Mauricio Braga de Paula

Bio: Mauricio Braga de Paula is an academic researcher from Universidade Federal de Pelotas. The author has contributed to research in topics: Context (language use) & Advanced driver assistance systems. The author has an hindex of 2, co-authored 7 publications receiving 74 citations. Previous affiliations of Mauricio Braga de Paula include University of Rio Grande.

Automatic Detection and Classification of Road Lane Markings Using Onboard Vehicular Cameras

Abstract: This paper presents a new approach for road lane classification using an onboard camera. Initially, lane boundaries are detected using a linear–parabolic lane model, and an automatic on-the-fly camera calibration procedure is applied. Then, an adaptive smoothing scheme is applied to reduce noise while keeping close edges separated, and pairs of local maxima–minima of the gradient are used as cues to identify lane markings. Finally, a Bayesian classifier based on mixtures of Gaussians is applied to classify the lane markings present at each frame of a video sequence as dashed, solid, dashed solid, solid dashed, or double solid. Experimental results indicate an overall accuracy of over 96% using a variety of video sequences acquired with different devices and resolutions.

Real-Time Detection and Classification of Road Lane Markings

Abstract: This paper presents a method for detection and recognition of road lane markings using an uncalibrated onboard camera. Initially, lane boundaries are detected based on a linear parabolic model. Then, we build a simple model to represent pixels related to the pavement, and explore this model to estimate pixels related to lane markings. A set of features is computed based on the detected lane markings, and a cascade of binary classifiers is adopted to distinguish five types of markings: dashed, dashed-solid, solid-dashed, single-solid and double-solid. Experimental results show that the proposed method presents good classification results under a variety of situations (shadows, varying illumination, etc.).

Curso de Licenciatura em Matemática a Distância: relato de Experiência

Abstract: This article presents the implementation of a graduation course in Mathematics offered in the modality of distance education by the Federal University of Pelotas, state of Rio Grande do Sul. It discusses aspects related to the participation of students and the course of the disciplines in the three cities where the course is held. Moreover, this report presents how students and tutors were qualified for the course and the way students were welcome aiming to motivate them for the collaborative learning experience. Finally, it presents aspects related to the administrative structure utilized to attend students needs, as well as the management of the course itself.

Brazilian Traffic Signs Detection and Recognition in Videos Using CLAHE, HOG Feature Extraction and SVM Cascade Classifier with Temporal Coherence.

Abstract: Worldwide, traffic safety is a strong concern as traffic accidents are one of the leading causes of death. In this context, advanced driver assistance systems (ADAS) and autonomous vehicles are traffic management measures aimed at improving road safety and flow. Automatic detection and recognition of traffic signs are important for intelligent vehicles and ADAS systems. This work proposes a pipeline of digital image processing (DIP) techniques, machine learning (ML), and temporal coherence to perform the detection and recognition of Brazilian traffic signs in videos aiming an application for real-time systems to help in traffic safety and to reduce the number of fatal accidents. We are mainly interested in recognizing signs of speed limit group, no overtaking and obligatory passage, thus our detection considers the traffic sign with a circular shape and red border. For detection, the red color segmentation and the Hough transform are used to find circular regions that will be classified through the SVM algorithm in sign and not sign. For recognition of these signs, the support vector machines (SVM) are used. For speed limit signs the thresholding and contours are used to segment the digits for later classification. Our proposed method achieved an accuracy of 0.82 in detection, an increase of 18% in the number of recognized frames and 0.96 in the recognition stage using temporal coherence.

End-To-End Ego Lane Estimation Based on Sequential Transfer Learning for Self-Driving Cars

Abstract: Autonomous cars establish driving strategies using the positions of ego lanes. The previous methods detect lane points and select ego lanes with heuristic and complex postprocessing with strong geometric assumptions. We propose a sequential end-to-end transfer learning method to estimate left and right ego lanes directly and separately without any postprocessing. We redefined a point-detection problem as a region-segmentation problem; as a result, the proposed method is insensitive to occlusions and variations of environmental conditions, because it considers the entire content of an input image during training. Also, we constructed an extensive dataset that is suitable for a deep neural network training by collecting a variety of road conditions, annotating ego lanes, and augmenting them systematically. The proposed method demonstrated improved accuracy and stability on input variations compared with a recent method based on deep learning. Our approach does not involve postprocessing, and is therefore flexible to change of target domain.

Lane Detection and Classification for Forward Collision Warning System Based on Stereo Vision

Abstract: This paper presents a lightweight stereo vision-based driving lane detection and classification system to achieve the ego-car’s lateral positioning and forward collision warning to aid advanced driver assistance systems (ADAS). For lane detection, we design a self-adaptive traffic lanes model in Hough Space with a maximum likelihood angle and dynamic pole detection region of interests (ROIs), which is robust to road bumpiness, lane structure changing while the ego-car’s driving and interferential markings on the ground. What’s more, this model can be improved with geographic information system or electronic map to achieve more accurate results. Besides, the 3-D information acquired by stereo matching is used to generate an obstacle mask to reduce irrelevant objects’ interfere and detect forward collision distance. For lane classification, a convolutional neural network is trained by using manually labeled ROI from KITTI data set to classify the left/right-side line of host lane so that we can provide significant information for lane changing strategy making in ADAS. Quantitative experimental evaluation shows good true positive rate on lane detection and classification with a real-time (15Hz) working speed. Experimental results also demonstrate a certain level of system robustness on variation of the environment.

A Fast Learning Method for Accurate and Robust Lane Detection Using Two-Stage Feature Extraction with YOLO v3.

Abstract: To improve the accuracy of lane detection in complex scenarios, an adaptive lane feature learning algorithm which can automatically learn the features of a lane in various scenarios is proposed. First, a two-stage learning network based on the YOLO v3 (You Only Look Once, v3) is constructed. The structural parameters of the YOLO v3 algorithm are modified to make it more suitable for lane detection. To improve the training efficiency, a method for automatic generation of the lane label images in a simple scenario, which provides label data for the training of the first-stage network, is proposed. Then, an adaptive edge detection algorithm based on the Canny operator is used to relocate the lane detected by the first-stage model. Furthermore, the unrecognized lanes are shielded to avoid interference in subsequent model training. Then, the images processed by the above method are used as label data for the training of the second-stage model. The experiment was carried out on the KITTI and Caltech datasets, and the results showed that the accuracy and speed of the second-stage model reached a high level.

A novel curve lane detection based on Improved River Flow and RANSA

Abstract: Accurate and robust lane detection, especially the curve lane detection, is the premise of a Lane Departure Warning System (LDWS) and a Forward Collision Warning System (FCWS). Lane detection on the structural roads under challenging scenarios such as the dashed lane markings and vehicle occlusion is a difficult task because of unreliable lane feature points. In this paper, a robust curve lane detection method based on the Improved River Flow (IRF) and the Random Sample Consensus (RANSAC) method is proposed to detect a curve lane under challenging conditions. The lane markings are grouped into a near vision field of a straight line and a far vision field of a curve line. The curve lanes are based on a Hyperbola-pair model. To determine the coefficient of curvature, a novel method is proposed based on the Improved River Flow method and the RANSAC method. In the new method, the Improved River Flow method is employed to search feature points in the far vision field guided by the results of detected straight lines in the near vision field or the curve lines from the last frame, which can connect dashed lane markings or obscured lane markings. So, it is robust on dashed lane markings and vehicle occlusion. Then, the RANSAC is utilized to calculate the curvature, which can eliminate noisy feature points obtained from the Improved River Flow. The experimental results show that the proposed method can robustly and accurately detect some challenging markings, such as the dashed lane markings and vehicle occlusion.

Low-Cost Curb Detection and Localization System Using Multiple Ultrasonic Sensors.

Abstract: Curb detection and localization systems constitute an important aspect of environmental recognition systems of autonomous driving vehicles. This is because detecting curbs can provide information about the boundary of a road, which can be used as a safety system to prevent unexpected intrusions into pedestrian walkways. Moreover, curb detection and localization systems enable the autonomous vehicle to recognize the surrounding environment and the lane in which the vehicle is driving. Most existing curb detection and localization systems use multichannel light detection and ranging (lidar) as a primary sensor. However, although lidar demonstrates high performance, it is too expensive to be used for commercial vehicles. In this paper, we use ultrasonic sensors to implement a practical, low-cost curb detection and localization system. To compensate for the relatively lower performance of ultrasonic sensors as compared to other higher-cost sensors, we used multiple ultrasonic sensors and applied a series of novel processing algorithms that overcome the limitations of a single ultrasonic sensor and conventional algorithms. The proposed algorithms consisted of a ground reflection elimination filter, a measurement reliability calculation, and distance estimation algorithms corresponding to the reliability of the obtained measurements. The performance of the proposed processing algorithms was demonstrated by a field test under four representative curb scenarios. The availability of reliable distance estimates from the proposed methods with three ultrasonic sensors was significantly higher than that from the other methods, e.g., 92.08% vs. 66.34%, when the test vehicle passed a trapezoidal-shaped road shoulder. When four ultrasonic sensors were used, 96.04% availability and 13.50 cm accuracy (root mean square error) were achieved.