최재식 교수

In this paper, we address the problem of querying video shots based on content-based matching. Our proposed system automatically partitions a video stream into video shots that maintain continuous movements of objects. Finding video shots of the same category is not an easy task because objects in a video shot change their locations over time. Our spatio-temporal pyramid matching (STPM) is the modified spatial pyramid matching (SPM), which considers temporal information in conjunction with spati

An autonomous vehicle is a demanding application for our daily life. Such vehicle requires to detect other vehicles on the road. Given the sequences of images, the algorithms need to find other vehicles in realtime. There two types of on-road vehicles, traveling in the same direction or traveling in the opposite direction. Due to the distinct features of two types of vehicles, different approaches are necessary to detect vehicles in different directions. Here, we use ‘optical flow‘ to detect veh

Robotic manipulation is important for real, physical world applications. General Purpose manipulation with a robot (eg. delivering dishes, opening doors with a key, etc.) is demanding. It is hard because (1) objects are constrained in position and orientation, (2) many non-spatial constraints interact (or interfere) with each other, and (3) robots may have multi-degree of freedoms (DOF). In this paper we solve the problem of general purpose robotic manipulation using a novel combination of plann

This paper deals with the concept of multi-robot task allocation, referring to the assignment of multiple robots to tasks such that an objective function is maximized. The performance of existing meta-heuristic methods worsens as the number of robots or tasks increases. To tackle this problem, a novel Markov decision process formulation for multi-robot task allocation is presented for reinforcement learning. The proposed formulation sequentially allocates robots to tasks to minimize the total ti

Relational Continuous Models (RCMs) represent joint probability densities over attributes of objects, when the attributes have continuous domains. With relational representations, they can model joint probability distributions over large numbers of variables compactly in a natural way. This paper presents a new exact lifted inference algorithm for RCMs, thus it scales up to large models of real world applications. The algorithm applies to Relational Pairwise Models which are (relational) product

Recently, the use of quadrotors has increased in numerous applications, such as agriculture, rescue, transportation, inspection, and localization. Time-optimal quadrotor waypoint tracking is defined as controlling quadrotors to follow the given waypoints as quickly as possible. Although PID control is widely used for quadrotor control, it is not adaptable to environmental changes, such as various trajectories and dynamic external disturbances. In this work, we discover that adjusting PID control

Handling large streaming data is essential for various applications such as network traffic analysis, social networks, energy cost trends, and environment modeling.However, it is in general intractable to store, compute, search and retrieve large streaming data.This paper addresses a fundamental issue, which is to reduce the size of large streaming data and still obtain accurate statistical analysis.As an example, when a high-speed network such as 100 Gbps network is monitored, the collected mea

Hybrid continuous-discrete models naturally represent many real-world applications in robotics, finance, and environmental engineering. Inference with large-scale models is challenging because relational structures deteriorate rapidly during inference with observations. The main contribution of this paper is an efficient relational variational inference algorithm that factors largescale probability models into simpler variational models, composed of mixtures of iid (Bernoulli) random variables.

In this paper, it is shown how a mobile robot can navigate with high speed in dynamic real environment. In order to achieve high speed and safe navigation, a robot collects environmental information. A robot empirically memorizes locations of high risk due to the abrupt appearance of dynamic obstacles. After collecting sufficient data, a robot navigates in high speed in safe regions. This fact implies that the robot accumulates location dependent environmental information and the robot exploits

Predicting potentially dangerous chemical reactions is a critical task for laboratory safety. However, a traditional experimental investigation of reaction conditions for possible hazardous or explosive byproducts entails substantial time and cost, for which machine learning prediction could accelerate the process and help detailed experimental investigations. Several machine learning models have been developed which allow the prediction of major chemical reaction products with reasonable accura

Motion planning for robotic arms is important for real, physical world applications. The planning for arms with high-degree-of-freedom (DOF) is hard because its search space is large (exponential in the number of joints), and the links may collide with static obstacles or other joints (self-collision). In this paper we present a motion planning algorithm that finds plans of motion from one arm configuration to a goal arm configuration in 2D space assuming no self-collision. Our algorithm is uniq

Aggregate factors (that is, those based on aggregate functions such as SUM, AVERAGE, AND etc.) in probabilistic relational models can compactly represent dependencies among a large number of relational random variables. However, propositional inference on a factor aggregating n k-valued random variables into an r-valued result random variable is O(r k 2n). Lifted methods can ameliorate this to O(r nk) in general and O(r k log n) for commutative associative aggregators. In this paper, we propose

While rate distortion theory compresses data under a distortion constraint, information bottleneck (IB) generalizes rate distortion theory to learning problems by replacing a distortion constraint with a constraint of relevant information. In this work, we further extend IB to multiple Markov bottlenecks (i.e., latent variables that form a Markov chain), namely Markov information bottleneck (MIB), which particularly fits better in the context of stochastic neural networks (SNNs) than the origina

The Kalman Filter (KF) is pervasively used to control a vast array of consumer, health and defense products. By grouping sets of symmetric state variables, the Relational Kalman Filter (RKF) enables us to scale the exact KF for large-scale dynamic systems. In this paper, we provide a parameter learning algorithm for RKF, and a regrouping algorithm that prevents the degeneration of the relational structure for efficient filtering. The proposed algorithms significantly expand the applicability of