Search

Research equipment is as essential for researchers as transportation is for travelers. Thus, to ascertain the extent to which research equipment affects research performance, this study employed project and performance information to examine the relationships between the qualitative and quantitative performance of papers and patents and the presence and prices of research equipment for research and development (R&D) projects supported by the Korean government from 2011 to 2014 with the Heckman selection model. We discovered that (1) when the equipment was directly constructed using the R&D budgets of the project, it had a positive influence on the performance of both papers and patents. Further, (2) regarding the equipment price, there were negative impacts on papers and patents. At the individual R&D project level, it is necessary to understand the input and output processes to secure project accountability and improvements. We believe this study presents a new perspective on resource allocation of public R&D and promotes an increase in R&D project results using research equipment.

A GPS is usually installed at the center of a vehicle because with this configuration its data become the position of the vehicle without complex calibration and transformation. In this paper, however, we verify that the off-center arrangement of the GPS improves the position and orientation accuracy theoretically and experimentally. The extended Kalman filter (EKF) formulation and its observability and uncertainty analysis present that the off-centered GPS is better observable and less uncertain. Moreover, our experiments with synthetic data and real sensor dataset confirm the improvement of localization accuracy. The synthetic data generated in various situations reveal the important properties of localization with the off-centered GPS. The public outdoor dataset with real GPS data also supports the advantage of the off-centered GPS.

In this paper, we present a method that is able to detect abnormal behavior of intoxicated people in surveillance videos. We first describe typical behavior patterns of intoxicated people in videos and derive two visual features that distinguish them effectively. We define a motion efficiency as one feature to capture intoxicated motion and the aspect ratio of a bounding box of an object as the other to detect intoxicated postures. For the computation of the proposed visual features, the method detects and tracks individual pedestrians in videos and evaluates their motion trajectories and pose trajectories, respectively. The experimental results on the test dataset on railway platform show that the proposed method is able to detect drunken passengers effectively and robustly in a real environment.

Simplified epipolar geometry is proposed in this paper to accelerate monocular visual odometry for ground vehicles. The vehicles on roads or indoors exhibit planar motion locally, and such prior has been effectively utilized to speed up monocular visual odometry. However, we observed that the previous planar motion models frequently failed because their over-simplification did not accept small non-planar motion caused by abrupt bumps or camera vibration. In this paper, simplified motion models are relaxed and their corresponding algorithms for relative pose estimation are derived. Effectiveness of the proposed algorithms is demonstrated by two types of experiments: relative pose estimation with synthetic data, and monocular visual odometry with real image sequences. In the first experiment, the proposed approximated 5-point algorithm provided similar (sometimes better) accuracy to the original 5-point algorithm, but it spent almost 15 times less computing time. In the second experiment, we also observed that monocular visual odometry with our algorithm had almost 9 times faster outlier rejection than previous approaches.

The Visual Object Tracking challenge VOT2017 is the fifth annual tracker benchmarking activity organized by the VOT initiative. Results of 51 trackers are presented; many are state-of-the-art published at major computer vision conferences or journals in recent years. The evaluation included the standard VOT and other popular methodologies and a new "real-time" experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The VOT2017 goes beyond its predecessors by (i) improving the VOT public dataset and introducing a separate VOT2017 sequestered dataset, (ii) introducing a realtime tracking experiment and (iii) releasing a redesigned toolkit that supports complex experiments. The dataset, the evaluation kit and the results are publicly available at the challenge website(1). Funding Agencies|Slovenian research agency research programs [P2-0214, P2-0094]; Slovenian research agency project [J2-8175]; Czech Science Foundation Project [GACR P103/12/G084]; WASP; VR (EMC2); SSF (SymbiCloud); SNIC; AIT Strategic Research Programme Visual Surveillance and Insight; Faculty of Computer Science, University of Ljubljana, Slovenia

In this paper, we introduce the concept of personal driving diary. A personal driving diary is a multimedia archive of a person's daily driving experience, describing important driving events of the user with annotated videos. This paper presents an automated system that constructs such multimedia diary by analyzing videos obtained from a vehicle-mounted camera. The proposed system recognizes important interactions between the driving vehicle and the other actors in videos (e.g., accident, overtaking, etc.), and labels them together with its contextual knowledge on the vehicle (e.g., mean velocity) to construct an event log. A decision tree based activity recognizer is designed, detecting driving events of vehicles and pedestrians from the first-person view videos by analyzing their trajectories and spatio-temporal relationships. The constructed diary enables efficient searching and event-based browsing of video clips, which helps the users when retrieving videos of dangerous situations. Our experiment confirms that the proposed system reliably generates driving diaries by annotating the vehicle events learned from training examples.

The Visual Object Tracking challenge VOT2016 aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 70 trackers are presented, with a large number of trackers being published at major computer vision conferences and journals in the recent years. The number of tested state-of-the-art trackers makes the VOT 2016 the largest and most challenging benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the Appendix. The VOT2016 goes beyond its predecessors by (i) introducing a new semi-automatic ground truth bounding box annotation methodology and (ii) extending the evaluation system with the no-reset experiment. The dataset, the evaluation kit as well as the results are publicly available at the challenge website (http://votchallenge.net).

The Thermal Infrared Visual Object Tracking challenge 2015, VOT-TIR2015, aims at comparing short-term single-object visual trackers that work on thermal infrared (TIR) sequences and do not apply pre-learned models of object appearance. VOT-TIR2015 is the first benchmark on short-term tracking in TIR sequences. Results of 24 trackers are presented. For each participating tracker, a short description is provided in the appendix. The VOT-TIR2015 challenge is based on the VOT2013 challenge, but introduces the following novelties: (i) the newly collected LTIR (Link -- ping TIR) dataset is used, (ii) the VOT2013 attributes are adapted to TIR data, (iii) the evaluation is performed using insights gained during VOT2013 and VOT2014 and is similar to VOT2015.

Color, as perceived through the eye, transcends mere information in the visible range of electromagnetism and serves as an agent for communication and entertainment. Mechanochromic systems have thus far only aimed at satisfying the sense of vision and have overlooked the possibility of generating acoustic vibrations in concert with their visual color responses that would enable the simultaneous satisfaction of the auditory system. Transcending the boundaries of the two senses (i.e., sound and color), herein a strategy for their concurrent and synesthetic fulfillment is elucidated by electrically actuating an organogel photonic device, controlled by a single input signal. This new class of devices that integrate a color module with a speaker is fabricated from a mechanochromic layer that comprises close-packed photonic lattice with an organogel matrix pervading the void fraction. Exploiting a dielectric elastomer actuator, the system's mechanical response permits the simultaneous, yet independent, exploration of visible-light reflection alongside audible sound-wave generation. Large areal strains at low frequencies of actuation tune the photonic stop-band, whereas the layer remains incompressible and exhibits negligible strain when actuated at higher frequencies (e.g., tens of Hz), thereby making it amenable to modulate sound and color simultaneously yet independently.

In the landmark-based localization problem, movement and ambiguity of landmarks and imperfect identification process make measurements of the landmarks completely different from its true value. The incorrect measured data have degraded existing localization methods in the practical applications. This paper proposes a framework to improve accuracy of the existing landmark-based localization methods regardless of such incorrect measured data. The framework is based on Maximum Likelihood Estimation Sample Consensus (MLESAC). It samples a set of measured data randomly to estimate position and orientation, and the estimated pose is evaluated through likelihood of whole measured data with respect to the result. Iterations of sampling, estimation, and evaluation are performed to find the best result to maximize the likelihood. Simulation results demonstrate that the proposed framework improved the the existing localization methods. Analysis using a concept of loss functions also explains that the framework is superior compared to previous researches such as Random Sample Consensus (RANSAC).

Optimization problem is to find the best solution from all feasible solutions such as camera calibration[1], 3D reconstruction [2], visual odometry[3], human skeleton modeling. In order to find best solution, choosing an object function is very important. According to object function, the optimization problem could be distinguished with singular or multiple variable problem and linear or nonlinear optimization problem. If the optimization problem has special constraints except an object function, the problem is constrained optimization problem in contrast non-constrained optimization problem.

In this research, we propose a noble methodology for modeling and simulation of the intensity and direction of the magnetic fields generated by coils in a limited 3-dimensional region. This method was strictly based on the Biot-Savart's law determining the magnetic fields induced by currents flowing through the coils. We also used Finite Element Method (FEM), a numerical technique for finding a solution for each subdivision of a whole domain within the regions of interest. Based on the introduction of rotational transform method for an arbitrary axis, this method possesses a strong analysis capability for the magnetic fields in the vicinity of the coil at an arbitrary position in 3-dimensional region. In addition, a linear calculation system adopted in the simulation process was able to carry on high-performance analysis for the magnetic fields generated by even multiple coils. We strongly propose that this noble method would be a powerful simulation tool for the design of a system that can generate magnetic fields within a 3-dim region of interest considering both the intensity and direction.

Ground provides useful and basic information such as traversal regions and location of 3D objects. The given point cloud may contain a point not only from ground, but also from other objects such as walls and people. Those points from other objects can disturb to find and identify a ground plane. In this paper, we propose robust and fast ground plane detection with an asymmetric kernel and RANSAC. We derive a probabilistic model of a 3D point based on an observation that a point from other objects is always above the ground. The asymmetric kernel is its approximation for fast computation, which is incorporated with RANSAC as a score function. We demonstrate effectiveness of our proposed method as quantitative experiments with our on-road 3D LiDAR dataset. The experimental result presents that our method was sufficiently accurate with slightly more computation. Finally, we also show our ground detection’s application to augmented perception and visualization for drivers and remote operators.

To describe performance of a mobile robot requires non-trivial efforts since robot navigation itself comprises various kinds of sub-components and the performance thereof is highly influenced by the surrounding environment and a given task. In this paper, we focus on performance metrics for robot navigation which are intended for indoor service robots. More particularly, we propose a set of performance metrics that may be useful to describe various attributes of robot navigation intended for indoor educational robots. Localization, mapping, and path planning function are considered.

This video introduces about monocular visual odometry based on planar and circular motion assumption. Many indoor and on-road vehicles show planar motion, and each small piece of motion can approximate to circular motion. We presents that the motion constraints generate more accurate trajectories more quickly.

This paper introduce about graph-search based global path planning on uneven elevation maps. An elevation map is an efficient and popular representation for 3-D terrains due to its easy manipulation by a computer. On the elevation map, we investigate three different optimal paths in the aspects of travel distance, travel time, and energy consumption. A distance/time-optimal path is derived by simple extension of A* on 2-D grid maps. A formulation on energy consumption leads an energy-optimal version and traversiblity criteria. We demonstrate effectiveness of our proposed method by experiments on randomly generated Gaussian hills.

This paper describes a concerted effort to realize an automated robotic service in exhibition environments, characterized by a dense population of people with dynamic, random movements and a complex structure with large-scale dimensions. We describe the developed robotic service framework built based on robot navigation function. Spatial representation of the environment is described, on which spatial path planning, robot localization, and remote monitoring and control of individual robots are developed. As observed from a long-term demonstration, the developed robotic system provided intended robotic services for visitors and obtained satisfactory user feedback, which encourages the adoption of automated robotic services in daily environments.

In this paper, we introduce the new approach to enhance the reliability of detection of objects in a driving environment (e.g. pedestrian and vehicle). We present the method of filtering out false positive detections while maintaining true positive detections. Our approach considers that if we remove a certain region from an image taken from a vehicle in a driving environment, the inpainting algorithm is able to restore the removed region based on its surroundings when it does not include objects. Previous inpainting algorithms were used for restoration of damaged paintings, and we expand its usage to confirm whether the detection result includes the real object or not. Furthermore, we introduce a simple but effective speedup method for the sliding window using simple edge features of objects. Experimental results confirm that our approach is able to improve the accuracies of various pedestrian and vehicle detectors. We show the improved accuracy of pedestrian and vehicle detection in a driving environment with various detectors.

In this paper, we introduce the concept of personal driving diary. A personal driving diary is a multimedia archive of a person's daily driving experience, describing important driving events of the user with annotated videos. This paper presents an automated system that constructs such multimedia diary by analyzing videos obtained from a vehicle-mounted camera. The proposed system recognizes important interactions between the driving vehicle and the others from videos (e.g. accident, overtaking, …), and labels them together with its contextual knowledge on the vehicle (e.g. its physical location on the map) to construct an event log. A novel decision tree based activity recognizer that incrementally learns driving events from first-person view videos is designed. The constructed diary enables efficient searching and event-based browsing of video clips, which helps the user to retrieve videos of dangerous situations and analyze his/her driving habits statistically. Our experiment confirms that the proposed system reliably generates driving diaries by annotating learned vehicle events.

A* on grid maps generates a path with zig-zag pattern as shown in Figure 1(a). Theta* had been proposed to produce a natural and shorter path as shown in Figure 1(b). However, it needs to perform a collision test at every cell expansion. The collision test significantly degrades computing time of Theta*. This paper proposes two pruning schemes to accelerate the collision test in Theta*: non-collision pruning and over-cautious pruning. During expanding search region, previously visited cells can entail the test result before it reaches the last cell. This paper investigates conditions which lead to such early termination. The conditions are easily incorporated with a fast collision test, Bresenham's algorithm. We performed experiments on two different types of maps: random and real maps. On real maps, the pruning schemes accelerated Theta* around two times.

We present a methodology for learning novel human activities incrementally. In many real-world scenarios (e.g. YouTube), new videos of novel activities are provided additively, and the system must incrementally adjust its activity models rather than retraining the entire system after each addition. We introduce our incremental codebook learning algorithm for an efficient mining of important visual words for human activities, and propose a method that incrementally trains activity models using them. The experimental results show that our approach successfully learns human activities from increasing number of training videos, while maintaining its recognition performance comparable to previous non-incremental systems.

Although GPS/DGPS become the dominant localization solution in the outdoor environment, it needs assistant sensors or algorithms for the covering the area not to get the position information from GPS. Especially, in the robot navigation, the sensor fusion algorithm is needed. In addition, it is hard to get the position information at the area surrounded the high buildings such as the downtown because GPS signals is so feeble. Therefore, this paper illustrates an efficient method for the outdoor localization incorporating DGPS, Encoder, and IMU sensor based on EKF. To show the localization performances of the proposed fusion algorithm, we have implemented the proposed algorithm and applied the advertising robot platform which is operating well during 80 days in the real semi-outdoor structured environment. The proposed sensor fusion algorithm and the experimental results showed the feasibility of our novel sensor fusion algorithm.

Many laboratories and companies are developing a mobile robot with various sensors and actuators. They implement navigation techniques usually tailored to their own robot. In this paper, we introduce a novel robot navigation library, Universal Robot Navigation (uRON). uRON is designed to be portable and independent from robot hardware and operating systems. Users can apply uRON to their robots with small amounts of codes. Moreover, uRON provides reusable navigation components and reconfigurable navigation framework. It contains the navigation components such as localization, path planning, path following, and obstacle avoidance. Users can create their own component using the existing ones. uRON also includes the navigation framework which assembles each component and wraps them as high-level functions. Users can achieve their robot service easily and quickly with this framework. We applied uRON to three service robots in Tomorrow City, Incheon, South Korea. Three robots had different hardwares and performed different services. uRON enables three robots movable and satisfies complex service requirements with less than 500 lines of codes.