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.

Image-Based Spatialization

An approach to spatialization is described in which the pixels of an image determine both spatial and other attributes of individual elements in a multi-channel musical texture. The application of this technique in the author’s composition Spaced Images with Noise and Lines is discussed in detail. The relationship of this technique to existing image-to-sound mappings is discussed. The particular advantage of modifying spatial properties with image filters is considered.

Human pose tracking in low dimensional space enhanced by limb correction

This paper proposes a two-level 3D human pose tracking method for a specific action captured by several cameras. The generation of pose estimates relies on fitting a 3D articulated model on a Visual Hull generated from the input images. First, an initial pose estimate is constrained by a low dimensional manifold learnt by Temporal Laplacian Eigenmaps. Then, an improved global pose is calculated by refining individual limb poses. The validation of our method uses a public standard dataset and demonstrates its accurate and computational efficiency. © 2011 IEEE.

Robust visual tracking using structurally random projection and weighted least squares

Sparse representation based visual tracking approaches have attracted increasing interests in the community in recent years. The main idea is to linearly represent each target candidate using a set of target and trivial templates while imposing a sparsity constraint onto the representation coefficients. After we obtain the coefficients using L1-norm minimization methods, the candidate with the lowest error, when it is reconstructed using only the target templates and the associated coefficients, is considered as the tracking result. In spite of promising system performance widely reported, it is unclear if the performance of these trackers can be maximised. In addition, computational complexity caused by the dimensionality of the feature space limits these algorithms in real-time applications. In this paper, we propose a real-time visual tracking method based on structurally random projection and weighted least squares techniques. In particular, to enhance the discriminative capability of the tracker, we introduce background templates to the linear representation framework. To handle appearance variations over time, we relax the sparsity constraint using a weighed least squares (WLS) method to obtain the representation coefficients. To further reduce the computational complexity, structurally random projection is used to reduce the dimensionality of the feature space while preserving the pairwise distances between the data points in the feature space. Experimental results show that the proposed approach outperforms several state-of-the-art tracking methods.

A machine vision approach to the grading of crushed aggregate

The grading of crushed aggregate is carried out usually by sieving. We describe a new image-based approach to the automatic grading of such materials. The operational problem addressed is where the camera is located directly over a conveyor belt. Our approach characterizes the information content of each image, taking into account relative variation in the pixel data, and resolution scale. In feature space, we find very good class separation using a multidimensional linear classifier. The innovation in this work includes (i) introducing an effective image-based approach into this application area, and (ii) our supervised classification using wavelet entropy-based features.

Dengue Virus Inhibition of Autophagic Flux and Dependency of Viral Replication on Proteasomal Degradation of the Autophagy Receptor p62

Autophagic flux involves formation of autophagosomes and their degradation by lysosomes. Autophagy can either promote or restrict viral replication. In the case of Dengue virus (DENV) several studies report that autophagy supports the viral replication cycle, and describe an increase of autophagic vesicles (AVs) following infection. However, it is unknown how autophagic flux is altered to result in increased AVs. To address this question, and gain insight into the role of autophagy during DENV infection, we established an unbiased, image-based flow cytometry approach to quantify autophagic flux under normal growth conditions and in response to activation by nutrient deprivation or the mTOR inhibitor Torin1. We found that DENV induced an initial activation of autophagic flux, followed by inhibition of general and specific autophagy. Early after infection, basal and activated autophagic flux was enhanced. However, during established replication, basal and Torin1-activated autophagic flux was blocked, while autophagic flux activated by nutrient deprivation was reduced, indicating a block to AV formation and reduced AV degradation capacity. During late infection AV levels increased as a result of inefficient fusion of autophagosomes with lysosomes. Additionally, endo-lysosomal trafficking was suppressed, while lysosomal activities were increased. We further determined that DENV infection progressively reduced levels of the autophagy receptor SQSTM1/p62 via proteasomal degradation. Importantly, stable over-expression of p62 significantly suppressed DENV replication suggesting a novel role for p62 as viral restriction factor. Overall our findings indicate that in the course of DENV infection, autophagy shifts from a supporting to an anti-viral role, which is countered by DENV.

IMPORTANCE: Autophagic flux is a dynamic process starting with the formation of autophagosomes and ending with their degradation after fusion with lysosomes. Autophagy impacts the replication cycle of many viruses. However, thus far the dynamics of autophagy in case of Dengue virus (DENV) infections has not been systematically quantified. Therefore, we employed high-content, imaging-based flow cytometry to quantify autophagic flux and endo-lysosomal trafficking in response to DENV infection. We report that DENV induced an initial activation of autophagic flux, followed by inhibition of general and specific autophagy. Further, lysosomal activity was increased, but endo-lysosomal trafficking was suppressed confirming the block of autophagic flux. Importantly, we provide evidence that p62, an autophagy receptor, restrict DENV replication and was specifically depleted in DENV-infected cells via increased proteasomal degradation. These results suggest that during DENV infection autophagy shifts from a pro- to an antiviral cellular process, which is counteracted by the virus.

Methods for Optimal Work Instruction Delivery: Pictograms v Images

This paper focuses on quantifying the benefits of pictogram based instructions relative to static images for work instruction delivery. The assembly of a stiffened aircraft panel has been used as an exemplar for the work which seeks to address the challenge of identifying an instructional mode that can be location or language neutral while at the same time optimising assembly build times and maintaining build quality. Key performance parameters measured using a series of panel build experiments conducted by two separate groups were: overall build time, the number of subject references to instructional media, the number of build errors and the time taken to correct any mistakes. Overall build time for five builds for a group using pictogram instructions was about 20% lower than for the group using image based instructions. Also, the pictogram group made fewer errors. Although previous work identified that animated instructions result in optimal build times, the language neutrality of pictograms as well as the fact that they can be used without visualisation hardware mean that, on balance, they have broader applicability in terms of transferring assembly knowledge to the manufacturing environment.

Comparison of Image Transform-Based Features for Visual Speech Recognition in Clean and Corrupted Videos

We present results of a study into the performance of a variety of different image transform-based feature types for speaker-independent visual speech recognition of isolated digits. This includes the first reported use of features extracted using a discrete curvelet transform. The study will show a comparison of some methods for selecting features of each feature type and show the relative benefits of both static and dynamic visual features. The performance of the features will be tested on both clean video data and also video data corrupted in a variety of ways to assess each feature type's robustness to potential real-world conditions. One of the test conditions involves a novel form of video corruption we call jitter which simulates camera and/or head movement during recording.