ProbExplorer: Uncertainty‐guided Exploration and Editing of Probabilistic Medical Image Segmentation

In this paper, we develop an interactive analysis and visualization tool for probabilistic segmentation results in medical imaging. We provide a systematic approach to analyze, interact and highlight regions of segmentation uncertainty. We introduce a set of visual analysis widgets integrating different approaches to analyze multivariate probabilistic field data with direct volume rendering. We demonstrate the user's ability to identify suspicious regions (e.g. tumors) and correct the misclassification results using a novel uncertainty‐based segmentation editing technique. We evaluate our system and demonstrate its usefulness in the context of static and time‐varying medical imaging datasets.     

Dynamic stills and clip trailers

We propose a method for generating visual summaries of video. It reduces browsing time, minimizes screen-space utilization, while preserving the crux of the video content and the sensation of motion. The outputs are images or short clips, denoted as dynamic stills or clip trailers, respectively. The method selects informative poses out of extracted video objects. Optimal rotations and transparency supports visualization of an increased number of poses, leading to concise activity visualization. Our method addresses previously avoided scenarios, e.g., activities occurring in one place, or scenes with non-static background. We demonstrate and evaluate the method for various types of videos.     

On the impact of knowledge extraction and aggregation on crowdsourced annotation of visual artworks

Cultural heritage institutions more and more provide online access to their collections. Collections containing visual artworks need detailed and thorough annotations of the represented visual objects (e.g. plants or animals) to enable human access and retrieval. To make these suitable for access and retrieval, visual artworks need detailed and thorough annotations of the visual classes. Crowdsourcing has proven a viable tool to cater for the pitfalls of automatic annotation techniques. However, differently from traditional photographic image annotation, the artwork annotation task requires workers to possess the knowledge and skills needed to identify and recognise the occurrences of visual classes. The extent to which crowdsourcing can be effectively applied for artwork annotation is still an open research question. Based on a real-life case study from Rijksmuseum Amsterdam, this paper investigates the performance of a crowd of workers drawn from the CrowdFlower platform. Our contributions include a detailed analysis of crowd annotations based on two annotation configurations and a comparison of these crowd annotations with the ones from trusted annotators. In this study we apply a novel method for the automatic aggregation of local (i.e. bounding box) annotations, and we study how different knowledge extraction and aggregation configurations affect the identification and recognition aspects of artwork annotation. Our work sheds new light on the process of crowdsourcing artwork annotations, and shows how techniques that are effective for photographic image annotation cannot be straightforwardly applied to artwork annotation, thus paving the way for new research in the area.     

Automatic image segmentation using constraint learning and propagation

In this paper, we propose automatic image segmentation using constraint learning and propagation. Recently, kernel learning is receiving much attention because a learned kernel can fit the given data better than a predefined kernel. To effectively learn the constraints generated by initial seeds for image segmentation, we employ kernel propagation (KP) based on kernel learning. The key idea of KP is first to learn a small-sized seed-kernel matrix and then propagate it into a large-sized full-kernel matrix. By applying KP to automatic image segmentation, we design a novel segmentation method to achieve high performance. First, we generate pairwise constraints, i.e., must-link and cannot-link, from initially selected seeds to make the seed-kernel matrix. To select the optimal initial seeds, we utilize global k-means clustering (GKM) and self-tuning spectral clustering (SSC). Next, we propagate the seed-kernel matrix into the full-kernel matrix of the entire image, and thus image segmentation results are obtained. We test our method on the Berkeley segmentation database, and the experimental results demonstrate that the proposed method is very effective in automatic image segmentation.     

ViComp: composition of user-generated videos

We propose ViComp, an automatic audio-visual camera selection framework for composing uninterrupted recordings from multiple user-generated videos (UGVs) of the same event. We design an automatic audio-based cut-point selection method to segment the UGV. ViComp combines segments of UGVs using a rank-based camera selection strategy by considering audio-visual quality and camera selection history. We analyze the audio to maintain audio continuity. To filter video segments which contain visual degradations, we perform spatial and spatio-temporal quality assessment. We validate the proposed framework with subjective tests and compare it with state-of-the-art methods.     

A unified framework for web video topic discovery and visualization

Together with the explosive growth of web video in sharing sites like YouTube, automatic topic discovery and visualization have become increasingly important in helping to organize and navigate such large-scale videos. Previous work dealt with the topic discovery and visualization problem separately, and did not take fully into account of the distinctive characteristics of multi-modality and sparsity in web video features. This paper tries to solve web video topic discovery problem with visualization under a single framework, and proposes a Star-structured K-partite Graph based co-clustering and ranking framework, which consists of three stages: (1) firstly, represent the web videos and their multi-model features (e.g., keyword, near-duplicate keyframe, near-duplicate aural frame, etc.) as a Star-structured K-partite Graph; (2) secondly, group videos and their features simultaneously into clusters (topics) and organize the generated clusters as a linked cluster network; (3) finally, rank each type of nodes in the linked cluster network by “popularity” and visualize them as a novel interface to let user interactively browse topics in multi-level scales. Experiments on a YouTube benchmark dataset demonstrate the flexibility and effectiveness of our proposed framework.     

Automatic Image Segmentation by Tree Pruning

The Image Foresting Transform (IFT) is a tool for the design of image processing operators based on connectivity, which reduces image processing problems into an optimum-path forest problem in a graph derived from the image. A new image operator is presented, which solves segmentation by pruning trees of the forest. An IFT is applied to create an optimum-path forest whose roots are seed pixels, selected inside a desired object. In this forest, object and background are connected by optimum paths (leaking paths), which cross the object’s boundary through its “most weakly connected” parts (leaking pixels). These leaking pixels are automatically identified and their subtrees are eliminated, such that the remaining forest defines the object. Tree pruning runs in linear time, is extensible to multidimensional images, is free of ad hoc parameters, and requires only internal seeds, with little interference from the heterogeneity of the background. These aspects favor solutions for automatic segmentation. We present a formal definition of the obtained objects, algorithms, sufficient conditions for tree pruning, and two applications involving automatic segmentation: 3D MR-image segmentation of the human brain and image segmentation of license plates. Given that its most competitive approach is the watershed transform by markers, we also include a comparative analysis between them.     

Object discovery in high-resolution remote sensing images: a semantic perspective

Given its importance, the problem of object discovery in high-resolution remote-sensing (HRRS) imagery has received a lot of attention in the literature. Despite the vast amount of expert endeavor spent on this problem, more efforts have been expected to discover and utilize hidden semantics of images for object detection. To that end, in this paper, we address this problem from two semantic perspectives. First, we propose a semantic-aware two-stage image segmentation approach, which preserves the semantics of real-world objects during the segmentation process. Second, to better capture semantic features for object discovery, we exploit a hyperclique pattern discovery method to find complex objects that consist of several co-existing individual objects that usually form a unique semantic concept. We consider the identified groups of co-existing objects as new feature sets and feed them into the learning model for better performance of image retrieval. Experiments with real-world datasets show that, with reliable segmentation and new semantic features as starting points, we can improve the performance of object discovery in terms of various external criteria.

---

Scene change detection techniques for video database systems

Scene change detection (SCD) is one of several fundamental problems in the design of a video database management system (VDBMS). It is the first step towards the automatic segmentation, annotation, and indexing of video data. SCD is also used in other aspects of VDBMS, e.g., hierarchical representation and efficient browsing of the video data. In this paper, we provide a taxonomy that classifies existing SCD algorithms into three categories: full-video-image-based, compressed-video-based, and model-based algorithms. The capabilities and limitations of the SCD algorithms are discussed in detail. The paper also proposes a set of criteria for measuring and comparing the performance of various SCD algorithms. We conclude by discussing some important research directions.     

Discovering simulation models

Process mining is a tool to extract non-trivial and useful information from process execution logs. These so-called event logs (also called audit trails, or transaction logs) are the starting point for various discovery and analysis techniques that help to gain insight into certain characteristics of the process. In this paper we use a combination of process mining techniques to discover multiple perspectives (namely, the control-flow, data, performance, and resource perspective) of the process from historic data, and we integrate them into a comprehensive simulation model. This simulation model is represented as a colored Petri net (CPN) and can be used to analyze the process, e.g., evaluate the performance of different alternative designs. The discovery of simulation models is explained using a running example. Moreover, the approach has been applied in two case studies; the workflows in two different municipalities in the Netherlands have been analyzed using a combination of process mining and simulation. Furthermore, the quality of the CPN models generated for the running example and the two case studies has been evaluated by comparing the original logs with the logs of the generated models.     

Activity based surveillance video content modelling

This paper tackles the problem of surveillance video content modelling. Given a set of surveillance videos, the aims of our work are twofold: firstly a continuous video is segmented according to the activities captured in the video; secondly a model is constructed for the video content, based on which an unseen activity pattern can be recognised and any unusual activities can be detected. To segment a video based on activity, we propose a semantically meaningful video content representation method and two segmentation algorithms, one being offline offering high accuracy in segmentation, and the other being online enabling real-time performance. Our video content representation method is based on automatically detected visual events (i.e. ‘what is happening in the scene’). This is in contrast to most previous approaches which represent video content at the signal level using image features such as colour, motion and texture. Our segmentation algorithms are based on detecting breakpoints on a high-dimensional video content trajectory. This differs from most previous approaches which are based on shot change detection and shot grouping. Having segmented continuous surveillance videos based on activity, the activity patterns contained in the video segments are grouped into activity classes and a composite video content model is constructed which is capable of generalising from a small training set to accommodate variations in unseen activity patterns. A run-time accumulative unusual activity measure is introduced to detect unusual behaviour while usual activity patterns are recognised based on an online likelihood ratio test (LRT) method. This ensures robust and reliable activity recognition and unusual activity detection at the shortest possible time once sufficient visual evidence has become available. Comparative experiments have been carried out using over 10 h of challenging outdoor surveillance video footages to evaluate the proposed segmentation algorithms and modelling approach.     

Network visualization for financial crime detection

Objective: We present a new software system, VisFAN, for the visual analysis of financial activity networks.MethodsWe combine enhanced graph drawing techniques to devise novel algorithms and interaction functionalities for the visual exploration of networked data sets, together with tools for SNA and for the automatic generation of reports.ResultsAn application example constructed on real data is presented. We also report the results of a study aimed at qualitatively understanding the satisfaction level of the analysts when using VisFAN.ConclusionVisFAN makes a strong use of visual interactive tools, combined with ad-hoc clustering techniques and customizable layout constraints management.ImplicationsAs this system confirms, information visualization can play a crucial role to face the discovery of financial crimes.     

Activity representation with motion hierarchies

Complex activities, e.g. pole vaulting, are composed of a variable number of sub-events connected by complex spatio-temporal relations, whereas simple actions can be represented as sequences of short temporal parts. In this paper, we learn hierarchical representations of activity videos in an unsupervised manner. These hierarchies of mid-level motion components are data-driven decompositions specific to each video. We introduce a spectral divisive clustering algorithm to efficiently extract a hierarchy over a large number of tracklets (i.e. local trajectories). We use this structure to represent a video as an unordered binary tree. We model this tree using nested histograms of local motion features. We provide an efficient positive definite kernel that computes the structural and visual similarity of two hierarchical decompositions by relying on models of their parent–child relations. We present experimental results on four recent challenging benchmarks: the High Five dataset (Patron-Perez et al., High five: recognising human interactions in TV shows, 2010), the Olympics Sports dataset (Niebles et al., Modeling temporal structure of decomposable motion segments for activity classification, 2010), the Hollywood 2 dataset (Marszalek et al., Actions in context, 2009), and the HMDB dataset (Kuehne et al., HMDB: A large video database for human motion recognition, 2011). We show that per-video hierarchies provide additional information for activity recognition. Our approach improves over unstructured activity models, baselines using other motion decomposition algorithms, and the state of the art.     

A survey on compressed domain video analysis techniques

Image and video analysis requires rich features that can characterize various aspects of visual information. These rich features are typically extracted from the pixel values of the images and videos, which require huge amount of computation and seldom useful for real-time analysis. On the contrary, the compressed domain analysis offers relevant information pertaining to the visual content in the form of transform coefficients, motion vectors, quantization steps, coded block patterns with minimal computational burden. The quantum of work done in compressed domain is relatively much less compared to pixel domain. This paper aims to survey various video analysis efforts published during the last decade across the spectrum of video compression standards. In this survey, we have included only the analysis part, excluding the processing aspect of compressed domain. This analysis spans through various computer vision applications such as moving object segmentation, human action recognition, indexing, retrieval, face detection, video classification and object tracking in compressed videos.