Nuestro objetivo es proporcionar información detallada y precisa sobre las cuevas y la dinámica de la población de quirópteros (murciélagos) que las habitan nos permite comprender las dimensiones y requerimientos del hábitat, monitorear tamaños de poblaciones, desarrollar planes de manejo y conservación específicos. Por tanto, aumentamos nuestro entendimiento de los murciélagos con su entorno y mejoramos la prevención de enfermedades zoonóticas. En este artículo presentamos el desarrollo de una plataforma portátil multisensor, compuesta por una cámara RGB, dos cámaras infrarrojas, sensores inerciales y un par de luces infrarrojas. Esta plataforma permite la detección de quirópteros y la reconstrucción de las cuevas donde habitan. Ejecuta un algoritmo en tiempo real, generando un mapa de nube de puntos y facilitando la observación y detección de los quirópteros. La plataforma fue probada en condiciones reales en diferentes cuevas del estado de Guanajuato por personal del “Comité Estatal para el Fomento y la Protección Pecuaria”.

This study presents the development and evaluation of a portable multisensor system for generating three-dimensional maps of the Normalized Difference Vegetation Index (NDVI) by integrating spectral and geometric information for vegetation monitoring in precision agriculture applications. The system integrates an RGB camera, a near-infrared camera (NIR; Arducam UC-844), and a depth sensor (Intel RealSense D435i), controlled by a Raspberry Pi 5 platform. The main methodological contribution lies in the design of a custom calibration pattern that enables the establishment of geometric correspondences among the sensors and the association of spectral values with points in the three-dimensional point cloud. Extrinsic calibration between the depth sensor and the RGB and NIR cameras yielded mean reprojection errors of 1.26 and 1.43 pixels, respectively. NDVI was calculated for each point in the 3D point cloud by projecting its coordinates onto the RGB and NIR images, incorporating a radiometric correction factor $\alpha$ estimated through a controlled leaf-drying experiment. System performance was evaluated by comparison with measurements from a GreenSeeker HCS-250 reference sensor, yielding correlation coefficients ranging from 0.94 to 0.98 and an overall coefficient of determination of R² = 0.9629. The results support the feasibility of integrating spectral and geometric information to generate three-dimensional NDVI maps with high agreement with reference measurements. The proposed system provides a portable alternative for spatially representing variability in vegetation condition and exploring its application in crop monitoring tasks within precision agriculture.

Automated wildlife monitoring systems are essential for studying bat populations in natural environments, where nocturnal behavior, high flight speeds, and limited illumination make conventional observation difficult. This paper presents a modular multi-sensor vision system that integrates RGB, near-infrared (NIR), and depth cameras for automated bat monitoring. The proposed architecture consists of one main module and two secondary modules that can be configured into multiple operating modes according to monitoring requirements. The main module operates independently to perform real-time habitat reconstruction using an integrated depth camera or bat detection using a YOLO-based model. When combined with one secondary module, it forms a stereo vision system for three-dimensional localization; when combined with both secondary modules, it generates panoramic images that substantially expand the field of view for monitoring large cave entrances and other complex environments. The proposed modular architecture enables flexible deployment while supporting multiple sensing configurations within a single platform. The modular design provides scalability, geometric consistency through multi-sensor calibration, and flexible deployment, enabling accurate bat detection, habitat reconstruction, and wide-area monitoring within a unified sensing framework. The proposed system provides a versatile and scalable solution for adapting wildlife monitoring to different environmental conditions and observation scenarios. Experimental results demonstrate a detection precision of 0.893, a panoramic field of view of 119°, and real-time processing at 60 fps, validating the effectiveness of the proposed modular architecture.