Semantic Segmentation in Large-Size Orthomosaics to Detect the Vegetation Area in Opuntia spp. Crop.

This study focuses on semantic segmentation in crop Opuntia spp. orthomosaics; this is a significant challenge due to the inherent variability in the captured images. Manual measurement of Opuntia spp. vegetation areas can be slow and inefficient, highlighting the need for more advanced and accurate methods. For this reason, we propose to use deep learning techniques to provide a more precise and efficient measurement of the vegetation area. Our research focuses on the unique difficulties posed by segmenting high-resolution images exceeding 2000 pixels, a common problem in generating orthomosaics for agricultural monitoring. The research was carried out on a Opuntia spp. cultivation located in the agricultural region of Tulancingo, Hidalgo, Mexico. The images used in this study were obtained by drones and processed using advanced semantic segmentation architectures, including DeepLabV3+, UNet, and UNet Style Xception. The results offer a comparative analysis of the performance of these architectures in the semantic segmentation of Opuntia spp., thus contributing to the development and improvement of crop analysis techniques based on deep learning. This work sets a precedent for future research applying deep learning techniques in agriculture.

Applying the NDVI from satellite images in delimiting management zones for annual crops

The utilization of Normalized Difference Vegetation Index (NDVI) data obtained through satellite images can technically improve the process of delimiting management zones (MZ) for annual crops, resulting in socio-economic and environmental benefits. The aim of this study was to compare delimited MZ, using crop productivity data, with delimited MZ using the NDVI obtained from satellite images in areas under a no-tillage system. The study was carried out in three areas located in the state of Rio Grande do Sul, Brazil. Three crop productivity maps, from 2009 to 2015, were used for each area, whereby the NDVI was calculated for each crop productivity map using images from the Landsat series of satellites. Descriptive and geostatistical analysis were conducted to determine the productivity and NDVI data. The MZ were then delimited using the fuzzy c-means algorithm. Spearman's correlation matrix was used to compare the methodologies used for delimiting the MZ. The MZ based on NDVI calculated from the satellite images correlated with the MZ based on crop productivity data (0.48 r 0.61), suggesting that the NDVI can replace or be complementary to productivity data in delimiting MZ for annual cropping systems.(AU)

Applying the NDVI from satellite images in delimiting management zones for annual crops

The utilization of Normalized Difference Vegetation Index (NDVI) data obtained through satellite images can technically improve the process of delimiting management zones (MZ) for annual crops, resulting in socio-economic and environmental benefits. The aim of this study was to compare delimited MZ, using crop productivity data, with delimited MZ using the NDVI obtained from satellite images in areas under a no-tillage system. The study was carried out in three areas located in the state of Rio Grande do Sul, Brazil. Three crop productivity maps, from 2009 to 2015, were used for each area, whereby the NDVI was calculated for each crop productivity map using images from the Landsat series of satellites. Descriptive and geostatistical analysis were conducted to determine the productivity and NDVI data. The MZ were then delimited using the fuzzy c-means algorithm. Spearman's correlation matrix was used to compare the methodologies used for delimiting the MZ. The MZ based on NDVI calculated from the satellite images correlated with the MZ based on crop productivity data (0.48 r 0.61), suggesting that the NDVI can replace or be complementary to productivity data in delimiting MZ for annual cropping systems.

Using Deep Learning and Low-Cost RGB and Thermal Cameras to Detect Pedestrians in Aerial Images Captured by Multirotor UAV.

The use of Unmanned Aerial Vehicles (UAV) has been increasing over the last few years in many sorts of applications due mainly to the decreasing cost of this technology. One can see the use of the UAV in several civilian applications such as surveillance and search and rescue. Automatic detection of pedestrians in aerial images is a challenging task. The computing vision system must deal with many sources of variability in the aerial images captured with the UAV, e.g., low-resolution images of pedestrians, images captured at distinct angles due to the degrees of freedom that a UAV can move, the camera platform possibly experiencing some instability while the UAV flies, among others. In this work, we created and evaluated different implementations of Pattern Recognition Systems (PRS) aiming at the automatic detection of pedestrians in aerial images captured with multirotor UAV. The main goal is to assess the feasibility and suitability of distinct PRS implementations running on top of low-cost computing platforms, e.g., single-board computers such as the Raspberry Pi or regular laptops without a GPU. For that, we used four machine learning techniques in the feature extraction and classification steps, namely Haar cascade, LBP cascade, HOG + SVM and Convolutional Neural Networks (CNN). In order to improve the system performance (especially the processing time) and also to decrease the rate of false alarms, we applied the Saliency Map (SM) and Thermal Image Processing (TIP) within the segmentation and detection steps of the PRS. The classification results show the CNN to be the best technique with 99.7% accuracy, followed by HOG + SVM with 92.3%. In situations of partial occlusion, the CNN showed 71.1% sensitivity, which can be considered a good result in comparison with the current state-of-the-art, since part of the original image data is missing. As demonstrated in the experiments, by combining TIP with CNN, the PRS can process more than two frames per second (fps), whereas the PRS that combines TIP with HOG + SVM was able to process 100 fps. It is important to mention that our experiments show that a trade-off analysis must be performed during the design of a pedestrian detection PRS. The faster implementations lead to a decrease in the PRS accuracy. For instance, by using HOG + SVM with TIP, the PRS presented the best performance results, but the obtained accuracy was 35 percentage points lower than the CNN. The obtained results indicate that the best detection technique (i.e., the CNN) requires more computational resources to decrease the PRS computation time. Therefore, this work shows and discusses the pros/cons of each technique and trade-off situations, and hence, one can use such an analysis to improve and tailor the design of a PRS to detect pedestrians in aerial images.

Utilização de um veículo aéreo não-tripulado em atividades de imageamento georeferenciado / On the use of unmanned aerial vehicle for acquisition of georrefecend image data

Este trabalho teve por objetivo desenvolver subsídios para propor um procedimento alternativo para aquisição de dados, telemetria, monitoramento e georeferenciamento das atividades agrícolas, por meio da acoplagem de equipamentos eletrônicos a um Veículo Aéreo Não-Tripulado (VANT). Para tal, foi desenvolvido um VANT na Universidade Federal de Santa Maria, no qual foram acoplados equipamentos para a coleta de imagens e a aquisição de pontos de referência. O equipamento desenvolvido mostrou imenso potencial para ser utilizado como ferramenta auxiliar na localização de áreas com falhas de germinação, na infestação de invasoras e no mapeamento de área. O maior entrave a um melhor emprego deste equipamento refere-se à baixa qualidade das imagens geradas, mostrando a necessidade de reavaliações do aparato utilizado.

The aim of this study consisted in developing and testing an alternative procedure for data acquisition, telemetry, monitoring and geo-referencing in agricultural fields. The proposed approach was implemented by placing dedicated electronic gear onboard Unmanned Aerial Vehicles (UAV). For this purpose an UAV was assembled at the Federal University in Santa Maria, Brazil and equipped with the required hardware for image and control points acquisition. Tests have shown that the proposed approach can be regarded as a valuable tool to detect areas affected by faulty germination, weed infestation and mapping in general. The tests have also shown that poor quality of the acquired image data was the main drawback in the equipment onboard the UAV, pointing to the need to reevaluate the system with regard to this particular aspect.

Utilização de um veículo aéreo não-tripulado em atividades de imageamento georeferenciado

The aim of this study consisted in developing and testing an alternative procedure for data acquisition, telemetry, monitoring and geo-referencing in agricultural fields. The proposed approach was implemented by placing dedicated electronic gear onboard Unmanned Aerial Vehicles (UAV). For this purpose an UAV was assembled at the Federal University in Santa Maria, Brazil and equipped with the required hardware for image and control points acquisition. Tests have shown that the proposed approach can be regarded as a valuable tool to detect areas affected by faulty germination, weed infestation and mapping in general. The tests have also shown that poor quality of the acquired image data was the main drawback in the equipment onboard the UAV, pointing to the need to reevaluate the system with regard to this particular aspect.

Este trabalho teve por objetivo desenvolver subsídios para propor um procedimento alternativo para aquisição de dados, telemetria, monitoramento e georeferenciamento das atividades agrícolas, por meio da acoplagem de equipamentos eletrônicos a um Veículo Aéreo Não-Tripulado (VANT). Para tal, foi desenvolvido um VANT na Universidade Federal de Santa Maria, no qual foram acoplados equipamentos para a coleta de imagens e a aquisição de pontos de referência. O equipamento desenvolvido mostrou imenso potencial para ser utilizado como ferramenta auxiliar na localização de áreas com falhas de germinação, na infestação de invasoras e no mapeamento de área. O maior entrave a um melhor emprego deste equipamento refere-se à baixa qualidade das imagens geradas, mostrando a necessidade de reavaliações do aparato utilizado.

Utilização de um veículo aéreo não-tripulado em atividades de imageamento georeferenciado

The aim of this study consisted in developing and testing an alternative procedure for data acquisition, telemetry, monitoring and geo-referencing in agricultural fields. The proposed approach was implemented by placing dedicated electronic gear onboard Unmanned Aerial Vehicles (UAV). For this purpose an UAV was assembled at the Federal University in Santa Maria, Brazil and equipped with the required hardware for image and control points acquisition. Tests have shown that the proposed approach can be regarded as a valuable tool to detect areas affected by faulty germination, weed infestation and mapping in general. The tests have also shown that poor quality of the acquired image data was the main drawback in the equipment onboard the UAV, pointing to the need to reevaluate the system with regard to this particular aspect.

Este trabalho teve por objetivo desenvolver subsídios para propor um procedimento alternativo para aquisição de dados, telemetria, monitoramento e georeferenciamento das atividades agrícolas, por meio da acoplagem de equipamentos eletrônicos a um Veículo Aéreo Não-Tripulado (VANT). Para tal, foi desenvolvido um VANT na Universidade Federal de Santa Maria, no qual foram acoplados equipamentos para a coleta de imagens e a aquisição de pontos de referência. O equipamento desenvolvido mostrou imenso potencial para ser utilizado como ferramenta auxiliar na localização de áreas com falhas de germinação, na infestação de invasoras e no mapeamento de área. O maior entrave a um melhor emprego deste equipamento refere-se à baixa qualidade das imagens geradas, mostrando a necessidade de reavaliações do aparato utilizado.