Telefon: +43(0) 662 834 602 - 0

DI Yerania Campos, PhD


Yerania Campos ist Researcher im Studio PCA.


Dipl.-Ing. Dr. Yerania Campos received the BS degree in Mathematical Engineering from the National Polytechnic Institute, Mexico, the MS in Computer Science and Industrial Mathematics from the Research Center in Mathematics, Mexico, and the PhD in Informatics from University Complutense of Madrid, Spain. Her research interests include machine visual perception, machine learning, precision agriculture and biomedical imaging applications.

Wichtigste Publikationen:

Campos Yerania, Rodner Erik, Denzler Joachim, Sossa Humberto, and Pajares, Gonzalo. “Vegetation Segmentation in Cornfield Images Using Bag of Words”, Proceedings: Advanced Concepts for Intelligent Vision Systems, 17th International Conference, Springer International Publishing 10016, 193-204 (2016).
Abstract: We provide an alternative methodology for vegetation segmentation in cornfield images. The process includes two main steps; a) a low-level segmentation and b) a class label assignment using Bag of Words representation in conjunction with a supervised learning framework. The experimental results show that our proposal is adequate to extract green plants in images of maize fields with an accuracy of 95.3 %.

Campos Yerania, Sossa Humberto, and Pajares Gonzalo. “Spatio-temporal Analysis for Obstacle Detection in Agricultural Videos”. Applied Soft Computing 45, 86-97 (2016).
Abstract: Autonomous mobile vehicles are becoming commoner in outdoor scenarios for agricultural applications. They are equipped with a robot navigation system for sensing, mapping, localization, path planning, and obstacle avoidance.  In autonomous vehicles, safety becomes a major challenge where unexpected obstacles in the working area must be conveniently addressed. Detection of unexpected obstacles on video sequences acquired with a machine vision system on-board of a tractor moving in cornfields is the main goal of this research. We propose a strategy for video analysis to detect static/dynamic obstacles. At a first stage obstacles are detected by using spatial information based on spectral colour analysis and texture data. At a second stage temporal information is used to discriminate between static and dynamic obstacles. Our method compare favorably with existing state-of-the-art when tested in different outdoor scenarios in agricultural environments.

Campos Yerania, Humberto Sossa, and Gonzalo Pajares. “Comparative analysis of texture descriptors in maize fields with plants, soil and object discrimination”, Precision Agriculture 18(5): 1-19 (2016).
Abstract: Precision Agriculture aims to apply selective treatments and tasks at localized areas concerning crop fields. Robotized and autonomous tractors, equipped with perception, decision-making and actuation systems, can apply specific treatments as may be required. The objective of this study was the design of a classifier for identifying plants (crops and weeds), soil and objects in maize images for autonomous tractors. The study included a comparative analysis of different texture descriptors. Also, the classifier was used for the detection of obstacles in the trajectory of the tractor.

Telefon: +43(0) 662 834 602 - 0