Semantic feature-based visual attention model for pedestrian detection

Objective
Pedestrian detection under video surveillance systems has always been a hot topic in computer vision research. These systems are widely used in train stations, airports, large commercial plazas, and other public places. However, pedestrian detection remains difficult because of complex backgrounds. Given its development in recent years, the visual attention mechanism has attracted increasing attention in object detection and tracking research, and previous studies have achieved substantial progress and breakthroughs. We propose a novel pedestrian detection method based on the semantic features under the visual attention mechanism.
Method
The proposed semantic feature-based visual attention model is a spatial-temporal model that consists of two parts: the static visual attention model and the motion visual attention model. The static visual attention model in the spatial domain is constructed by combining bottom-up with top-down attention guidance. Based on the characteristics of pedestrians, the bottom-up visual attention model of Itti is improved by intensifying the orientation vectors of elementary visual features to make the visual saliency map suitable for pedestrian detection. In terms of pedestrian attributes, skin color is selected as a semantic feature for pedestrian detection. The regional and Gaussian models are adopted to construct the skin color model. Skin feature-based visual attention guidance is then proposed to complete the top-down process. The bottom-up and top-down visual attentions are linearly combined using the proper weights obtained from experiments to construct the static visual attention model in the spatial domain. The spatial-temporal visual attention model is then constructed via the motion features in the temporal domain. Based on the static visual attention model in the spatial domain, the frame difference method is combined with optical flowing to detect motion vectors. Filtering is applied to process the field of motion vectors. The saliency of motion vectors can be evaluated via motion entropy to make the selected motion feature more suitable for the spatial-temporal visual attention model.
Result
Standard datasets and practical videos are selected for the experiments. The experiments are performed on a MATLAB R2012a platform. The experimental results show that our spatial-temporal visual attention model demonstrates favorable robustness under various scenes, including indoor train station surveillance videos and outdoor scenes with swaying leaves. Our proposed model outperforms the visual attention model of Itti, the graph-based visual saliency model, the phase spectrum of quaternion Fourier transform model, and the motion channel model of Liu in terms of pedestrian detection. The proposed model achieves a 93% accuracy rate on the test video.
Conclusion
This paper proposes a novel pedestrian method based on the visual attention mechanism. A spatial-temporal visual attention model that uses low-level and semantic features is proposed to calculate the saliency map. Based on this model, the pedestrian targets can be detected through focus of attention shifts. The experimental results verify the effectiveness of the proposed attention model for detecting pedestrians.

Clustering-based Query Routing in Cooperative Semi-structured Peer to Peer Networks

We consider the problem of resource selection in clustered Peer-to-Peer Information Retrieval (P2P IR) networks with cooperative peers. The clustered P2P IR framework presents a significant departure from general P2P IR architectures by employing clustering to ensure content coherence between resources at the resource selection layer, without disturbing document allocation. We propose that such a property could be leveraged in resource selection by adapting well-studied and popular inverted lists for centralized document retrieval. Accordingly, we propose the Inverted PeerCluster Index (IPI), an approach that adapts the inverted lists, in a straightforward manner, for resource selection in clustered P2P IR. IPI also encompasses a strikingly simple peer-specific scoring mechanism that exploits the said index for resource selection. Through an extensive empirical analysis on P2P IR testbeds, we establish that IPI competes well with the sophisticated state-of-the-art methods in virtually every parameter of interest for the resource selection task, in the context of clustered P2P IR.

Binary Mixtures of 1-Butyl-1-Methylpyrrolidinium Bis{(trifluoromethyl)Sulfonyl}Imide and Aliphatic Nitrile Solvents As Electrolyte for Electrochemical Double Layer Capacitors (Invited).

Electrochemical double layer capacitors (EDLCs), also known as supercapacitors, are promising energy storage devices, especially when considering high power applications [1]. EDLCs can be charged and discharged within seconds [1], feature high power (10 kW·kg-1) and an excellent cycle life (>500,000 cycles). All these properties are a result of the energy storage process of EDLCs, which relies on storing energy by charge separation instead of chemical redox reactions, as utilized in battery systems. Upon charging, double layers are forming at the electrode/electrolyte interface consisting of the electrolyte’s ions and electric charges at the electrode surface.In state-of-the-art EDLC systems activated carbons (AC) are used as active materials and tetraethylammonium tetrafluoroborate ([Et4N][BF4]) dissolved in organic solvents like propylene carbonate (PC) or acetonitrile (ACN) are commonly used as the electrolyte [2]. These combinations of materials allow operative voltages up to 2.7 V - 2.8 V and an energy in the order of 5 Wh·kg-1[3]. The energy of EDLCs is dependent on the square of the operative voltage, thus increasing the usable operative voltage has a strong effect on the delivered energy of the device [1]. Due to their high electrochemical stability, ionic liquids (ILs) were thoroughly investigated as electrolytes for EDLCs, as well as, batteries, enabling high operating voltages as high as 3.2 V - 3.5 V for the former [2]. While their unique ionic structure allows the usage of neat ILs as electrolyte in EDLCs, ILs suffer from low conductivity and high viscosity increasing the intrinsic resistance and, as a result, a lower power output of the device. In order to overcome this issue, the usage of blends of ionic liquids and organic solvents has been considered a feasible strategy as they combine high usable voltages, while still retaining good transport properties at the same time.In our recent work the ionic liquid 1-butyl-1-methylpyrrolidinium bis{(trifluoromethyl)sulfonyl}imide ([Pyrr14][TFSI]) was combined with two nitrile-based organic solvents, namely butyronitrile (BTN) and adiponitrile (ADN), and the resulting blends were investing regarding their usage in electrochemical double layer capacitors [4,5]. Firstly, the physicochemical properties were investigated, showing good transport properties for both blends, which are similar to the state-of-the-art combination of [Et4N][BF4] in PC. Secondly, the electrochemical properties for EDLC application were studied in depth revealing a high electrochemical stability with a maximum operative voltage as high as 3.7 V. In full cells these high voltage organic solvent based electrolytes have a good performance in terms of capacitance and an acceptable equivalent series resistance at cut-off voltages of 3.2 and 3.5 V. However, long term stability tests by float testing revealed stability issues when using a maximum voltage of 3.5 V for prolonged time, whereas at 3.2 V no such issues are observed (Fig. 1).Considering the obtained results, the usage of ADN and BTN blends with [Pyrr14][TFSI] in EDLCs appears to be an interesting alternative to state-of-the-art organic solvent based electrolytes, allowing the usage of higher maximum operative voltages while having similar transport properties to 1 mol∙dm-3 [Et4N][BF4] in PC at the same time.

Multiclass Adaboost Based on an Ensemble of Binary Adaboosts

This paper presents a multi-class AdaBoost based on incorporating an ensemble of binary AdaBoosts which is organized as Binary Decision Tree (BDT). It is proved that binary AdaBoost is extremely successful in producing accurate classification but it does not perform very well for multi-class problems. To avoid this performance degradation, the multi-class problem is divided into a number of binary problems and binary AdaBoost classifiers are invoked to solve these classification problems. This approach is tested with a dataset consisting of 6500 binary images of traffic signs. Haar-like features of these images are computed and the multi-class AdaBoost classifier is invoked to classify them. A classification rate of 96.7% and 95.7% is achieved for the traffic sign boarders and pictograms, respectively. The proposed approach is also evaluated using a number of standard datasets such as Iris, Wine, Yeast, etc. The performance of the proposed BDT classifier is quite high as compared with the state of the art and it converges very fast to a solution which indicates it as a reliable classifier.

Feature-based camera pose estimation

The estimating of the relative orientation and position of a camera is one of the integral topics in the field of computer vision. The accuracy of a certain Finnish technology company’s traffic sign inventory and localization process can be improved by utilizing the aforementioned concept. The company’s localization process uses video data produced by a vehicle installed camera. The accuracy of estimated traffic sign locations depends on the relative orientation between the camera and the vehicle. This thesis proposes a computer vision based software solution which can estimate a camera’s orientation relative to the movement direction of the vehicle by utilizing video data. The task was solved by using feature-based methods and open source software. When using simulated data sets, the camera orientation estimates had an absolute error of 0.31 degrees on average. The software solution can be integrated to be a part of the traffic sign localization pipeline of the company in question.

A Note on Iterations-based Derivations of High-order Homogenization Correctors for Multiscale Semi-linear Elliptic Equations

This Note aims at presenting a simple and efficient procedure to derive the structure of high-order corrector estimates for the homogenization limit applied to a semi-linear elliptic equation posed in perforated domains. Our working technique relies on monotone iterations combined with formal two-scale homogenization asymptotics. It can be adapted to handle more complex scenarios including for instance nonlinearities posed at the boundary of perforations and the vectorial case, when the model equations are coupled only through the nonlinear production terms.

Automatic Glaucoma Detection Based on Optic Disc Segmentation and Texture Feature Extraction

The use of digital image processing techniques is prominent in medical settings for the automatic diagnosis of diseases. Glaucoma is the second leading cause of blindness in the world and it has no cure. Currently, there are treatments to prevent vision loss, but the disease must be detected in the early stages. Thus, the objective of this work is to develop an automatic detection method of Glaucoma in retinal images. The methodology used in the study were: acquisition of image database, Optic Disc segmentation, texture feature extraction in different color models and classification of images in glaucomatous or not. We obtained results of 93% accuracy

Learning Binary Code Representations for Effective and Efficient Image Retrieval

The size of online image datasets is constantly increasing. Considering an image dataset with millions of images, image retrieval becomes a seemingly intractable problem for exhaustive similarity search algorithms. Hashing methods, which encodes high-dimensional descriptors into compact binary strings, have become very popular because of their high efficiency in search and storage capacity. In the first part, we propose a multimodal retrieval method based on latent feature models. The procedure consists of a nonparametric Bayesian framework for learning underlying semantically meaningful abstract features in a multimodal dataset, a probabilistic retrieval model that allows cross-modal queries and an extension model for relevance feedback. In the second part, we focus on supervised hashing with kernels. We describe a flexible hashing procedure that treats binary codes and pairwise semantic similarity as latent and observed variables, respectively, in a probabilistic model based on Gaussian processes for binary classification. We present a scalable inference algorithm with the sparse pseudo-input Gaussian process (SPGP) model and distributed computing. In the last part, we define an incremental hashing strategy for dynamic databases where new images are added to the databases frequently. The method is based on a two-stage classification framework using binary and multi-class SVMs. The proposed method also enforces balance in binary codes by an imbalance penalty to obtain higher quality binary codes. We learn hash functions by an efficient algorithm where the NP-hard problem of finding optimal binary codes is solved via cyclic coordinate descent and SVMs are trained in a parallelized incremental manner. For modifications like adding images from an unseen class, we propose an incremental procedure for effective and efficient updates to the previous hash functions. Experiments on three large-scale image datasets demonstrate that the incremental strategy is capable of efficiently updating hash functions to the same retrieval performance as hashing from scratch.

Football Video Annotation Based on Player Motion Recognition Using Enhanced Entropy

This paper presents a semi-parametric Algorithm for parsing football video structures. The approach works on a two interleaved based process that closely collaborate towards a common goal. The core part of the proposed method focus perform a fast automatic football video annotation by looking at the enhance entropy variance within a series of shot frames. The entropy is extracted on the Hue parameter from the HSV color system, not as a global feature but in spatial domain to identify regions within a shot that will characterize a certain activity within the shot period. The second part of the algorithm works towards the identification of dominant color regions that could represent players and playfield for further activity recognition. Experimental Results shows that the proposed football video segmentation algorithm performs with high accuracy.