Search

This paper presents a method for the automated detection of dropped objects in surveillance scenarios, which is a very important task for abandoned object detection. Our method works in single views and exploits prior information of the scene, such as geometry or the fact that a number of false alarms are caused by known objects, such as humans. The proposed approach builds dropped object candidates by analyzing blobs obtained with a multi-layer background subtraction approach. The created dropped object candidates are then characterized both by appearance and by temporal aspects such as the estimated drop time. Next, we incorporate prior knowledge about the possible sizes and positions of dropped objects through an efficient filtering approach. Finally, the output of a human detector is exploited over in order to filter out static objects that are likely to be humans that remain still. Experimental results on the publicly available PETS2006 datasets and on several long sequences recorded in metro stations show the effectiveness of the proposed approach. Furthermore, our approach can operate in real-time.

The approach to indexing an image collection depends on the type of data to organize. Satellite images are likely to be searched with latitude and longitude coordinates, medical images are often searched with an image example that serves as a visual query, and personal image collections are generally browsed by event. A more general retrieval scenario is based on the use of textual keywords to search for images containing a specific object, or representing a given scene type. This requires the manual annotation of each image in the collection to allow for the retrieval of relevant visual information based on a text query. This time-consuming and subjective process is the current price to pay for a reliable and convenient text-based image search. This dissertation investigates the use of probabilistic models to assist the automatic organization of image collections, attempting to link the visual content of digital images with a potential textual description. Relying on robust, patch-based image representations that have proven to capture a variety of visual content, our work proposes to model images as mixtures of \emph{latent aspects}. These latent aspects are defined by multinomial distributions that capture patch co-occurrence information observed in the collection. An image is not represented by the direct count of its constituting elements, but as a mixture of latent aspects that can be estimated with principled, generative unsupervised learning methods. An aspect-based image representation therefore incorporates contextual information from the whole collection that can be exploited. This emerging concept is explored for several fundamental tasks related to image retrieval - namely classification, clustering, segmentation, and annotation - in what represents one of the first coherent and comprehensive study of the subject. We first investigate the possibility of classifying images based on their estimated aspect mixture weights, interpreting latent aspect modeling as an unsupervised feature extraction process. Several image categorization tasks are considered, where images are classified based on the present objects or according to their global scene type. We demonstrate that the concept of latent aspects allows to take advantage of non-labeled data to infer a robust image representation that achieves a higher classification performance than the original patch-based representation. Secondly, further exploring the concept, we show that aspects can correspond to an interesting soft clustering of an image collection that can serve as a browsing structure. Images can be ranked given an aspect, illustrating the corresponding co-occurrence context visually. In the third place, we derive a principled method that relies on latent aspects to classify image patches into different categories. This produces an image segmentation based on the resulting spatial class-densities. We finally propose to model images and their caption with a single aspect model, merging the co-occurrence contexts of the visual and the textual modalities in different ways. Once a model has been learned, the distribution of words given an unseen image is inferred based on its visual representation, and serves as textual indexing. Overall, we demonstrate with extensive experiments that the co-occurrence context captured by latent aspects is suitable for the above mentioned tasks, making it a promising approach for multimedia indexing.

The lack of a common benchmark for the evaluation of the gaze estimation task from RGB and RGB-D data is a serious limitation for distinguishing the advantages and disadvantages of the many proposed algorithms found in the literature. The EYEDIAP database intends to overcome this limitation by providing a common framework for the training and evaluation of gaze estimation approaches. In particular, this database has been designed to enable the evaluation of the robustness of algorithms with respect to the main challenges associated to this task: i) Head pose variations; ii) Person variation; iii) Changes in ambient and sensing conditions and iv) Types of target: screen or 3D object. This technical report contains an extended description of the database, we include the processing methodology for the elements provided along with the raw data, the database organization and additional benchmarks we consider relevant to evaluate diverse properties of a given gaze estimator.

We present a novel approach for contextual segmentation of complex visual scenes, based on the use of bags of local invariant features (visterms) and probabilistic aspect models. Our approach uses context in two ways: (1) by using the fact that specific learned aspects correlate with the semantic classes, which resolves some cases of visual polysemy, and (2) by formalizing the notion that scene context is image-specific -what an individual visterm represents depends on what the rest of the visterms in the same bag represent too-. We demonstrate the validity of our approach on a man-made vs. natural visterm classification problem. Experiments on an image collection of complex scenes show that the approach improves region discrimination, producing satisfactory results, and outperforming a non-contextual method. Furthermore, through the later use of a Markov Random Field model, we also show that co-occurrence and spatial contextual information can be conveniently integrated for improved visterm classification.

Image auto-annotation, i.e., the association of words to whole images, has attracted considerable attention. In particular, unsupervised, probabilistic latent variable models of text and image features have shown encouraging results, but their performance with respect to other approaches remains unknown. In this paper, we apply and compare two simple latent space models commonly used in text analysis, namely Latent Semantic Analysis (LSA) and Probabilistic LSA (PLSA). Annotation strategies for each model are discussed. Remarkably, we found that, on a 8000-image dataset, a classic LSA model defined on keywords and a very basic image representation performed as well as much more complex, state-of-the-art methods. Furthermore, non-probabilistic methods (LSA and direct image matching) outperformed PLSA on the same dataset.