Technical session talks from ICRA 2012
TechTalks from event: Technical session talks from ICRA 2012
Conference registration code to access these videos can be accessed by visiting this link: PaperPlaza. Step-by-step to access these videos are here: step-by-step process .
Why some of the videos are missing? If you had provided your consent form for your video to be published and still it is missing, please contact email@example.com
A Game Theoretical Approach to Finding Optimal Strategies for Pursuit Evasion in Grid EnvironmentsPursuit evasion problems, in which evading targets must be cleared from an environment, are encountered in surveillance and search and rescue applications. Several works have addressed variants of this problem in order to study strategies for the pursuers. As a common trait, many of these works present results in the general form: given some assumptions on the environment, on the pursuers, and on the evaders, upper and lower bounds are calculated for the time needed for (the probability of, the resources needed for, ...) clearing the environment. The question ''what is the optimal strategy for a given pursuer in a given environment to clear a given evader?'' is left largely open. In this paper, we propose a game theoretical framework that contributes in finding an answer to the above question in a version of the pursuit evasion problem in which the evader enters and exits a grid environment and the pursuer has to intercept it along its path. We adopt a criterion for optimality related to the probability of capture. We experimentally evaluate the proposed approach in simulated settings and we provide some hints to generalize the framework to other versions of the pursuit evasion problem.
Online Patrolling Using Hierarchical Spatial RepresentationsUnmanned Aerial Vehicles (UAVs) can be an effective technology for security applications involving patrolling and search missions. Defining online patrolling strategies for UAVs presents challenges related both to classical patrolling, as periodic monitoring of the environment, and to search, as accurate localization and identification of the mission-related activities. In this paper, we deal with this problem considering probabilistic intrusions and a variable resolution sensing model that naturally applies to the domain of UAVs. We present three online single--robot patrolling strategies exploiting a variable resolution paradigm to represent the environment that has recently shown promising results for search problems. The approach uses a hierarchical representation based on probabilistic quadtrees that allows UAVs to tradeoff sensing accuracy with sensing area. The model is extended by adding stochastic arrivals of intruders in space and time. Obtained results validate this approach for online patrolling against approaches based on uniform grids.
Laser-Based Intelligent Surveillance and Abnormality Detection in Extremely Crowded ScenariosAbnormal activity detection plays a crucial role in surveillance applications, and a surveillance system that can perform robustly in the extremely crowded area has become an urgent need for public security. In this paper, we propose a novel laser-based system which can simultaneously perform the tracking, semantic scene learning and abnormality detection in the large and crowded environment. In our system, a novel abnormality detection model is proposed, and it considers and combines various factors that will influence human activity. Moreover, this model intensively investigate the relationship between pedestrians' social behaviors and their walking scenarios. We successfully applied the proposed system to the JR subway station of Tokyo, which can cover a 60*35m area, robustly track more than 180 targets at the same time and simultaneously perform the online semantic scene learning and abnormality detection with no human intervention.
Strong Shadow Removal Via Patch-Based Shadow Edge DetectionDetecting objects in shadows is a challenging task in computer vision. For example, in clear path detection application, strong shadows on the road confound the detection of the boundary between clear path and obstacles, making clear path detection algorithms less robust. Shadow removal, relies on the classification of edges as shadow edges or non-shadow edges. We present an algorithm to detect strong shadow edges, which enables us to remove shadows. By analyzing the patch-based characteristics of shadow edges and non-shadow edges (e.g., object edges), the proposed detector can discriminate strong shadow edges from other edges in images by learning the distinguishing characteristics. In addition, spatial smoothing is used to further improve shadow edge detection. Numerical experiments show convincing results that shadows on the road are either removed or attenuated with few visual artifacts, which benefits the clear path detection. In addition, we show that the proposed method outperforms the state-of-art algorithms in different conditions.
Integrated Probabilistic Generative Model for Detecting Smoke on Visual ImagesEarly fire detection is crucial to minimise damage and save lives. Video surveillance smoke detectors do not suffer from transport delays and can cover large areas. The smoke detection on images is, however, a difficult problem due the variability of smoke density, lighting conditions, background clutter, and unstable patterns. In order to solve this problem, we propose a novel unsupervised object classifier. Single visual features are classified using a model that simultaneously creates a codebook and categorises the smoke using a bag-of-words paradigm based on LDA model. Our algorithm can also tell the amount of smoke present on the image. Multiple image sequences from different cameras are used to show the viability of the proposed approach. Our experiments show that the model generalises well for different cameras, perspectives and scales.
Localization in Indoor Environments by Querying Omnidirectional Visual Maps Using Perspective ImagesThis article addresses the problem of image-based localization in a indoor environment. The localization is achieved by querying a database of omnidirectional images that constitutes a detailed visual map of the building where the robot operates. Omnidirectional cameras have the advantage, when compared to standard perspectives, of capturing in a single frame the entire visual content of a room. This, not only speeds up the process of acquiring data for creating the map, but also favors scalability by significantly decreasing the size of the database. The problem is that omnidirectional images have strong non-linear distortion, which leads to poor retrieval results when the query images are standard perspectives. This paper reports for the first time thorough experiments in using perspectives to index a database of para-catadioptric images for the purpose of robot localization. We propose modifications to the SIFT algorithm that significantly improve point matching between the two types of images with positive impact in the recognition based in visual words. We also compare the classical bags-of-words against the recent framework of visual-phrases, showing that the latter outperforms the former.