Vehicle relocation is the problem in which a mobile robot has to estimate the self-position with respect to an a priori map of landmarks using the perception and the motion measurements without using any knowledge of the initial self-position. Recently, RANdom SAmple Consensus (RANSAC), a robust multi-hypothesis estimator, has been successfully applied to offline relocation in static environments. On the other hand, online relocation in dynamic environments is still a difficult problem, for available computation time is always limited, and for measurement include many outliers. To realize real time algorithm for such an online process, we have developed an incremental version of RANSAC algorithm by extending an efficient preemption RANSAC scheme. This novel scheme named incremental RANSAC is able to find inlier hypotheses of self-positions out of large number of outlier hypotheses contaminated by outlier measurements.
The position we advocate in this paper is that relational algebra can provide a unified language for both representing and computing with statistical-relational objects, much as linear algebra does for traditional single-table machine learning. Relational algebra is implemented in the Structured Query Language (SQL), which is the basis of relational database management systems. To support our position, we have developed the FACTORBASE system, which uses SQL as a high-level scripting language for statistical-relational learning of a graphical model structure. The design philosophy of FACTORBASE is to manage statistical models as first-class citizens inside a database. Our implementation shows how our SQL constructs in FACTORBASE facilitate fast, modular, and reliable program development. Empirical evidence from six benchmark databases indicates that leveraging database system capabilities achieves scalable model structure learning.
We study the persistent homology of the data set of syntactic parameters of the world languages. We show that, while homology generators behave erratically over the whole data set, non-trivial persistent homology appears when one restricts to specific language families. Different families exhibit different persistent homology. We focus on the cases of the Indo-European and the Niger-Congo families, for which we compare persistent homology over different cluster filtering values. We investigate the possible significance, in historical linguistic terms, of the presence of persistent generators of the first homology. In particular, we show that the persistent first homology generator we find in the Indo-European family is not due (as one might guess) to the Anglo-Norman bridge in the Indo-European phylogenetic network, but is related to the position of Ancient Greek and the Hellenic branch within the network.
The paper proposes an algorithm for the script recognition based on the texture characteristics. The image texture is achieved by coding each letter with the equivalent script type (number code) according to its position in the text line. Each code is transformed into equivalent gray level pixel creating an 1-D image. Then, the image texture is subjected to the run-length analysis. This analysis extracts the run-length features, which are classified to make a distinction between the scripts under consideration. In the experiment, a custom oriented database is subject to the proposed algorithm. The database consists of some text documents written in Cyrillic, Latin and Glagolitic scripts. Furthermore, it is divided into training and test parts. The results of the experiment show that 3 out of 5 run-length features can be used for effective differentiation between the analyzed South Slavic scripts.
We developed a machine vision system to automatically capture the dynamics of pedestrians under four different traffic scenarios. By considering the overhead view of each pedestrian as a digital object, the system processes the image sequences to track the pedestrians. Considering the perspective effect of the camera lens and the projected area of the hallway at the top-view scene, the distance of each tracked object from its original position to its current position is approximated every video frame. Using the approximated distance and the video frame rate (30 frames per second), the respective velocity and acceleration of each tracked object are later derived. The quantified motion characteristics of the pedestrians are displayed by the system through 2-dimensional graphs of the kinematics of motion. The system also outputs video images of the pedestrians with superimposed markers for tracking. These visual markers were used to visually describe and quantify the behavior of the pedestrians under different traffic scenarios.
Purpose. Radiation therapy is a local treatment aimed at cells in and around a tumor. The goal of this study is to develop an algorithmic solution for predicting the position of a target in 3D in real time, aiming for the short fixed calibration time for each patient at the beginning of the procedure. Accurate predictions of lung tumor motion are expected to improve the precision of radiation treatment by controlling the position of a couch or a beam in order to compensate for respiratory motion during radiation treatment. Methods. For developing the algorithmic solution, data mining techniques are used. A model form from the family of exponential smoothing is assumed, and the model parameters are fitted by minimizing the absolute disposition error, and the fluctuations of the prediction signal (jitter). The predictive performance is evaluated retrospectively on clinical datasets capturing different behavior (being quiet, talking, laughing), and validated in real-time on a prototype system with respiratory motion imitation. Results. An algorithmic solution for respiratory motion prediction (called ExSmi) is designed. ExSmi achieves good accuracy of prediction (error $4-9$ mm/s) with acceptable jitter values (5-7 mm/s), as tested on out-of-sample data. The datasets, the code for algorithms and the experiments are openly available for research purposes on a dedicated website. Conclusions. The developed algorithmic solution performs well to be prototyped and deployed in applications of radiotherapy.
This paper derives a novel linear position constraint for cameras seeing a common scene point, which leads to a direct linear method for global camera translation estimation. Unlike previous solutions, this method deals with collinear camera motion and weak image association at the same time. The final linear formulation does not involve the coordinates of scene points, which makes it efficient even for large scale data. We solve the linear equation based on $L_1$ norm, which makes our system more robust to outliers in essential matrices and feature correspondences. We experiment this method on both sequentially captured images and unordered Internet images. The experiments demonstrate its strength in robustness, accuracy, and efficiency.
Discourse structure is the hidden link between surface features and document-level properties, such as sentiment polarity. We show that the discourse analyses produced by Rhetorical Structure Theory (RST) parsers can improve document-level sentiment analysis, via composition of local information up the discourse tree. First, we show that reweighting discourse units according to their position in a dependency representation of the rhetorical structure can yield substantial improvements on lexicon-based sentiment analysis. Next, we present a recursive neural network over the RST structure, which offers significant improvements over classification-based methods.
Text alignment is crucial to the accuracy of Machine Translation (MT) systems, some NLP tools or any other text processing tasks requiring bilingual data. This research proposes a language independent sentence alignment approach based on Polish (not position-sensitive language) to English experiments. This alignment approach was developed on the TED Talks corpus, but can be used for any text domain or language pair. The proposed approach implements various heuristics for sentence recognition. Some of them value synonyms and semantic text structure analysis as a part of additional information. Minimization of data loss was ensured. The solution is compared to other sentence alignment implementations. Also an improvement in MT system score with text processed with described tool is shown.
Text alignment and text quality are critical to the accuracy of Machine Translation (MT) systems, some NLP tools, and any other text processing tasks requiring bilingual data. This research proposes a language independent bi-sentence filtering approach based on Polish (not a position-sensitive language) to English experiments. This cleaning approach was developed on the TED Talks corpus and also initially tested on the Wikipedia comparable corpus, but it can be used for any text domain or language pair. The proposed approach implements various heuristics for sentence comparison. Some of them leverage synonyms and semantic and structural analysis of text as additional information. Minimization of data loss was ensured. An improvement in MT system score with text processed using the tool is discussed.
In this position paper, I argue that standardized tests for elementary science such as SAT or Regents tests are not very good benchmarks for measuring the progress of artificial intelligence systems in understanding basic science. The primary problem is that these tests are designed to test aspects of knowledge and ability that are challenging for people; the aspects that are challenging for AI systems are very different. In particular, standardized tests do not test knowledge that is obvious for people; none of this knowledge can be assumed in AI systems. Individual standardized tests also have specific features that are not necessarily appropriate for an AI benchmark. I analyze the Physics subject SAT in some detail and the New York State Regents Science test more briefly. I also argue that the apparent advantages offered by using standardized tests are mostly either minor or illusory. The one major real advantage is that the significance is easily explained to the public; but I argue that even this is a somewhat mixed blessing. I conclude by arguing that, first, more appropriate collections of exam style problems could be assembled, and second, that there are better kinds of benchmarks than exam-style problems. In an appendix I present a collection of sample exam-style problems that test kinds of knowledge missing from the standardized tests.
Semantic object parsing is a fundamental task for understanding objects in detail in computer vision community, where incorporating multi-level contextual information is critical for achieving such fine-grained pixel-level recognition. Prior methods often leverage the contextual information through post-processing predicted confidence maps. In this work, we propose a novel deep Local-Global Long Short-Term Memory (LG-LSTM) architecture to seamlessly incorporate short-distance and long-distance spatial dependencies into the feature learning over all pixel positions. In each LG-LSTM layer, local guidance from neighboring positions and global guidance from the whole image are imposed on each position to better exploit complex local and global contextual information. Individual LSTMs for distinct spatial dimensions are also utilized to intrinsically capture various spatial layouts of semantic parts in the images, yielding distinct hidden and memory cells of each position for each dimension. In our parsing approach, several LG-LSTM layers are stacked and appended to the intermediate convolutional layers to directly enhance visual features, allowing network parameters to be learned in an end-to-end way. The long chains of sequential computation by stacked LG-LSTM layers also enable each pixel to sense a much larger region for inference benefiting from the memorization of previous dependencies in all positions along all dimensions. Comprehensive evaluations on three public datasets well demonstrate the significant superiority of our LG-LSTM over other state-of-the-art methods.
We propose a novel Linear Program (LP) based formula- tion for solving jigsaw puzzles. We formulate jigsaw solving as a set of successive global convex relaxations of the stan- dard NP-hard formulation, that can describe both jigsaws with pieces of unknown position and puzzles of unknown po- sition and orientation. The main contribution and strength of our approach comes from the LP assembly strategy. In contrast to existing greedy methods, our LP solver exploits all the pairwise matches simultaneously, and computes the position of each piece/component globally. The main ad- vantages of our LP approach include: (i) a reduced sensi- tivity to local minima compared to greedy approaches, since our successive approximations are global and convex and (ii) an increased robustness to the presence of mismatches in the pairwise matches due to the use of a weighted L1 penalty. To demonstrate the effectiveness of our approach, we test our algorithm on public jigsaw datasets and show that it outperforms state-of-the-art methods.
Facial landmark localization plays an important role in face recognition and analysis applications. In this paper, we give a brief introduction to a coarse-to-fine pipeline with neural networks and sequential regression. First, a global convolutional network is applied to the holistic facial image to give an initial landmark prediction. A pyramid of multi-scale local image patches is then cropped to feed to a new network for each landmark to refine the prediction. As the refinement network outputs a more accurate position estimation than the input, such procedure could be repeated several times until the estimation converges. We evaluate our system on the 300-W dataset [11] and it outperforms the recent state-of-the-arts.
Traditional algorithms for robots who need to integrate into a wireless network often focus on one specific task. In this work we want to develop simple, adaptive and reusable algorithms for real world applications for this scenario. Starting with the most basic task for mobile wireless network nodes, finding the position of another node, we introduce an algorithm able to solve this task. We then show how this algorithm can readily be employed to solve a large number of other related tasks like finding the optimal position to bridge two static network nodes. For this we first introduce a meta-algorithm inspired by autonomous robot learning strategies and the concept of internal models which yields a class of source seeking algorithms for mobile nodes. The effectiveness of this algorithm is demonstrated in real world experiments using a physical mobile robot and standard 802.11 wireless LAN in an office environment. We also discuss the differences to conventional algorithms and give the robotics perspective on this class of algorithms. Then we proceed to show how more complex tasks, which might be encountered by mobile nodes, can be encoded in the same framework and how the introduced algorithm can solve them. These tasks can be direct (cross layer) optimization tasks or can also encode more complex tasks like bridging two network nodes. We choose the bridging scenario as an example, implemented on a real physical robot, and show how the robot can solve it in a real world experiment.
In convolutional deep neural networks, receptive field (RF) size increases with hierarchical depth. When RF size approaches full coverage of the input image, different RF positions result in RFs with different specificity, as portions of the RF fall out of the input space. This leads to a departure from the convolutional concept of positional invariance and opens the possibility for complex forms of context specificity.
In this position paper we describe a general framework for applying machine learning and pattern recognition techniques in healthcare. In particular, we are interested in providing an automated tool for monitoring and incrementing the level of awareness in the operating room and for identifying human errors which occur during the laparoscopy surgical operation. The framework that we present is divided in three different layers: each layer implements algorithms which have an increasing level of complexity and which perform functionality with an higher degree of abstraction. In the first layer, raw data collected from sensors in the operating room during surgical operation, they are pre-processed and aggregated. The results of this initial phase are transferred to a second layer, which implements pattern recognition techniques and extract relevant features from the data. Finally, in the last layer, expert systems are employed to take high level decisions, which represent the final output of the system.
While invasively recorded brain activity is known to provide detailed information on motor commands, it is an open question at what level of detail information about positions of body parts can be decoded from non-invasively acquired signals. In this work it is shown that index finger positions can be differentiated from non-invasive electroencephalographic (EEG) recordings in healthy human subjects. Using a leave-one-subject-out cross-validation procedure, a random forest distinguished different index finger positions on a numerical keyboard above chance-level accuracy. Among the different spectral features investigated, high $\beta$-power (20-30 Hz) over contralateral sensorimotor cortex carried most information about finger position. Thus, these findings indicate that finger position is in principle decodable from non-invasive features of brain activity that generalize across individuals.
Real-time, accurate, and robust pupil detection is an essential prerequisite for pervasive video-based eye-tracking. However, automated pupil detection in real-world scenarios has proven to be an intricate challenge due to fast illumination changes, pupil occlusion, non centered and off-axis eye recording, and physiological eye characteristics. In this paper, we propose and evaluate a method based on a novel dual convolutional neural network pipeline. In its first stage the pipeline performs coarse pupil position identification using a convolutional neural network and subregions from a downscaled input image to decrease computational costs. Using subregions derived from a small window around the initial pupil position estimate, the second pipeline stage employs another convolutional neural network to refine this position, resulting in an increased pupil detection rate up to 25% in comparison with the best performing state-of-the-art algorithm. Annotated data sets can be made available upon request.
Usually, routing models in pedestrian dynamics assume that agents have fulfilled and global knowledge about the building's structure. However, they neglect the fact that pedestrians possess no or only parts of information about their position relative to final exits and possible routes leading to them. To get a more realistic description we introduce the systematics of gathering and using spatial knowledge. A new wayfinding model for pedestrian dynamics is proposed. The model defines for every pedestrian an individual knowledge representation implying inaccuracies and uncertainties. In addition, knowledge-driven search strategies are introduced. The presented concept is tested on a fictive example scenario.