designed for straightforward fusion with range sensor data. Unlike other publications, our representation explicitly models uncertainties in the evidential model. We present results of our grid mapping pipeline based on a monocular vision setup and a stereo vision setup. Our mapping results are accurate and dense mapping due to the incorporation of a disparity- or depth-based ground surface estimation in the inverse perspective mapping. We conclude this paper by providing a detailed quantitative evaluation based on real traffic scenarios in the KITTI odometry benchmark dataset and demonstrating the advantages compared to other semantic grid mapping approaches.

The Constraints between Edge Depth and Uncertainty for Monocular Depth Estimation

“…Currently, most of the work related to improving edge depth requires the introduction of an additional network, e.g., semantic segmentation [10][11][12], edge map detection networks [13][14][15], or optical flow [16]. We found that research on uncertainty, which has only recently entered the limelight, can also improve the quality of edge depth and without learning other complex networks.…”

Mapping LiDAR and Camera Measurements in a Dual Top-View Grid Representation Tailored for Automated Vehicles

“…None of the above-mentioned publications models occupancy and semantic estimates in a joint evidential context. In [19]- [21] a sensor grid mapping pipeline was presented estimating a BBA on a FOD containing ground and object hypotheses for range sensors and cameras. Here, we present an advancement of the evidential model and rethink the BBA estimation.…”

Crowdsourcing-Based Indoor Semantic Map Construction and Localization Using Graph Optimization

“…Since semantic landmarks are associated with Wi-Fi landmarks, Wi-Fi fingerprinting is used to determine a one-to-one association between semantic landmarks. Additionally, the distance between semantic landmarks is calculated using Equations ( 6)- (8). Utilizing pre-matching significantly improves the efficiency of matching landmarks.…”

“…Scholars have proposed many sensor-based mapping solutions, such as lidar-based [7], camera-based [8], Wi-Fi-based, inertial measurement unit (IMU)-based, and magneticbased [9], to solve the mapping problem in unknown indoor environments. Due to these sensors' inherent characteristics, single-sensor-based map construction methods have limited application scopes.…”