Abstract

3D imaging modalities are becoming increasingly popular and relevant in retinal imaging owing to their effectiveness in highlighting structures in sub-retinal layers. OCT is one such modality which has great importance in the context of analysis of cystoid structures in subretinal layers. Signal to noise ratio(SNR) of the images obtained from OCT is less and hence automated and accurate determination of cystoid structures from OCT is a challenging task. We propose an auto-mated method for detecting/segmenting cysts in 3D OCT volumes. The proposed method is biologically inspired and fast aided by the domain-knowledge about the cystoid structures. An ensemble learning method-Random forests is learnt for classification of detected region into cyst region. The method achieves detection and segmentation in a unified set-ting. We believe the proposed approach with further improvements can be a promising starting point for more robust approach. This methodis validated against the training set achieves a mean dice coefficient of0.3893 with a standard deviation of 0.2987

Abstract

Saliency computation is widely studied in computer vision but not in medical imaging. Existing computational saliency models have been developed for general (natural) images and hence may not be suitable for medical images. This is due to the variety of imaging modalities and the requirement of the models to capture not only normal but also deviations from normal anatomy. We present a biologically inspired model for colour fundus images and illustrate it for the case of diabetic retinopathy. The proposed model uses spatially-varying morphological operations to enhance lesions locally and combines an ensemble of results, of such operations, to generate the saliency map. The model is validated against an average Human Gaze map of 15 experts and found to have 10% higher recall (at 100% precision) than four leading saliency models proposed for natural images. The F-score for match with manual lesion markings by 5 experts was0.4 (as opposed to 0.532 for gaze map) for our model and very poor for existing models. The model’s utility is shown via a novel enhancement method which employs saliency to selectively enhance the abnormal regions and this was found to boost their contrast to noise ratio by∼30%

Abstract

Humans display a variety of behaviors including greedy and other unexpected biases during emergency situations. In this paper, we study the effect of such behaviors on traffic patterns during an emergency situation. In particular,we assume that during an emergency there are traffic police or other personnel trying to guide the vehicles so that the traffic clearance is sped up (to minimize the human or property losses). However each individual driver agent has its own motives and biases that may slowdown such a clearing up of traffic. In particular, we assume that the traffic police use the Ford-Fulkerson Algorithm to maximize the flow in the (traffic) network and then perform an extensive agent based analysis to study the traffic patterns that arise due to a variety of human factors and biases. Through a series of experiments performed using the well-known traffic simulator SUMO we could show that: (a) Ford-Fulkerson Algorithm is indeed efficient for clearance of vehicles in such settings (b)Driver agents that do not follow the directions due to their preferences and biases lose out on an average and (c) As can be expected, having more information about the environment available via prior knowledge and/or real-time updates can offset the effect of biases to a good extent.

Abstract

In most practical problems of classifier learning, the training data suffers from the label noise. Hence, it is important to understand how robust is a learning algorithm to such label noise. This paper presents some theoretical analysis to show that many popular decision tree algorithms are robust to symmetric label noise under large sample size. We also present some sample complexity results which provide some bounds on the sample size for the robustness to hold with a high probability. Through extensive simulations we illustrate this robustness.

Abstract

Slow moving traffic in heavily populated cities, can many times result in loss of lives due to emergency vehicles not being able to reach their destination hospitals on time. Recent advances in the field of Intelligent Transportation Systems (ITS) makes it increasingly likely that vehicles in the near future will be equipped with advanced systems that allow inter vehicular communication. In this paper, we assume the usage of such a system to optimize the lane level dynamics for an emergency vehicle (EV), traversing a multi lane stretch of road under a variety of traffic settings. In particular, we present the Fixed Lane Strategy (FLS) and the Best Lane Strategy (BLS) for EV traversal and perform an extensive agent based analysis to study their strengths and weaknesses. Through a series of experiments performed using the well-known traffic simulator SUMO, we could show that: (a) BLS performs better than SUMO strategy on all traffic settings we tested. (b) BLS performs better than FLS in settings that capture real-world traffic conditions involving congestion and uncertainties while FLS performs better in well-behaved conditions and (c) BLS was found to be the best strategy for the setting calibrated using real world data (obtained from NYCDOT).

Abstract

Slow moving traffic in heavily populated cities, can many times result in loss of lives due to emergency vehicles not being able to reach their destination hospitals on time. In this paper, we assume the usage of inter vehicular communication to optimize the lane level dynamics for an Emergency Vehicle Agent (EVA), traversing a multi lane stretch of road in an urban traffic setting. In particular, we present the Fixed Lane Strategy (FLS) and the Best Lane Strategy (BLS) for EVA traversal. FLS is a simple strategy that acts as a good baseline while BLS is a sophisticated strategy that can adapt to varying traffic patterns.

Abstract

We focus on the problem of wearer's action recognition in first person aka egocentric videos. This problem is more challenging than third person activity recognition due to unavailability of wearer's pose and sharp movements in the videos caused by the natural head motion of the wearer. Carefully crafted features based on hands and objects cues for the problem have been shown to be successful for limited targeted datasets. We propose convolutional neural networks (CNNs) for end to end learning and classification of wearer's actions. The proposed network makes use of egocentric cues by capturing hand pose, head motion and saliency map. It is compact. It can also be trained from relatively small number of labeled egocentric videos that are available. We show that the proposed network can generalize and give state of the art performance on various disparate egocentric action datasets.

Abstract

Crowded urban environments are composed of different types of dynamic and static elements. Learning and classification of features is a major task in solving the localization problem in such environments. This work presents a gradual learning methodology to learn the useful features using multiple experiences. The usefulness of an observed element is evaluated by a scoring mechanism which uses two scores – reliability and distinctiveness. The visual features thus learned are used to partition the visual map into smaller regions. The robot is efficiently localized in such a partitioned environment using two-level localization. The concept of active map (AM) is proposed here, which is a map that represents one partition of the environment in which there is a high probability of the robot existing. High-level localization is used to track the mode of the AMs using discrete Bayes filter. Low-level localization uses a bag-of …

Abstract

We propose a semi-supervised self-training method for fine-tuning human pose estimations in videos that provides accurate estimations even for complex sequences. We surpass state-of-the-art on most of the datasets used and also show a 2.33% gain over the baseline on our new dataset of unrestricted sports videos. The self-training model presented has two components: a static Pictorial Structure (PS) based model and a dynamic ensemble of exemplars. We present a pose quality criteria that is primarily used for batch selection and automatic parameter selection. The same criteria works as a low-level pose evaluator used in post-processing. We set a new challenge by introducing a full human body-parts annotated complex dataset, CVIT-SPORTS, which contains complex videos from the sports domain. The strength of our method is demonstrated by adapting to videos of complex activities such as cricket …

Abstract

Several methods have been proposed for large-scale 3D reconstruction from large, unorganized image collections. A large reconstruction problem is typically divided into multiple components which are reconstructed independently using structure from motion (SFM) and later merged together. Incremental SFM methods are most popular for the basic structure recovery of a single component. They are robust and effective but strictly sequential in nature. We present a multistage approach for SFM reconstruction of a single component that breaks the sequential nature of the incremental SFM methods. Our approach begins with quickly building a coarse 3D model using only a fraction of features from given images. The coarse model is then enriched by localizing remaining images and matching and triangulating remaining features in subsequent stages. The geometric information available in form of the coarse model allows us to make these stages effective, efficient, and highly parallel. We show that our method produces similar quality models as compared to standard SFM methods while being notably fast and parallel.