Performance Assessment of Object Detection Models Trained with Synthetic Data: A Case Study on Electrical Equipment Detection.

This paper explores a data augmentation approach for images of rigid bodies, particularly focusing on electrical equipment and analogous industrial objects. By leveraging manufacturer-provided datasheets containing precise equipment dimensions, we employed straightforward algorithms to generate synthetic images, permitting the expansion of the training dataset from a potentially unlimited viewpoint. In scenarios lacking genuine target images, we conducted a case study using two well-known detectors, representing two machine-learning paradigms: the Viola-Jones (VJ) and You Only Look Once (YOLO) detectors, trained exclusively on datasets featuring synthetic images as the positive examples of the target equipment, namely lightning rods and potential transformers. Performances of both detectors were assessed using real images in both visible and infrared spectra. YOLO consistently demonstrates F1 scores below 26% in both spectra, while VJ's scores lie in the interval from 38% to 61%. This performance discrepancy is discussed in view of paradigms' strengths and weaknesses, whereas the relatively high scores of at least one detector are taken as empirical evidence in favor of the proposed data augmentation approach.

Latent Space Representations for Marker-Less Realtime Hand-Eye Calibration.

Marker-less hand-eye calibration permits the acquisition of an accurate transformation between an optical sensor and a robot in unstructured environments. Single monocular cameras, despite their low cost and modest computation requirements, present difficulties for this purpose due to their incomplete correspondence of projected coordinates. In this work, we introduce a hand-eye calibration procedure based on the rotation representations inferred by an augmented autoencoder neural network. Learning-based models that attempt to directly regress the spatial transform of objects such as the links of robotic manipulators perform poorly in the orientation domain, but this can be overcome through the analysis of the latent space vectors constructed in the autoencoding process. This technique is computationally inexpensive and can be run in real time in markedly varied lighting and occlusion conditions. To evaluate the procedure, we use a color-depth camera and perform a registration step between the predicted and the captured point clouds to measure translation and orientation errors and compare the results to a baseline based on traditional checkerboard markers.

Denoising digital breast tomosynthesis projections using deep learning with synthetic data as training set.

Purpose: Image denoising based on deep neural networks (DNN) needs a big dataset containing digital breast tomosynthesis (DBT) projections acquired in different radiation doses to be trained, which is impracticable. Therefore, we propose extensively investigating the use of synthetic data generated by software for training DNNs to denoise DBT real data. Approach: The approach consists of generating a synthetic dataset representative of the DBT sample space by software, containing noisy and original images. Synthetic data were generated in two different ways: (a) virtual DBT projections generated by OpenVCT and (b) noisy images synthesized from photography regarding noise models used in DBT (e.g., Poisson-Gaussian noise). Then, DNN-based denoising techniques were trained using a synthetic dataset and tested for denoising physical DBT data. Results were evaluated in quantitative (PSNR and SSIM measures) and qualitative (visual analysis) terms. Furthermore, a dimensionality reduction technique (t-SNE) was used for visualization of sample spaces of synthetic and real datasets. Results: The experiments showed that training DNN models with synthetic data could denoise DBT real data, achieving competitive results to traditional methods in quantitative terms but showing a better balance between noise filtering and detail preservation in a visual analysis. T-SNE enables us to visualize if synthetic and real noises are in the same sample space. Conclusion: We propose a solution for the lack of suitable training data to train DNN models for denoising DBT projections, showing that we just need the synthesized noise to be in the same sample space as the target image.

Nanoparticle Detection on SEM Images Using a Neural Network and Semi-Synthetic Training Data.

Processing images represents a necessary step in the process of analysing the information gathered about nanoparticles after characteristic material samples have been scanned with electron microscopy, which often requires the use of image processing techniques or general purpose image manipulation software to carry out tasks such as nanoparticle detection and measurement. In recent years, the use of networks has been successfully implemented to detect and classify electron microscopy images as well as the objects within them. In this work, we present four detection models using two versions of the YOLO neural network architectures trained to detect cubical and quasi-spherical particles in SEM images; the training datasets are a mixture of real images and synthetic ones generated by a semi-arbitrary method. The resulting models were capable of detecting nanoparticles in images different than the ones used for training and identifying them in some cases as the close proximity between nanoparticles proved a challenge for the neural networks in most situations.

An Augmented Reality Periscope for Submarines with Extended Visual Classification.

Submarines are considered extremely strategic for any naval army due to their stealth capability. Periscopes are crucial sensors for these vessels, and emerging to the surface or periscope depth is required to identify visual contacts through this device. This maneuver has many procedures and usually has to be fast and agile to avoid exposure. This paper presents and implements a novel architecture for real submarine periscopes developed for future Brazilian naval fleet operations. Our system consists of a probe that is connected to the craft and carries a 360 camera. We project and take the images inside the vessel using traditional VR/XR devices. We also propose and implement an efficient computer vision-based MR technique to estimate and display detected vessels effectively and precisely. The vessel detection model is trained using synthetic images. So, we built and made available a dataset composed of 99,000 images. Finally, we also estimate distances of the classified elements, showing all the information in an AR-based interface. Although the probe is wired-connected, it allows for the vessel to stand in deep positions, reducing its exposure and introducing a new way for submarine maneuvers and operations. We validate our proposal through a user experience experiment using 19 experts in periscope operations.

Artificial Mercosur license plates dataset.

Mercosur (a.k.a. Mercosul) is a trade bloc comprising five South American countries. In 2018, a unified Mercosur license plate model was rolled out. Access to large volumes of ground truth Mercosur license plates with sufficient presentation variety is a significant challenge for training supervised models for license plate detection (LPD) in automatic license plate recognition (ALPR) systems. To address this problem, a Mercosur license plate generator was developed to generate artificial license plate images meeting the new standard with sufficient variety for ALPR training purposes. This includes images with variation due to occlusions and environmental conditions. An embedded system was developed for detecting legacy license plates in images of real scenarios and overwriting these with artificially generated Mercosur license plates. This data set comprises 3,829 images of vehicles with synthetic license plates that meet the new Mercosur standard in real scenarios, and equivalent number of text files containing label information for the images, all organized in a CSV file with compiled image file paths and associated labels.