Convolutional neural networks (CNNs) have shown great potential in different real word application. Defining a suitable CNN architecture is vital for obtaining good performance. In this work we propose a random forest surrogate combined with two bio-inspired optimization algorithm, genetic algorithms (GA) and particle swarm optimization (PSO) used to find good CNN fully connected layer architecture and hyperparameters for three state of the art CNNs: VGG-16, Resnet-50 and Densenet-201. The proposed model is used to classify breast thermography images from the DMR-IR database in order to find whether or not the patient has cancer. The proposed model improved F1-score from 0.92 to 1 for the Densenet using the GA and also Resnet from 0.85 of F1-score to 0.92 using the PSO. Moreover, the surrogate model also helped reducing training time.

Breast cancer is a disease that affects many women throughout the world. It is the second most common type of cancer. The early diagnosis of the disease is relevant for increasing the chances of the patient recovering. Thermography is a promising technique that might be used to help the early diagnosis of breast cancer. In this work, we use three state of the art CNNs (VGG-16, Densenet201, and Resnet50) combined with transfer learning to classify static thermography images (sick and healthy). In our experiments, the best results have an F1-score of 0.92, 91.67% for accuracy, 100% for sensitivity, and 83.3% for specificity obtained with the Densenet using 38 static images for each class.

The recent precision increase in image-based depth estimation encourages to use this type of data for mapping. Recent work proposes different approaches to deal with the problem of occlusion generated by different scene perspectives of stereo cameras. However, there is less attention to depth estimation and inpainting for object removal and object occlusion. In this paper, we study recent inpainting approaches for RGB images and apply these methods on depth maps. We propose a Generative Adversarial Network (GAN) for depth feature extraction to estimate the depth inside a masked area, in order to remove objects on disparity images. Our results show that using depth features on the loss function and on the network architecture, increase the result precision and give to the generated image a depth distribution close to the real data. Our main contribution is a GAN, which estimates depth information in a masked area inside a disparity image.

The detection of failures (DF) in coffee crops is fundamental in evaluating product quality and the optimal occupation of planted areas. The use of unmanned aerial vehicles (UAVs) in precision agriculture has great potential as a tool to analyze critical parameters in cultivation, among them the detection of planting failures. This letter presents a novel methodology for DF from aerial images, obtained using a UAV capable of collecting high-resolution RGB images. The proposed approach uses mathematical morphology operators to detect failures over planted areas and returns both the individual positions of these failures and total failure length (sum of empty spaces between plants), thus facilitating decision making for further actions. Results show that the proposed DF method is reliable for accurately identifying failures over rows of planted coffee crops.

One of the challenges in precision agriculture is the detection of diseased crops in agricultural environments. This paper presents a methodology to detect the Ceratocystis wilt disease in Eucalyptus crops. An unmanned aerial vehicle is used to obtain high-resolution RGB images of a predefined area. The methodology enables the extraction of visual features from image regions and uses several supervised machine learning (ML) techniques to classify regions into three classes: ground, healthy and diseased plants. Several learning techniques were compared using data obtained from a commercial Eucalyptus plantation. Experimental results show that the GP learning model is more reliable than the other learning methods for accurately identifying diseased trees.

A key challenge for long-term autonomy is to enable a robot to automatically model properties of the environment while actively searching for better decisions to accomplish its task. This amounts to the problem of exploration-exploitation in the context of active perception. This paper addresses active perception and presents a technique to incrementally model the roughness of the terrain a robot navigates on while actively searching for waypoints that reduce the overall vibration experienced during travel. The approach employs Gaussian processes in conjunction with Bayesian optimisation for decision making. The algorithms are executed in real-time on the robot while it explores the environment. We present experiments with an outdoor vehicle navigating over several types of terrains demonstrating the properties and effectiveness of the approach.