Sunglok Choi

Performance Evaluation of RANSAC Family

RANSAC (Random Sample Consensus) has been popular in regression problem with samples contaminated with outliers. It has been a milestone of many researches on robust estimators, but there are a few survey and performance analysis on them. This paper categorizes them on their objectives: being accurate, being fast, and being robust. Performance evaluation performed on line fitting with various data distribution. Planar homography estimation was utilized to present performance in real data.

Robust video stabilization to outlier motion using adaptive RANSAC

The core step of video stabilization is to estimate global motion from locally extracted motion clues. Outlier motion clues are generated from moving objects in image sequence, which cause incorrect global motion estimates. Random Sample Consensus (RANSAC) is popularly used to solve such outlier problem. RANSAC needs to tune parameters with respect to the given motion clues, so it sometimes fail when outlier clues are increased than before. Adaptive RANSAC is proposed to solve this problem, which is based on Maximum Likelihood Sample Consensus (MLESAC). It estimates the ratio of outliers through expectation maximization (EM), which entails the necessary number of iteration for each frame. The adaptation sustains high accuracy in varying ratio of outliers and faster than RANSAC when fewer iteration is enough. Performance of adaptive RANSAC is verified in experiments using four images sequences.

Fast any-angle path planning on grid maps with non-collision pruning

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, Bresenhams 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.

Any-angle path planning on non-uniform costmaps

A* on grid maps generates a path with zig-zag pattern, but Theta* is known to be free from this disadvantage. Theta* assumes that cost of each cell, cell-cost, is uniform, but non-uniform costs are effective ways to represent traversability on grid maps. Theta* does not work on non-uniform costmaps. In this paper, we generalize Theta* toward non-uniform costmaps. To extend Theta*, we propose two kinds of cost functions considering non-uniform cell-costs. The first function adopts the arithmetic mean under the assumption that all cells contribute equally to the overall cost. The second function uses the weighted mean by considering the true traversal length on each cell. We applied the proposed methods to two types of maps: synthetic and real maps. An experiment on synthetic maps quantifies performance of the two methods in terms of accuracy and computing time. The other experiment on real maps presents the effectiveness of Theta* with the proposed methods. The generalized Theta* generated the least-cost path compared with the original Theta* and A* on non-uniform costmaps.

Autonomous navigation of mobile robot based on DGPS/INS sensor fusion by EKF in semi-outdoor structured environment

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.

Resolving scale ambiguity for monocular visual odometry

Scale ambiguity is an inherent problem in monocular visual odometry and SLAM. Our approach is based on common assumptions such that the ground is locally planar and its distance to a camera is constant. The assumptions are usually valid in mobile robots and vehicles moving in indoor and on-road environments. Based on the assumptions, the scale factors are derived by finding the ground in locally reconstructed 3D points. Previously, kernel density estimation with a Gaussian kernel was applied to detect the ground plane, but it generated biased scale factors. This paper proposes an asymmetric Gaussian kernel to estimate unknown scale factors accurately. The asymmetric kernel is inspired from a probabilistic modeling of inliers and outliers, that is, 3D point can comes from the ground and also other objects such as buildings and trees. We experimentally verified that our asymmetric kernel had almost twice higher accuracy than the previous Gaussian kernel. Our experiments was based on an open-source visual odometry and two kinds of public datasets.

uRON v1.5: A device-independent and reconfigurable robot navigation library

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.

Robust Ground Plane Detection from 3D Point Clouds

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 detections application to augmented perception and visualization for drivers and remote operators.

Global path planning on uneven elevation maps

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.

Personal driving diary: Constructing a video archive of everyday driving events

In this paper, we introduce the concept of personal driving diary. A personal driving diary is a multimedia archive of a persons 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.