Abstract

Projector-Camera systems are extensively used for various applications in computer vision, immersive environments, visual servoing, etc. Due to gaps between neighboring pixels on the projector’s image plane and variations in scene depth, the mage projected onto a scene shows pixelation and blurring artifacts. In certain vision and graphics applications, it is desirable that a high quality composition of the scene and the projected image, excluding the artifacts, is captured, while retaining the scene characteristics. Localization of projected pixels can also help in dense estimation of scene shape. In this paper, we address the problem of localizing each of the projected pixels from a captured scene and restoring the captured image so that the pixelation and blurring artifacts of the projector are removed. We improve the quality of the captured image further by virtualizing a high resolution projector. i.e., we modify the captured image as if the scene were illuminated with a high-resolution projector. We propose robust solutions to these problems and demonstrate their effectiveness on scenes of different complexities.

Abstract

Constructing a high-resolution (HR) image from low resolution (LR) image(s) has been a very active research topic recently with focus shifting from multi-frames to learning based single-frame super-resolution (SR). Multi-frame R algorithms attempt the exact reconstruction of reality, but are limited to small magnification factors. Learning based SR algorithms learn the correspondences between LR and HR patches. Accurate replacements or revealing the exact underlying information is not guaranteed in many scenarios. In this paper we propose an alternate solution. We propose to capture images at right zoom such that it has just sufficient amount of information so that further resolution enhancements can be easily achieved using any off the shelf single-frame SR algorithm. This is true under the assumption that such a zoom factor is not very high, which is true for most man-made structures. The low-resolution image is divided into small patches and ideal resolution is predicted for every patch. The contextual information is incorporated using a Markov Random Field based prior. Training data is generated from high-quality images and can use any singleframe SR algorithm. Several constraints are proposed to minimize the extent of zoom-in. We validate the proposed approach on synthetic data and real world images to show the robustness

Abstract

Recognition of object categories from their images is extremely challenging due to the large intra-class variations, and variations in pose, illumination and scale, in addition to lack of depth information of the object. Recovering the depth information from multiple images or from image cues such as variations in illumination or focus, is both computationally intensive and error prone. In contrast, the appearance based approaches are more robust and computationally efficient. However, they lack the potential accuracy of 3D feature based approaches due to the lack of shape information. We propose the use of structured lighting patterns projected on the object, which gets deformed according to the shape of the object for recognition. Since our goal is object classification and not shape recovery, we characterize the deformations using simple texture measures, thus avoiding depth recovery step. Moreover, the shape information present in the deformations is implicitly used for classification. We show that the information thus derived can significantly improve the accuracy of object category recognition from arbitrary-pose images.

Abstract

This paper deals with the tracking and following of a person with a camera mounted mobile robot. A modified energy based optical flow approach is used for motion segmentation from a pair of images. Further a spatial relative veolcity based filering is used to extract prominently moving objects. Depth and color information are also used to robustly identify and follow a person.

Abstract

This paper explains how to singularize a robot to a unique hypothesis state from a state of multiple hypotheses. This it does by computing a path whose expected distance is minimum from a tree where each path to the leaf from the root results in a singular hypothesis. At various nodes of the tree the number of hypotheses is reduced as it proceeds down from the root. The nodes of the tree are computed as the best locations to move from an earlier higher hypotheses state. They are either frontier regions or a direction of traversal that result in reduction of hypotheses from an earlier multi hypotheses state. The method has been tested robustly in various simulation situations and its efficacy confirmed.

Abstract

We present a method for finding reduced time coverage paths of multiple UAVs (Unmanned Air Vehicles) monitoring a 3D terrain represented as height fields. A novel metric based on per time visibility is used that couples visibility gained at a terrain point with the time spent to reach the point. This coupled metric is utilized to form reduced time paths by maximizing the visibility gained per unit time at every step. We compare the results of this approach with an approach that covers the terrain based on a per distance visibility metric, which reduces the sum, over distances covered by each UAV path. The comparisons show that the current method gives substantially time reduced paths albeit with an expected increase in sum over distances of UAV paths. We also show that time taken to cover the terrain based on the current metric is far less than prevalent methods that try to decompose the terrain based on visibility followed by time or time followed by visibility in a decoupled fashion. The method is further extended to provide for fault tolerance on a hostile terrain. Each terrain point is guaranteed to be seen by at-least one UAV that has not been damaged due to any calamity, shot or otherwise.

Abstract

To improve the mobility of wheeled robots traversing on and uneven terrain having slopes in all three orthogonal directions is the primary focus of our research. Past research on ‘all terrain vehicles’,[1],[2], was focused on developing mechanical suspension systems which could improve terrain adaptability and locomotion. Consequently control algorithms were developed for posture stability of the vehicle [3],[4]. Shrimp robots [1] and Rocky rovers [2] are terrain vehicles with passive suspension systems which have excellent terrain adaptability and ability to negotiate terrains having discontinuities that are higher than the wheel radius. But mobility and stability of such vehicles is not guaranteed. Thus for such conditions Sreenivasan and Waldron [4] developed vehicles called Wheeled and Actively Articulated Vehicles

Abstract

This paper presents a novel real-time algorithm to sequentially solve the triangulation problem. The problem addressed is estimation of 3D point coordinates given its images and the matrices of the respective cameras used in the imaging process. The algorithm has direct application to real time systems like visual SLAM. This article demonstrates the application of the proposed algorithm to the mapping problem in visual SLAM. Experiments have been carried out for the general triangulation problem as well as the application to visual SLAM. Results show that the application of the proposed method to mapping in visual SLAM outperforms the state of the art mapping methods.

Abstract

In environments which possess relatively few features that enable a robot to unambiguously determine its location, global localization algorithms can result in multiple hypotheses locations of a robot. In such a scenario the robot, for effective localization, has to be actively guided to those locations where there is a maximum chance of eliminating most of the ambiguous states - which is often referred to as dasiaactive localizationpsila. When extended to multi robotic scenarios where all robots possess more than one hypothesis of their position, there is the opportunity to do better by using robots apart from obstacles as dasiahypotheses resolving agentspsila. The paper presents a unified framework accounting for the map structure as well as measurement amongst robots while guiding a set of robots to locations where they can singularize to a unique state. The appropriateness of our approach is demonstrated empirically in both simulation & real-time (on Amigobots) and its efficacy verified. Extensive comparative analysis portrays the advantage of the current method over others that do not perform active localization in a multi-robotic sense.

Abstract

We present a method for finding paths for multiple unmanned air vehicles (UAVs) such that the sum over their lengths is minimum as they cover a 3D terrain (represented as height fields). The paths are constrained to lie beneath an exposure surface to ensure stealth from enemy outposts. The exposure surface is also computed as a height field. The algorithm greedily clusters the terrain such that gain in visibility per distance would be higher for intra-cluster points than points across clusters. Paths generated on clusters formed by such a per distance visibility metric are reduced by more than 25% over other related decoupled methods. The method is extended to cover terrains with partial visibilities. The advantage of the coupled metric extends under constrained visibility also. We again show performance gain by comparing with an existing decoupled algorithm that solves a similar problem of minimum distance terrain coverage with constrained visibility. The paper reveals that decomposing the terrain based on visibility first and then distance is always better than the other way round to cover the terrain in shorter distances.