Alberto F. De Souza

Facial expression recognition with Convolutional Neural Networks: Coping with few data and the training sample order

Facial expression recognition has been an active research area in the past 10 years, with growing application areas including avatar animation, neuromarketing and sociable robots. The recognition of facial expressions is not an easy problem for machine learning methods, since people can vary significantly in the way they show their expressions. Even images of the same person in the same facial expression can vary in brightness, background and pose, and these variations are emphasized if considering different subjects (because of variations in shape, ethnicity among others). Although facial expression recognition is very studied in the literature, few works perform fair evaluation avoiding mixing subjects while training and testing the proposed algorithms. Hence, facial expression recognition is still a challenging problem in computer vision. In this work, we propose a simple solution for facial expression recognition that uses a combination of Convolutional Neural Network and specific image pre-processing steps. Convolutional Neural Networks achieve better accuracy with big data. However, there are no publicly available datasets with sufficient data for facial expression recognition with deep architectures. Therefore, to tackle the problem, we apply some pre-processing techniques to extract only expression specific features from a face image and explore the presentation order of the samples during training. The experiments employed to evaluate our technique were carried out using three largely used public databases (CK+, JAFFE and BU-3DFE). A study of the impact of each image pre-processing operation in the accuracy rate is presented. The proposed method: achieves competitive results when compared with other facial expression recognition methods 96.76% of accuracy in the CK+ database it is fast to train, and it allows for real time facial expression recognition with standard computers. HighlightsA CNN based approach for facial expression recognition.A set of pre-processing steps allowing for a simpler CNN architecture.A study of the impact of each pre-processing step in the accuracy.A study for lowering the impact of the sample presentation order during training.High facial expression recognition accuracy (96.76%) with real time evaluation.

A Dataset for Improved RGBD-Based Object Detection and Pose Estimation for Warehouse Pick-and-Place

An important logistics application of robotics involves manipulators that pick-and-place objects placed in warehouse shelves. A critical aspect of this task corresponds to detecting the pose of a known object in the shelf using visual data. Solving this problem can be assisted by the use of an RGBD sensor, which also provides depth information beyond visual data. Nevertheless, it remains a challenging problem since multiple issues need to be addressed, such as low illumination inside shelves, clutter, texture-less and reflective objects as well as the limitations of depth sensors. This letter provides a new rich dataset for advancing the state-of-the-art in RGBD-based 3D object pose estimation, which is focused on the challenges that arise when solving warehouse pick-and-place tasks. The publicly available dataset includes thousands of images and corresponding ground truth data for the objects used during the first Amazon Picking Challenge at different poses and clutter conditions. Each image is accompanied with ground truth information to assist in the evaluation of algorithms for object detection. To show the utility of the dataset, a recent algorithm for RGBD-based pose estimation is evaluated in this letter. Given the measured performance of the algorithm on the dataset, this letter shows how it is possible to devise modifications and improvements to increase the accuracy of pose estimation algorithms. This process can be easily applied to a variety of different methodologies for object pose detection and improve performance in the domain of warehouse pick-and-place.

Automated multi-label text categorization with VG-RAM weightless neural networks

In automated multi-label text categorization, an automatic categorization system should output a label set, whose size is unknown a priori, for each document under analysis. Many machine learning techniques have been used for building such automatic text categorization systems. In this paper, we examine virtual generalizing random access memory weightless neural networks (VG-RAM WNN), an effective machine learning technique which offers simple implementation and fast training and test, as a tool for building automatic multi-label text categorization systems. We evaluated the performance of VG-RAM WNN on two real-world problems:, (i) categorization of free-text descriptions of economic activities and (ii) categorization of Web pages, and compared our results with that of the multi-label lazy learning approach (Multi-Label K-Nearest Neighbors, ML-KNN). Our experimental comparative analysis showed that, on average, VG-RAM WNN either outperforms ML-KNN or show similar categorization performance.

Large-scale mapping in complex field scenarios using an autonomous car

We present a mapping system for large-scale environments with changing features.We describe in a high level of detail a mapping algorithm for 3D-LiDAR.G-ICP was used for loop closure displacement calculation in GraphSLAM.Experiments were made with an autonomous vehicle in 3 real world environments. In this paper, we present an end-to-end framework for precise large-scale mapping with applications in autonomous driving. In special, the problem of mapping complex environments, with features changing from tree-lined streets to urban areas with dense traffic, is studied. The robotic car is equipped with an odometry sensor, a 3D LiDAR Velodyne HDL-32E, a IMU, and a low cost GPS, and the data generated by these sensors are integrated in a pose-based GraphSLAM estimator. A new strategy for identification and correction of odometry data using evolutionary algorithms is presented. This new strategy makes odometry data significantly more consistent with GPS. Loop closures are detected using GPS data, and GICP, a 3D point cloud registration algorithm, is used to estimate the displacement between the different travels over the same region. After path estimation, 3D LiDAR data is used to build an occupancy grid mapping of the environment. A detailed mathematical description of how occupancy evidence can be calculated from the point clouds is given, and a submapping strategy to handle memory limitations is presented as well. The proposed framework is tested in three real world environments with different sizes, and features: a parking lot, a university beltway, and a city neighborhood. In all cases, satisfactory maps were built, with precise loop closures even when the vehicle traveled long distances between them.

Face Recognition with VG-RAM Weightless Neural Networks

Virtual Generalizing Random Access Memory Weightless Neural Networks ( Vg-ram wnn ) are effective machine learning tools that offer simple implementation and fast training and test. We examined the performance of Vg-ram wnn on face recognition using a well known face database--the AR Face Database. We evaluated two Vg-ram wnn architectures configured with different numbers of neurons and synapses per neuron. Our experimental results show that, even when training with a single picture per person, Vg-ram wnn are robust to various facial expressions, occlusions and illumination conditions, showing better performance than many well known face recognition techniques.

Traffic sign recognition with VG-RAM Weightless Neural Networks

Virtual Generalizing Random Access Memory Weightless Neural Networks (VG-RAM WNN) is an effective machine learning technique that offers simple implementation and fast training and test. In this paper, we present a new approach for traffic sign recognition based on VG-RAM WNN. We evaluate its performance using the German Traffic Sign Recognition Benchmark (GTSRB), a large multi-class classification benchmark. Our experimental results showed that our VG-RAM WNN architecture for traffic sign recognition was able to rank at 4th position in the GTSRB evaluation system, with a recognition rate of 98.73%, and was overcome by only one automatic approach.

Image-based global localization using VG-RAM Weightless Neural Networks

Mapping and localization are fundamental problems in autonomous robotics. Autonomous robots need to know where they are in their area of operation to navigate through it and to perform activities of interest. In this paper, we propose an Image-Based Global Localization (VibGL) system that uses Virtual Generalizing Random Access Memory Weightless Neural Networks (VG-RAM WNN). For mapping, we employ a VG-RAM WNN that learns the world positions associated with the images captured along a trajectory. During the localization, new images from the trajectory are presented to the VG-RAM WNN, which outputs their positions in the world. We performed experiments with our VibGL system applied to the problem of localizing an autonomous car. Our experimental results show that the system is able to learn large maps (several kilometers in length) of real world environments and perform global localization with median pose precision of about 3m. Considering a tolerance of 10m VibGL is able to localize the car 95% of the time.

Fast learning and predicting of stock returns with virtual generalized random access memory weightless neural networks

We employ virtual generalized random access memory weightless neural networks, VG‐RAM WNN, for predicting future stock returns. We evaluated our VG‐RAM WNN stock predictor architecture in predicting future weekly returns of the Brazilian stock market and obtained the same error levels and properties of baseline autoregressive neural network predictors; however, our VG‐RAM WNN predictor runs 5000 times faster than autoregressive neural network predictors. This allowed us to employ VG‐RAM WNN predictors to build a high frequency trading system able to achieve a monthly return of approximately 35% in the Brazilian stock market. Copyright

A Model-Predictive Motion Planner for the IARA autonomous car

We present the Model-Predictive Motion Planner (MPMP) of the Intelligent Autonomous Robotic Automobile (IARA). IARA is a fully autonomous car that uses a path planner to compute a path from its current position to the desired destination. Using this path, the current position, a goal in the path and a map, IARAs MPMP is able to compute smooth trajectories from its current position to the goal in less than 50 ms. MPMP computes the poses of these trajectories so that they follow the path closely and, at the same time, are at a safe distance of occasional obstacles. Our experiments have shown that MPMP is able to compute trajectories that precisely follow a path produced by a Human driver (distance of 0.15 m in average) while smoothly driving IARA at speeds of up to 32.4 km/h (9 m/s).

Re-emission and satellite aerial maps applied to vehicle localization on urban environments

Vehicle localization in large-scale urban environments has been commonly addressed as a map-matching problem in the literature. Generally, the maps are 2D images of the world where each pixel covers a part of it. However, building maps for large-scale urban environments requires driving the vehicle along the desired path at least once. In order to simplify this task, in this work, we propose a new localization system that uses satellite aerial map-images available on the Internet to localize a vehicle in a complex urban environment. Satellite aerial map-images are compared against re-emission maps built from the infrared reflectance information of the vehicles LiDAR. Normalized Mutual Information (NMI) is used to compare re-emission and aerial map images. A Particle Filter Localization strategy is applied for vehicles localization. As a result, the system has an accuracy of 0.89m in a test course with 6.5km. Our system can be used continuously without losing track, and it works even in dark and partially occluded areas.