Dongwook Seo

Multiple Camera-Based Correspondence of Ground Foot for Human Motion Tracking

In this paper, we describe correspondence among multiple images taken by multiple cameras. The correspondence among multiple views is an interesting problem which often appears in the application like visual surveillance or gesture recognition system. We use the principal axis and the ground plane homography to estimate foot of human. The principal axis belongs to the subtracted silhouette-based region of human using subtraction of the predetermined multiple background models with current image which includes moving person. For the calculation of the ground plane homography, we use landmarks on the ground plane in 3D space. Thus the ground plane homography means the relation of two common points in different views. In the normal human being, the foot of human has an exactly same position in the 3D space and we represent it to the intersection in this paper. The intersection occurs when the principal axis in an image crosses to the transformed ground plane from other image. However the positions of the intersection are different depend on camera views. Therefore we construct the correspondence that means the relationship between the intersection in current image and the transformed intersection from other image by homography. Those correspondences should confirm within a short distance measuring in the top viewed plane. Thus, we track a person by these corresponding points on the ground plane. Experimental result shows the accuracy of the proposed algorithm has almost 90% of detecting person for tracking based on correspondence of intersections.

Inverse Perspective Mapping based road curvature estimation

This paper proposes a solution for road curvature estimation. This information is relevant for the task of autonomous navigation. The proposed method is based on the Inverse Perspective Mapping (IPM) which gets rid of perspective distortion. From the IPM with multi scale lane markers appear as the parallel lines. Then, the lane markers are detected by using color segmentation, Hough transform and RANSAC. The detected lines are used for calculating the road curvature which is used to estimate a vehicle trajectory for autonomous vehicle or driver assistance system. In the current experiments, the correct detection rate reached 88.45%.

Real-time flood detection for video surveillance

This paper introduces the real-time flash flood detection method for stationary surveillance cameras. It can be applied for rural and urban areas and capable of working during day time. The background subtraction was used to detect all changes appear in a scene. After this step, many pixel belonging to the same moving objects may be divided. They are united by morphological closing. Too small separate objects are then removed form the scene. Color probability was calculated for all the pixels belonging to a foreground mask and connected components with low probability value were filtered out. Finally, results were improved by edge density and boundary roughness. The most time consuming step was implemented in parallel using CUDA. Real-time performance was achieved in this way. The algorithm was tested on publicly accepted video.

Robust lane marking detection based on multi-feature fusion

In the field of intelligent vehicle systems (IVS), color and edge of lane markings are important features for vision-based applications. This paper proposes a method to detect lane marking based on a fusion approach which combine color and edge lane marking information. Firstly, by knowing the vehicle speed the road surface region of interest is extracted using the typical stopping distance. Secondly, a lane marking clustering method is introduced. This is done by combining the edge and color information of the lane marking. Finally, a fitting model is implemented. A line fitting model is used to extract the lane marking parameters. However for those regions in which lane can not described as a line, the algorithm computed the curve parameters using Lagrange interpolating polynomial.

Lane marking recognition based on laser scanning

Towards safe autonomous vehicle navigation the problem of lane detection and classification is highly important in the development of advanced driver assistance system (ADAS). This paper proposes a new method to detect the road lane marking for safe autonomous navigation purpose. It focuses on unconventional methods of identifying lane markings on a road surface through Laser Measurement System (LMS). This method was executed in three steps. Firstly, to detect lane markings a Density-based spatial clustering of applications with noise (DBSCAN) method was implemented. Secondly, in order to determine the surface course a distance clustering analysis was proposed. Thirdly, the Random Sample Consensus (RANSAC) line fitting method was implemented for removing the noise points around the road lane area. Lastly, an automatic peak detection was implemented to perform lane marking detection on road surfaces. Preliminary results were performed and tested on a group of consecutive fames to prove its effectiveness.

Laser scanner based heading angle and distance estimation

Towards autonomous vehicle navigation the problem of guidance is a major difficulty faced by fully autonomous vehicle. This paper proposes a new method to estimate the heading angle for safe autonomous navigation purpose. The authors focus on unconventional methods of identifying lane markings on a road surface through Laser Measurement System (LMS). This was achieved by taking advantage of the reflection of the laser beam. This method was executed in three steps. Firstly to detect lane markings we employed the Density-based spatial clustering of applications with noise (DBSCAN) method. Secondly, in order to determine the surface course a distance clustering analysis was implemented. Lastly, the steering angle as well as the lateral distance between the heading and the goal point was estimated. Preliminary results were performed and tested on a group of consecutive fames to prove its effectiveness.

Crosswalk detection based on laser scanning from moving vehicle

The safety plays the most important role for both pedestrian and driver in autonomous, semi-autonomous or non-autonomous vehicle. To improve pedestrian safety, this paper presents a new type of laser feature extraction methods for crosswalk marking through Laser Measurement System (LMS). The crosswalk detection is achieved in three stages as follows: Lane Surface Identification (LSI), Lane Marking Recognition (LMR), and finally Crosswalk Marking Detection (CMD). Preliminary results were performed and tested on a group of consecutive frames during the daylight condition to prove its effectiveness.

Iterative road detection based on vehicle speed

When moving towards fully autonomous navigation, safety plays the most important role for both pedestrian and driver. This paper proposes a method to estimate the lane road region of interest based on the stopping typical distance of a vehicle required by the current speed of the vehicle. This was achieved by taking advantage of the difference in color of the road surface given by the lane marking as well as the pavement road. This method was executed in three main steps. Firstly, a distance estimation method using the vehicle speed was presented. Secondly, a lane marking edge feature extraction method was proposed. Finally, in order to determine the road surface a curve fitting model was implemented. Preliminary results were performed and tested on a group of consecutive frames to prove the effectiveness of the proposed method.

Real-time lane marking detection

For autonomous navigation the real-time processing is crucial. This paper proposes a method to detect the lane markings in real-time using the advantage of parallel processing. A region of interest is constrained by the current velocity of a vehicle. The segmentation was achieved by utilizing a difference in color between lane marking and road pavement. The overall process is divided into three steps. The first is detection of lane markings based on the color probability. The second is the implementation of distance clustering analysis to define the surface course. Finally, The curve fitting was applied to assure the lane markings. The method was tested on a dataset to prove its effectiveness.

Path planning and global trajectory tracking control assistance to autonomous vehicle

This paper presents two contributions for the path planning for motion, and convergent global trajectory tracking, which assistance to autonomous vehicle. The path planning for motion is processed by two stages: road network detection and the shortest path estimation for vehicle motion. A road network is detected using the road map images based on image-processing techniques such color filter, segmentation technique. The road map images are collected from online free charge maps services. The road network method estimates not only the shape of road network but also the directed road network, which could not be estimated by the use of only aerial/satellite images. Some lack road segments, which are not annotated by map service, are detected using satellite images based on some filter techniques. The shortest path for motion is estimated using the Dijkstra combining with heuristic based on greedy breadth-first search technique. The road network is converted to the global coordinate, which provides a convenience for online auto-navigation task. The stable and robust control method is used for global trajectory tracking to navigate vehicle motion. The results of simulation and experiment demonstrate the effectiveness of this method under a large scene of the outdoor environments.