Blog - August 2020

Convolutional Neural Networks (CNN) have been being widely employed to solve the challenging remote sensing task of aerial scene classification. Nevertheless, it is not straightforward to find single CNN models that can solve all aerial scene classification tasks, allowing the development of a better alternative, which is to fuse CNN-based classifiers into an ensemble. However, an appropriate choice of the classifiers that will belong to the ensemble is a critical factor, as it is unfeasible to employ all the possible classifiers in the literature. Therefore, this work proposes a novel framework based on meta-heuristic optimization for creating optimized ensembles in the context of aerial scene classification. The experimental results were performed across nine meta-heuristic algorithms and three aerial scene literature datasets, being  compared in terms of effectiveness (accuracy), efficiency (execution time), and behavioral performance in different scenarios.  Our results suggest that the Univariate Marg...

Tropical forest conservation is a current issue of social and ecological relevance, due to their important role in the global ecosystem. Tropical forests have a great diversity of fauna and flora, act in the regulation of climate and rainfall, absorb large amounts of carbon dioxide, and serve as a home for countless indigenous peoples. Unfortunately, for years, thousands of hectares have been deforested and degraded in the Amazon rainforest. Government programs and private initiatives have emerged with the aim of mitigating the effects of the caused damage through monitoring and inspection. Most monitoring programs involve the inspection of remote sensing images by specialists, generally counting on the support of computational resources for automatic detection of patterns. This thesis proposes a novel %deforestation detection system called ForestEyes, which aims to detect deforestation in tropical forests based on Citizen Science and Machine Learning approaches. ForestEyes project uses non-specialist volu...

In this paper, entitled "The Good, the Bad, and the Ugly: Neural Networks Straight from JPEG", we investigate whether the spatial resolution and JPEG quality affects the performance of CNNs fed with DCT coefficients. More specifically, we studied several aspects of a state-of-the-art CNN recently proposed by Gueguen et al. [1], which is a modified version of the ResNet-50 architecture [2]. Despite the speed-up obtained by partially decoding JPEG images, their architectural changes raised the computation complexity and the number of parameters of the network. To alleviate these drawbacks, we propose a Frequency Band Selection (FBS) technique to select the most relevant DCT coefficients before feeding them to the network. A comparison among the original ResNet-50 network [2], the modified ResNet-50 network proposed by Gueguen et al. [1], and our improved version with FBS is presented below. Original ResNet-50 network [2] ResNet-50 using DCT as input [1]...