Web and MATLAB-Based Platform for UAV Flight Management and Multispectral Image Processing.

The deployment of any UAV application in precision agriculture involves the development of several tasks, such as path planning and route optimization, images acquisition, handling emergencies, and mission validation, to cite a few. UAVs applications are also subject to common constraints, such as weather conditions, zonal restrictions, and so forth. The development of such applications requires the advanced software integration of different utilities, and this situation may frighten and dissuade undertaking projects in the field of precision agriculture. This paper proposes the development of a Web and MATLAB-based application that integrates several services in the same environment. The first group of services deals with UAV mission creation and management. It provides several pieces of flight conditions information, such as weather conditions, the KP index, air navigation maps, or aeronautical information services including notices to Airmen (NOTAM). The second group deals with route planning and converts selected field areas on the map to an UAV optimized route, handling sub-routes for long journeys. The third group deals with multispectral image processing and vegetation indexes calculation and visualizations. From a software development point of view, the app integrates several monolithic and independent programs around the MATLAB Runtime package with an automated and transparent data flow. Its main feature consists in designing a plethora of executable MATLAB programs, especially for the route planning and optimization of UAVs, images processing and vegetation indexes calculations, and running them remotely.

Advanced Driver Assistance Systems (ADAS) Based on Machine Learning Techniques for the Detection and Transcription of Variable Message Signs on Roads.

Among the reasons for traffic accidents, distractions are the most common. Although there are many traffic signs on the road that contribute to safety, variable message signs (VMSs) require special attention, which is transformed into distraction. ADAS (advanced driver assistance system) devices are advanced systems that perceive the environment and provide assistance to the driver for his comfort or safety. This project aims to develop a prototype of a VMS (variable message sign) reading system using machine learning techniques, which are still not used, especially in this aspect. The assistant consists of two parts: a first one that recognizes the signal on the street and another one that extracts its text and transforms it into speech. For the first one, a set of images were labeled in PASCAL VOC format by manual annotations, scraping and data augmentation. With this dataset, the VMS recognition model was trained, a RetinaNet based off of ResNet50 pretrained on the dataset COCO. Firstly, in the reading process, the images were preprocessed and binarized to achieve the best possible quality. Finally, the extraction was done by the Tesseract OCR model in its 4.0 version, and the speech was done by the cloud service of IBM Watson Text to Speech.

Machine Learning Techniques for Undertaking Roundabouts in Autonomous Driving.

This article presents a machine learning-based technique to build a predictive model and generate rules of action to allow autonomous vehicles to perform roundabout maneuvers. The approach consists of building a predictive model of vehicle speeds and steering angles based on collected data related to driver-vehicle interactions and other aggregated data intrinsic to the traffic environment, such as roundabout geometry and the number of lanes obtained from Open-Street-Maps and offline video processing. The study systematically generates rules of action regarding the vehicle speed and steering angle required for autonomous vehicles to achieve complete roundabout maneuvers. Supervised learning algorithms like the support vector machine, linear regression, and deep learning are used to form the predictive models.

Using Open Geographic Data to Generate Natural Language Descriptions for Hydrological Sensor Networks.

Providing descriptions of isolated sensors and sensor networks in natural language, understandable by the general public, is useful to help users find relevant sensors and analyze sensor data. In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions. We present a general method that uses such information to generate sensor descriptions in natural language. The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches. In the paper we also analyze certain problems that we found in public databases (e.g., heterogeneity, non-standard use of labels, or rigid search methods) and their impact in the generation of sensor descriptions.