Browsing by Autor "Edgar Eduardo Salazar Florez"

Now showing 1 - 3 of 3

A Computer Vision-Based Autonomous System for Ripe Strawberry Detection and Navigation
(2025) M. Barba; Marcelo Saavedra Alcoba; Edgar Eduardo Salazar Florez
This work presents an autonomous robotic system designed for ripe strawberry detection and navigation in agricultural environments using cost-efficient hardware and optimized algorithms. The system integrates a Jetson Nano for real-time image processing, employing LAB color space transformation, morphological filtering, and a lightweight MobileNet SSD model trained on the StrawDI dataset to classify strawberries by ripeness. Autonomous navigation is achieved via a Pixhawk flight controller that tracks GPS waypoints and adjusts trajectories dynamically using ultrasonic sensors for obstacle detection. Field experiments in a controlled strawberry field setup demonstrated robust performance: the vision system achieved 86.21% precision and 89.29% recall. Navigation tests showed 95% accuracy in following a 5-meter path, with successful obstacle avoidance. The results validate the feasibility of deploying low-cost, energy-efficient embedded systems for agricultural automation, addressing scalability challenges in resource-limited settings.
A Portable Embedded System for Skin Lesions Detection
(2024) Giancarlo López Bustos; Xavier Alexis Murillo Sanchez; Edgar Eduardo Salazar Florez
Skin cancer is one of the most common types of cancer in the present decade. It can be classified into two categories: melanoma and non-melanoma. Melanoma is a dangerous, rare, and fatal type of skin cancer. Detection of melanoma in early stages is beneficial because it can improve the survival rate. As such in this paper, we developed an embedded system using a Jetson Nano that employs image processing techniques based on the ABCD rule to classify skin lesions according risk levels. The structure of the proposed system consists of two phases: the first phase involves an algorithm that performs segmentation, feature extraction, and classification; the second phase includes the electronic and mechanical design of the embedded system. This embedded system is intended to serve as a support tool for patients and doctors in the diagnosis of skin lesions and it represents the first of its kind in Bolivia.
An Algorithm for Medical Specialists to Assist in the Diagnosis of Down Syndrome Using Nasal Bone Location in Ultrasound Images
(2025) Giancarlo López-Bustos; Sergio Velásquez; Xavier Alexis Murillo Sanchez; Edgar Eduardo Salazar Florez
Down syndrome is a genetic disorder caused by the presence of an additional chromosome at position 21, also known as trisomy 21. This condition leads to intellectual disability and affects the physical and cognitive development of the child. For early diagnosis, medical specialists consider two key parameters: the absence or presence of the nasal bone and the size of the nuchal translucency. These assessments are typically conducted between 11–13 weeks of the 1<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">st</sup> trimester of gestation using ultrasound imaging. In this paper we propose an algorithm to assist in the diagnosis of Down Syndrome by detecting the presence of nasal bone using a data-independent algorithm. The image processing pipeline consists of segmentation procedures developed grouping higher intensity pixels with similar features and detecting the nasal bone based on pattern recognition using geometrical features. The algorithm was tested with 45 images captured locally, 43 of which are normal cases and 2 are Down Syndrome obtaining an accuracy of 84% and the evaluation was carried out with an ultrasound specialist doctor.