Feature scalability for a low complexity face recognition with unconstrained spatial resolution

Automatic face recognition (FR) based applications in low computing power constrained systems, such as mobile and smart camera, have become particularly interesting topic in recent years. In this context, we present computationally efficient FR framework underpinning the so-called feature scalability algorithm. The proposed framework aims at implementing robust FR systems under low-computing power restriction and varying face resolution. Key beneficial property of our proposed FR framework based on feature scalability is to require low computational complexity without sacrificing a level of FR performance. To do this, using feature scalability algorithm enables to directly estimate the features (from pre-enrolled gallery images) that are well matched with the feature of an input probe image with different resolution (generally lower resolution) without any complex process. In addition, our method is helpful for relieving storage shortage problem as it does not require a large amount of training and gallery images with different face resolutions. Results show that our proposed feature scalability algorithm can be seamlessly embedded into state-of-the-art feature extraction methods extensively used for FR by achieving impressive recognition performance. Also, according to the results on computational complexity measurement, the proposed method is proven to be useful for substantially saving FR operation time.     

Real-time abandoned and stolen object detection based on spatio-temporal features in crowded scenes

Abandoned and stolen object detection is a challenging task due to occlusion, changes in lighting, large perspective distortion, and the similarity in appearance of different people. This paper presents real-time detection methods of abandoned and stolen objects in a complex video. The adaptive background modeling method is applied to stable tracking and the ghost image removing. To detect abandoned and stolen objects, the methods determine spatio-temporal relationship between moving people and suspicious drops. The space first detection method measures the distance between a moving object and a non-moving object in spatial change analysis. The time first detection method conducts temporal change analysis and then spatial change analysis. The potential abandoned object is classified as a definite abandoned or stolen object by two-level detection approach. The time-to-live timer is applied by adjusting several key parameters on each camera and environment. In experiments, we show the experimental results to evaluate our proposed methods using benchmark datasets.     

Comparison of two scaling approaches for the development of biomechanical multi-body human models

Dimensional scaling approaches are widely used to develop multi-body human models in injury biomechanics research. Given the limited experimental data for any particular anthropometry, a validated model can be scaled to different sizes to reflect the biological variance of population and used to characterize the human response. This paper compares two scaling approaches at the whole-body level: one is the conventional mass-based scaling approach which assumes geometric similarity; the other is the structure-based approach which assumes additional structural similarity by using idealized mechanical models to account for the specific anatomy and expected loading conditions. Given the use of exterior body dimensions and a uniform Young’s modulus, the two approaches showed close values of the scaling factors for most body regions, with 1.5 % difference on force scaling factors and 13.5 % difference on moment scaling factors, on average. One exception was on the thoracic modeling, with 19.3 % difference on the scaling factor of the deflection. Two 6-year-old child models were generated from a baseline adult model as application example and were evaluated using recent biomechanical data from cadaveric pediatric experiments. The scaled models predicted similar impact responses of the thorax and lower extremity, which were within the experimental corridors; and suggested further consideration of age-specific structural change of the pelvis. Towards improved scaling methods to develop biofidelic human models, this comparative analysis suggests further investigation on interior anatomical geometry and detailed biological material properties associated with the demographic range of the population.     

Location K-anonymity in indoor spaces

With the expansion of wireless-communication infrastructure and the evolution of indoor positioning technologies, the demand for location-based services (LBS) has been increasing in indoor as well as outdoor spaces. However, we should consider a significant challenge regarding the location privacy for realizing indoor LBS. To avoid violations of location privacy, much research has been performed, and location \(\mathcal {K}\)-anonymity has been intensively studied to blur a user location with a cloaking region involving at least \(\mathcal {K}-1\) locations of other persons. Owing to the differences between indoor and outdoor spaces, it is, however, difficult to apply this approach directly in an indoor space. First, the definition of the distance metric in indoor space is different from that in Euclidean and road-network spaces. Second, a bounding region, which is a general form of an anonymizing spatial region (ASR) in Euclidean space, does not respect the locality property in indoor space, where movement is constrained by building components. Therefore, we introduce the concept of indoor location \(\mathcal {K}\)-anonymity in this paper. Then, we investigate the requirements of ASR in indoor spaces and propose novel methods to determine the ASR, considering hierarchical structures of the indoor space. While indoor ASRs are determined at the anonymizer, we also propose processing methods for r-range queries and k-nearest-neighbor queries at a location-based service provider. We validate our methods with experimental analysis of query-processing performance and resilience against attacks in indoor spaces.     

The impact of tangled code changes on defect prediction models

When interacting with source control management system, developers often commit unrelated or loosely related code changes in a single transaction. When analyzing version histories, such tangled changes will make all changes to all modules appear related, possibly compromising the resulting analyses through noise and bias. In an investigation of five open-source Java projects, we found between 7 % and 20 % of all bug fixes to consist of multiple tangled changes. Using a multi-predictor approach to untangle changes, we show that on average at least 16.6 % of all source files are incorrectly associated with bug reports. These incorrect bug file associations seem to not significantly impact models classifying source files to have at least one bug or no bugs. But our experiments show that untangling tangled code changes can result in more accurate regression bug prediction models when compared to models trained and tested on tangled bug datasets—in our experiments, the statistically significant accuracy improvements lies between 5 % and 200 %. We recommend better change organization to limit the impact of tangled changes.     

Efficient indexing and retrieval of large-scale geo-tagged video databases

We are witnessing a significant growth in the number of smartphone users and advances in phone hardware and sensor technology. In conjunction with the popularity of video applications such as YouTube, an unprecedented number of user-generated videos (UGVs) are being generated and consumed by the public, which leads to a Big Data challenge in social media. In a very large video repository, it is difficult to index and search videos in their unstructured form. However, due to recent development, videos can be geo-tagged (e.g., locations from GPS receiver and viewing directions from digital compass) at the acquisition time, which can provide potential for efficient management of video data. Ideally, each video frame can be tagged by the spatial extent of its coverage area, termed Field-Of-View (FOV). This effectively converts a challenging video management problem into a spatial database problem. This paper attacks the challenges of large-scale video data management using spatial indexing and querying of FOVs, especially maximally harnessing the geographical properties of FOVs. Since FOVs are shaped similar to slices of pie and contain both location and orientation information, conventional spatial indexes, such as R-tree, cannot index them efficiently. The distribution of UGVs’ locations is non-uniform (e.g., more FOVs in popular locations). Consequently, even multilevel grid-based indexes, which can handle both location and orientation, have limitations in managing the skewed distribution. Additionally, since UGVs are usually captured in a casual way with diverse setups and movements, no a priori assumption can be made to condense them in an index structure. To overcome the challenges, we propose a class of new R-tree-based index structures that effectively harness FOVs’ camera locations, orientations and view-distances, in tandem, for both filtering and optimization. We also present novel search strategies and algorithms for efficient range and directional queries on our indexes. Our experiments using both real-world and large synthetic video datasets (over 30 years’ worth of videos) demonstrate the scalability and efficiency of our proposed indexes and search algorithms.     

Image processing acceleration for intelligent unmanned aerial vehicle on mobile GPU

In this paper, we present an algorithm for providing visually-guided unmanned aerial vehicle (UAV) control using visual information that is processed on a mobile graphic processing unit (GPU). Most real-time machine vision applications for UAVs exploit low-resolution images because the shortage of computational resources comes from size, weight and power issue. This leads to the limitation that the data are insufficient to provide the UAV with intelligent behavior. However, GPUs have emerged as inexpensive parallel processors that are capable of providing high computational power in mobile environments. We present an approach for detecting and tracking lines that use a mobile GPU. Hough transform and clustering techniques were used for robust and fast tracking. We achieved accurate line detection and faster tracking performance using the mobile GPU as compared with an x86 i5 CPU. Moreover, the average results showed that the GPU provided approximately five times speedup as compared to an ARM quad-core Cortex-A15. We conducted a detailed analysis of the performance of proposed tracking and detection algorithm and obtained meaningful results that could be utilized in real flight.     

Page segmentation using minimum homogeneity algorithm and adaptive mathematical morphology

Document layout analysis or page segmentation is the task of decomposing document images into many different regions such as texts, images, separators, and tables. It is still a challenging problem due to the variety of document layouts. In this paper, we propose a novel hybrid method, which includes three main stages to deal with this problem. In the first stage, the text and non-text elements are classified by using minimum homogeneity algorithm. This method is the combination of connected component analysis and multilevel homogeneity structure. Then, in the second stage, a new homogeneity structure is combined with an adaptive mathematical morphology in the text document to get a set of text regions. Besides, on the non-text document, further classification of non-text elements is applied to get separator regions, table regions, image regions, etc. The final stage, in refinement region and noise detection process, all regions both in the text document and non-text document are refined to eliminate noises and get the geometric layout of each region. The proposed method has been tested with the dataset of ICDAR2009 page segmentation competition and many other databases with different languages. The results of these tests showed that our proposed method achieves a higher accuracy compared to other methods. This proves the effectiveness and superiority of our method.     

Pseudo-inversion: closure properties and decidability

We consider a pseudo-inversion operation inspired by biological events, such as DNA sequence transformations, where only parts of a string are reversed. We define the pseudo-inversion of a string \(w = uxv\) to be the set of all strings \(v^Rxu^R\), where \(uv \ne \lambda \) and consider the operation from a formal language theoretic viewpoint. We show that regular languages are closed under the pseudo-inversion operation whereas context-free languages are not. Furthermore, we study the iterated pseudo-inversion operation and show that the iterated pseudo-inversion of a context-free language is recognized by a nondeterministic reversal-bounded multicounter machine. Finally, we introduce the notion of pseudo-inversion-freeness and examine closure properties and decidability problems for regular and context-free languages. We demonstrate that pseudo-inversion-freeness is decidable in polynomial time for regular languages and undecidable for context-free languages.