Abstract

Abstract
Recent advances in visual motion detection and interpretation have made possible the rising of new robotic systems for autonomous and active surveillance. In this line of research, the current work discusses motion perception by proposing a novel technique that analyzes dense flow fields and distinguishes several regions with distinct motion models. The method is called Wise Optical Flow Clustering (WOFC) and extracts the moving objects by performing two consecutive operations: evaluating and resetting. Motion properties of the flow field are retrieved and described in the evaluation phase, which provides high level information about the spatial segmentation of the flow field. During the resetting operation, these properties are combined and used to feed a guided segmentation approach. The WOFC requires information about the number of motion models and, therefore, this paper introduces a model selection method based on a Bayesian approach that balances the model's fitness and complexity. It combines the correlation of a histogram-based analysis with the decay ratio of the normalized entropy criterion. This approach interprets the flow field and gives an estimative about the number of moving objects. The experiments conducted in a realistic environment have proved that the WOFC presents several advantages that meet the requirements of common robotic and surveillance applications: is computationally efficient and provides a pixel-wise segmentation, comparatively to other state-of-the-art methods.

Abstract

Abstract
Autonomous underwater vehicles (AUVs) are increasingly being used to perform search operations but its capabilities are limited by the efficiency of the planning process. The objective of the paper is to propose new survey planning methods for AUVs. In particular, the problem of multi-objective search mission planning with an AUV navigating in known or unknown 3D environments is studied. The vehicle should completely cover the operating area while maximizing the probability of detecting the targets and minimizing the required energy and time to complete the mission. The approach presented here differs from other CPP methods in that paths for coverage are generated based on a coverage map that is actively maintained as the vehicle executed its mission. Our replanning approach borrows ideas from case-based reasoning (CBR) in which old problem and solution information helps solve a new problem. The resulting combination takes advantage of both paradigms where our evolutionary approach in conjunction with an artificial neural network (ANN), presented earlier, delivers robustness and adaptive learning while the case-based component speeds up the replanning process. The experiments show that the online algorithm was able to successfully replan missions in varied scenarios and guarantee full area coverage while minimizing resource consumption.

Abstract
It is commonly accepted that one of the most important factors for assuring the high performance of an electrical network is the surveillance and the respective preventive maintenance. From a long time ago that TSOs and DSOs incorporate in their maintenance plans the surveillance of the grid, where is included the aerial power lines inspection. Those inspections started by human patrol, including structure climbing when needed and later were substituted by helicopters with powerful sensors and specialised technicians. More recently the Unmanned Aerial Vehicles (UAV) technology has been used, taking advantage of its numerous advantages. This paper addresses the problem of improving the real-time perception capabilities of UAVs for endowing them with capabilities for safe and robust autonomous and semi-autonomous operations. It presents a new vision based power line detection algorithm denoted by PLineD, able to improve the detection robustness even in the presence of image with background noise. The algorithm is tested in real outdoor images of a dataset with multiple backgrounds and weather conditions. The experimental results demonstrate that the proposed approach is effective and able to implemented in real-time image processing pipeline.

Abstract
The development of vision-based navigation systems for mobile robotics applications in outdoor scenarios is a very challenging problem due to frequent changes in contrast and illumination, image blur, pixel noise, lack of image texture, low image overlap and other effects that lead to ambiguity in the interpretation of motion from image data. To mitigate the problems arising from multiple possible interpretations of the data in outdoor stereo egomotion, we present a fully probabilistic method denoted as probabilistic stereo egomotion transform. Our method is capable of computing 6-degree of freedom motion parameters solely based on probabilistic correspondences without the need to track or commit key point matches between two consecutive frames. The use of probabilistic correspondence methods allows to maintain several match hypothesis for each point, which is an advantage when ambiguous matches occur (which is the rule in image feature correspondence problems), because no commitment is made before analysing all image information. Experimental validation is performed in simulated and real outdoor scenarios in the presence of image noise and image blur. Comparison with other current state-of-the-art visual motion estimation method is also provided. Our method is capable of significant reduction of estimation errors mainly in harsh conditions of noise and blur.