No abstract

This paper presents an approach for road detection based on image segmentation. This segmentation is resulted from merging 2D and 3D image processing data from a stereo vision system. The 2D layer returns a matrix containing pixel's clusters based on the Watershed transform. Whereas the 3D layer return labels, that are classified by the V-Disparity technique, to free spaces, obstacles and non-classified area. Thus, a feature's descriptor for each cluster is composed with features from both layers. The road pattern recognition was performed by an artificial neural network, trained to obtain a final result from this feature's descriptor. The proposed work reports real experiments carried out in a challenging urban environment to illustrate the validity and application of this approach.

This paper presents an overview on the advances of watershed processing algorithms executed on GPU architecture. The programming model, memory hierarchy and restrictions are discussed, and its influence on image processing algorithms detailed. The recently proposed algorithms of watershed transform for GPU computation are examined and briefly described. Its implementations are analyzed in depth and evaluations are made to compare them both on the GPU, against a CPU version and on two different GPU cards

Being highly unsaturated, carotenoids are susceptible to isomerization and oxidation during the processing and storage of food. In the present study, the degradation of acyclic lycopene and dicyclic beta-carotene in low-moisture and aqueous model systems, as well as in lyophilized guava, during storage at ambient temperature, in the absence or presence of light, was investigated. Both carotenoids followed first order kinetics under the various conditions investigated. Lycopene degraded much faster than beta-carotene in all the model systems. In a comparison of lycopene isolated from guava, tomato, and watermelon, greater losses were observed with lycopene from tomato. Since the model system was identical in the 3 cases, these results indicated that other compounds from the food sources, co-extracted with lycopene, might have influenced the oxidation. Light consistently and strongly promoted degradation under all conditions studied. The susceptibility of lycopene to degradation was much less in lyophilized guava than in the model systems, showing the marked protective influence of the food matrix. Loss of beta-carotene, found at a concentration of about 18 times lower than lycopene, was only slightly lower than that of lycopene in lyophilized guava, indicating that the effect of matrix and/or the initial concentration overshadowed the structural influence.

No abstract

Autonomous robots have motivated researchers from different groups due to the challenge that it represents. Many applications for control of autonomous platform are being developed and one important aspect is the excess of information, frequently redundant, that imposes a great computational cost in data processing. Taking into account the temporal coherence between consecutive frames, we have proposed a set of tools based on Pearson's Correlation Coefficient (PCC): (i) a Discarding Criteria methodology was proposed and applied as (ii) a Dynamic Power Management solution; (iii) an environment observer method based on PCC selects automatically only the Regions-Of-Interest; and taking place in the obstacle avoidance context, (iv) a method for Collision Risk Estimation was proposed for vehicles in dynamic and unknown environments.Applying the PCC to these tasks has not been done yet, making the concepts unique. All these solutions have been evaluated from real data obtained by experimental vehicles.

The navigation of an autonomous vehicle is a highly complex task and the dynamic environment is used as a source for reasoning. Road detection is a major issue in autonomous systems and advanced driving assistance systems applied for inner-city. Uncertainty may arise in environments with unmarked or weakly marked roads or poor lightning conditions. Moreover, when a common benchmark is not used, it is hard to decide which approach performs better on the road detection problem. This paper introduces a comprehensive performance analysis of two road recognition approaches using the urban Kitti-road benchmark. The first approach makes the extraction of a feature set based on statistical measures of 2D and 3D information from each superpixel. An Artificial Neural Network is used to detect the road pattern. The second approach extracts the feature set based on a multi-normalized histogram of Textons and Disptons for each superpixel. This feature set is used as a source for a Joint Boosting algorithm to model the road pattern. The proposed work presents a detailed evaluation highliting the pros and cons of each approach.

The design of the robotic vehicle VILMA at UNICAMP is developed in-vehicle platform Fiat Punto. In addition to a set of sensors, actuators, mechanism and components (hardware and/or software), new technologies should be developed in support of Automation, Control, Perception, Localization and Navigation. This work presents the design and simulation of path tracking control using model predictive control (MPC) which attempts to exploit the characteristics of the structured environment where the future path is previously known. The model for design the controller is based in a single tracking model of the vehicle and in a model of the steering which the state variables are observed by the Extended Kalman Filter (EKF). Finally, it is explained how the path is smoothed generating an arc between the points and making an optimization process by the gradient algorithm.Index Terms-Autonomous Vehicle, Path Tracking, Model Predictive Control, VDA test 2014 Joint Conference on Robotics: SBR-LARS Robotics Symposium and Robocontrol 978-1-4799-6711-7/14 $31.00