With the significant advancement of sensor and communication technology and the reliable application of obstacle detection techniques and algorithms, automated driving is becoming a pivotal technology that can revolutionize the future of transportation and mobility. Sensors are fundamental to the perception of vehicle surroundings in an automated driving system, and the use and performance of multiple integrated sensors can directly determine the safety and feasibility of automated driving vehicles. Sensor calibration is the foundation block of any autonomous system and its constituent sensors and must be performed correctly before sensor fusion and obstacle detection processes may be implemented. This paper evaluates the capabilities and the technical performance of sensors which are commonly employed in autonomous vehicles, primarily focusing on a large selection of vision cameras, LiDAR sensors, and radar sensors and the various conditions in which such sensors may operate in practice. We present an overview of the three primary categories of sensor calibration and review existing open-source calibration packages for multi-sensor calibration and their compatibility with numerous commercial sensors. We also summarize the three main approaches to sensor fusion and review current state-of-the-art multi-sensor fusion techniques and algorithms for object detection in autonomous driving applications. The current paper, therefore, provides an end-to-end review of the hardware and software methods required for sensor fusion object detection. We conclude by highlighting some of the challenges in the sensor fusion field and propose possible future research directions for automated driving systems.

Sensor and Sensor Fusion Technology in Autonomous Vehicles: A Review

Intelligent food processing: Journey from artificial neural network to deep learning

It is common to generate digital elevation models (DEMs) from aerial laser scanning (ALS) data. However, cost and lack of knowledge may preclude its use. In contrast, global navigation satellite systems (GNSS) are seldom used to collect and generate DEMs. These receivers have the potential to be considered as data sources for DEM interpolation, as they can be inexpensive, easy to use, and mobile. The data interpolation method and spatial resolution from this method needs to be optimised to create accurate DEMs. Moreover, the density of GNSS data is likely to affect DEM accuracy. This study investigates three different deterministic approaches, in combination with spatial resolution and data thinning, to determine their combined effects on DEM accuracy. Digital elevation models were interpolated, with resolutions ranging from 0.5 m to 10 m using natural neighbour (NaN), topo to raster (ANUDEM), and inverse distance weighted (IDW) methods. The GNSS data were thinned by 25% (0.389 points m−2), 50% (0.259 points m−2), and 75% (0.129 points m−2) and resulting DEMs were contrast against a DEM interpolated from unthinned data (0.519 points m−2). Digital elevation model accuracy was measured by root mean square error (RMSE) and mean absolute error (MAE). It was found that the highest resolution, 0.5 m, produced the lowest errors in resulting DEMs (RMSE = 0.428 m, MAE = 0.274 m). The ANUDEM method yielded the greatest DEM accuracy from a quantitative perspective (RMSE = 0.305 m and MAE = 0.197 m); however, NaN produced a more visually appealing surface. In all the assessments, IDW showed the lowest accuracy. Thinning the input data by 25% and even 50% had relatively little impact on DEM quality; however, accuracy decreased markedly at 75% thinning (0.129 points m−2). This study showed that, in a time where ALS is commonly used to generate DEMs, GNSS-surveyed data can be used to create accurate DEMs. This study confirmed the need for optimization to choose the appropriate interpolation method and spatial resolution in order to produce a reliable DEM.

https://www.mdpi.com/2220-9964/7/8/300/pdf

A Comparative Study of Three Non-Geostatistical Methods for Optimising Digital Elevation Model Interpolation

Prediction of large-scale demolition waste generation during urban renewal: A hybrid trilogy method.

The importance of earth observation (EO) from space is felt today more than ever in many different fields of human activity. Governments, international organizations, military bodies, private industry, and even individuals benefit every day of the products of spaceborne remote sensing technology. In this paper, we present a brief overview of some of the main trends in the EO scenario, focusing on the emergence of a new paradigm for EO space systems namely: the ongoing, disruptive shift from large satellites to constellations of small spacecraft, fueled by the recent introduction of several key technologies, such as for instance electric propulsion. We present the outline of a tool specifically conceived to assist the system architect in the early design phase of an EO constellation of microsatellites equipped with electric thrusters. A case study is presented for the application of a multisegmented constellation, with visual, thermal infrared, and radar components to remotely monitor a national railway network. We conclude that, in spite of the complexity of modern small satellite constellations, preliminary design can be successfully performed in a simplified and effective way.

Smaller Satellites, Larger Constellations: Trends and Design Issues for Earth Observation Systems

The main goal of this paper is to collect information about pathfinding algorithms A*, BFS, Dijkstra's algorithm, HPA* and LPA*, and compare them on different criteria, including execution time and memory requirements. Work has two parts, the first being theoretical and the second practical. The theoretical part details the comparison of pathfinding algorithms. The practical part includes implementation of specific algorithms and series of experiments using algorithms implemented. Such factors as various size two dimensional grids and choice of heuristics were taken into account while conducting experiments.

/pdf/pathfinding-algorithm-efficiency-analysis-in-2d-grid-53t1q9mfcw.pdf

Pathfinding Algorithm Efficiency Analysis in 2D Grid

Building Recognition Using LiDAR and Energy Minimization Approach

Real Estate Monitoring System Based on Remote Sensing and Image Recognition Technologies

Received: January 11th, 2021 ; Accepted: April 10th, 2021 ; Published: April 22nd, 2021 ; Correspondence: sergejs.kodors@rta.lv

Apple scab detection using CNN and Transfer Learning

A parameter “point density” is often used to evaluate the quality of aerial laser scanning data. It is a parameter simple for understanding and human imagination. However, the true quality of LiDAR point cloud is based on point distribution. There are researches, which mention importance of point distribution and users’ false perception, that higher point density is better quality of LiDAR point cloud. The goal of this study is to define the mathematical model how to measure quality of LiDAR point cloud. This article discusses the point distribution and LiDAR data quality defining the image resolution of point cloud. It can be interesting for experts in civil geospatial intelligence, LiDAR data processing and flight planning.

/pdf/point-distribution-as-true-quality-of-lidar-point-cloud-ohx2zz8tl0.pdf

Sergejs Kodors

Papers

Pathfinding Algorithm Efficiency Analysis in 2D Grid

Building Recognition Using LiDAR and Energy Minimization Approach

Real Estate Monitoring System Based on Remote Sensing and Image Recognition Technologies

Apple scab detection using CNN and Transfer Learning

Point Distribution as True Quality of LiDAR Point Cloud