Abstract: The fields of segmentation, tracking and behavior analysis demand for challenging video resources to test, in a scalable manner, complex scenarios like crowded environments or scenes with high semantics. Nevertheless, existing public databases cannot scale the presence of appearing agents, which would be useful to study long-term occlusions and crowds. Moreover, creating these resources is expensive and often too particularized to specific needs. We propose an augmented reality framework to increase the complexity of image sequences in terms of occlusions and crowds, in a scalable and controllable manner. Existing datasets can be increased with augmented sequences containing virtual agents. Such sequences are automatically annotated, thus facilitating evaluation in terms of segmentation, tracking, and behavior recognition. In order to easily specify the desired contents, we propose a natural language interface to convert input sentences into virtual agent behaviors. Experimental tests and validation in indoor, street, and soccer environments are provided to show the feasibility of the proposed approach in terms of robustness, scalability, and semantics.

Abstract: Visual categorization is important to manage large collections of digital images and video, where textual meta-data is often incomplete or simply unavailable. The bag-of-words model has become the most powerful method for visual categorization of images and video. Despite its high accuracy, a severe drawback of this model is its high computational cost. As the trend to increase computational power in newer CPU and GPU architectures is to increase their level of parallelism, exploiting this parallelism becomes an important direction to handle the computational cost of the bag-of-words approach. When optimizing a system based on the bag-of-words approach, the goal is to minimize the time it takes to process batches of images. Additionally, we also consider power usage as an evaluation metric. In this paper, we analyze the bag-of-words model for visual categorization in terms of computational cost and identify two major bottlenecks: the quantization step and the classification step. We address these two bottlenecks by proposing two efficient algorithms for quantization and classification by exploiting the GPU hardware and the CUDA parallel programming model. The algorithms are designed to (1) keep categorization accuracy intact, (2) decompose the problem and (3) give the same numerical results. In the experiments on large scale datasets it is shown that, by using a parallel implementation on the Geforce GTX260 GPU, classifying unseen images is 4.8 times faster than a quad-core CPU version on the Core i7 920, while giving the exact same numerical results. In addition, we show how the algorithms can be generalized to other applications, such as text retrieval and video retrieval. Moreover, when the obtained speedup is used to process extra video frames in a video retrieval benchmark, the accuracy of visual categorization is improved by 29%.

Abstract: Recent progress in the field of human action recognition points towards the use of Spatio-TemporalInterestPoints (STIPs) for local descriptor-based recognition strategies. In this paper, we present a novel approach for robust and selective STIP detection, by applying surround suppression combined with local and temporal constraints. This new method is significantly different from existing STIP detection techniques and improves the performance by detecting more repeatable, stable and distinctive STIPs for human actors, while suppressing unwanted background STIPs. For action representation we use a bag-of-video words (BoV) model of local N-jet features to build a vocabulary of visual-words. To this end, we introduce a novel vocabulary building strategy by combining spatial pyramid and vocabulary compression techniques, resulting in improved performance and efficiency. Action class specific Support Vector Machine (SVM) classifiers are trained for categorization of human actions. A comprehensive set of experiments on popular benchmark datasets (KTH and Weizmann), more challenging datasets of complex scenes with background clutter and camera motion (CVC and CMU), movie and YouTube video clips (Hollywood 2 and YouTube), and complex scenes with multiple actors (MSR I and Multi-KTH), validates our approach and show state-of-the-art performance. Due to the unavailability of ground truth action annotation data for the Multi-KTH dataset, we introduce an actor specific spatio-temporal clustering of STIPs to address the problem of automatic action annotation of multiple simultaneous actors. Additionally, we perform cross-data action recognition by training on source datasets (KTH and Weizmann) and testing on completely different and more challenging target datasets (CVC, CMU, MSR I and Multi-KTH). This documents the robustness of our proposed approach in the realistic scenario, using separate training and test datasets, which in general has been a shortcoming in the performance evaluation of human action recognition techniques.

Abstract: In this paper, we propose a circular blurred shape model descriptor to deal with the problem of symbol detection and classification as a particular case of object recognition. The feature extraction is performed by capturing the spatial arrangement of significant object characteristics in a correlogram structure. The shape information from objects is shared among correlogram regions, where a prior blurring degree defines the level of distortion allowed in the symbol, making the descriptor tolerant to irregular deformations. Moreover, the descriptor is rotation invariant by definition. We validate the effectiveness of the proposed descriptor in both the multiclass symbol recognition and symbol detection domains. In order to perform the symbol detection, the descriptors are learned using a cascade of classifiers. In the case of multiclass categorization, the new feature space is learned using a set of binary classifiers which are embedded in an error-correcting output code design. The results over four symbol data sets show the significant improvements of the proposed descriptor compared to the state-of-the-art descriptors. In particular, the results are even more significant in those cases where the symbols suffer from elastic deformations.

Abstract: IF JCR CCIA 1.303 2009 54/103
The classification of large number of object categories is a challenging trend in the pattern recognition field. In literature, this is often addressed using an ensemble of classifiers. In this scope, the Error-correcting output codes framework has demonstrated to be a powerful tool for combining classifiers. However, most state-of-the-art ECOC approaches use a linear or exponential number of classifiers, making the discrimination of a large number of classes unfeasible. In this paper, we explore and propose a minimal design of ECOC in terms of the number of classifiers. Evolutionary computation is used for tuning the parameters of the classifiers and looking for the best minimal ECOC code configuration. The results over several public UCI datasets and different multi-class computer vision problems show that the proposed methodology obtains comparable (even better) results than state-of-the-art ECOC methodologies with far less number of dichotomizers.

Abstract: In this paper, we address two complex issues: 1) Text frame classification and 2) Multi-oriented text detection in video text frame. We first divide a video frame into 16 blocks and propose a combination of wavelet and median-moments with k-means clustering at the block level to identify probable text blocks. For each probable text block, the method applies the same combination of feature with k-means clustering over a sliding window running through the blocks to identify potential text candidates. We introduce a new idea of symmetry on text candidates in each block based on the observation that pixel distribution in text exhibits a symmetric pattern. The method integrates all blocks containing text candidates in the frame and then all text candidates are mapped on to a Sobel edge map of the original frame to obtain text representatives. To tackle the multi-orientation problem, we present a new method called Angle Projection Boundary Growing (APBG) which is an iterative algorithm and works based on a nearest neighbor concept. APBG is then applied on the text representatives to fix the bounding box for multi-oriented text lines in the video frame. Directional information is used to eliminate false positives. Experimental results on a variety of datasets such as non-horizontal, horizontal, publicly available data (Hua’s data) and ICDAR-03 competition data (camera images) show that the proposed method outperforms existing methods proposed for video and the state of the art methods for scene text as well.