Tsong-Yi Chen

Moving object detection and tracking from video captured by moving camera

Proposed method has good performance for a moving camera without additional sensors.Proposed method works well for tracking overlapping objects with scale changes.Proposed method outperforms the-state-of-art methods. This paper presents an effective method for the detection and tracking of multiple moving objects from a video sequence captured by a moving camera without additional sensors. Moving object detection is relatively difficult for video captured by a moving camera, since camera motion and object motion are mixed. In the proposed method, the feature points in the frames are found and then classified as belonging to foreground or background features. Next, moving object regions are obtained using an integration scheme based on foreground feature points and foreground regions, which are obtained using an image difference scheme. Then, a compensation scheme based on the motion history of the continuous motion contours obtained from three consecutive frames is applied to increase the regions of moving objects. Moving objects are detected using a refinement scheme and a minimum bounding box. Finally, moving object tracking is achieved using a Kalman filter based on the center of gravity of a moving object region in the minimum bounding box. Experimental results show that the proposed method has good performance.

Rapid detection of camera tampering and abnormal disturbance for video surveillance system

Camera tampering and abnormalities are examined for video surveillance system.Brightness, edge details, and histogram information are computationally efficient.The system runs at 20-30frames/s, meeting the requirement of real-time operation.An average of 4.4% of missed events indicates the feasibility of proposed method. Camera tampering may indicate that a criminal act is occurring. Common examples of camera tampering are turning the camera lens to point to a different direction (i.e., camera motion) and covering the lens by opaque objects or with paint (i.e., camera occlusion). Moreover, various abnormalities such as screen shaking, fogging, defocus, color cast, and screen flickering can strongly deteriorate the performance of a video surveillance system. This study proposes an automated method for rapidly detecting camera tampering and various abnormalities for a video surveillance system. The proposed method is based on the analyses of brightness, edge details, histogram distribution, and high-frequency information, making it computationally efficient. The proposed system runs at a frame rate of 20-30frames/s, meeting the requirement of real-time operation. Experimental results show the superiority of the proposed method with an average of 4.4% of missed events compared to existing works.

License Plate Recognition for Moving Vehicles Using a Moving Camera

This paper is dedicated to a license plate recognition (LPR) system for moving vehicles by using car video camera. The proposed LPR method mainly consists of preprocessing, plate location, and character segmentation & recognition. At irst, the possible regions of license plate are enhanced from the captured images through the proposed edge detection method and gradient-based binarization. Then, the correct plate regions are selected by analyzing the horizontal projection and the corner distribution. A vertical Sobel processing is performed on the segmented license-plate region and then the proposed weighted-binarization method is employed to segment each character of the license, followed by the skew correction. Finally, a probabilistic neural network (PNN) technique is applied to recognize each segmented character. Experimental results show that the accuracy rates of license-plate location and license-plate recognition can achieve 91.7% and 88.5%, respectively.

Effective Moving Object Detection from Videos Captured by a Moving Camera

This paper presents an effective method to detect moving objects for videos captured by a moving camera. Moving object detection is relatively difficult to videos captured by a moving camera, since in the case of the video filmed by moving cameras, not only do the objects move, but also the frames shift. In the proposed schemes, the feature points in the frames are first found and then classified into the foreground and background. Next, the foreground regions and image difference are obtained and then further merged to obtain moving object contours. Finally, the moving object is detected based on the motion history of the continuous motion contours and refinement schemes. Experimental results show that the proposed method performs well in terms of moving object detection.

Vehicle detection and inter-vehicle distance estimation using single-lens video camera on urban/suburb roads ☆

Abstract This paper presents a driver assistance system for vehicle detection and inter-vehicle distance estimation using a single-lens video camera on urban/suburb roads. The task of vehicle detection on urban/suburb roads is more challenging due to their high scene complexity. In this work, the still area of frame inside the host vehicle is first removed using temporal differencing, followed by detecting vanishing point. Segmentation of road regions is then conducted using vanishing point and road’s edge lines. Shadow regions at the bottoms of vehicles verified using the HOG feature and an SVM classifier are utilized to detect vehicle positions. The distances between the host and its front vehicles are estimated based on the locations of detected vehicles and vanishing point. Experimental results show varied performance of vehicle detection with different scenes of urban/suburb roads and the detection rate can achieve up to 94.08%, indicating the feasibility of the proposed method.

Front Vehicle Detection and Distance Estimation Using Single-Lens Video Camera

This paper is dedicated to the front vehicle detection and its distance estimation using one single-lens car video camera on the urban & suburb road roads. The proposed method mainly consists of road area detection and the front vehicle detection & distance calculation. Firstly, Hough transform is used to detect lines in which the appropriate straight lines are selected and their intersection points are exploited for obtaining the vanishing point. Then, both strong right and left edges are extracted and connected to the vanishing point for segmenting the road area, and on such area the bottom shadow of the front vehicle is utilized to locate the vehicles position. Finally, the distance between the host vehicle and the front vehicle is calculated based on the position of a vehicle and the vanishing point. Experimental results show that the proposed technique can moderately detect the front vehicles on the urban & suburb roads with detection rate of 78% at least.

Video Stabilization for Fast Moving Camera Based on Feature Point Classification

This paper is dedicated to video stabilization for fast moving photographing based on feature points classification, especially for the moving camera in various speeds. The proposed method mainly consists of feature point detection and classification, calculating global motion vector and rotation angle of frame, and frame compensation. It is first to search feature points and then classify these feature points into foreground (i.e., moving object) type and background type based on multiple view geometry and DBSCAN algorithm. Then, the global feature points and their optical-flows are derived and utilized for calculating the global motion vector and global rotation angle of frame. Finally, both global motion vector and global rotation angle are refined through motion smoothing using a Kalman filter for providing better frame compensation to generate stable frames. Experimental results show that the proposed method can moderately stabilize the frames captured by a moving camera.

Vehicle Detection in Nighttime Environment by Locating Road Lane and Taillights

In this study, we developed a driver-assistance system on Lane Detection during nighttime by mounting a CCD camera inside the car to capture images and to use computer visions to detect lanes and the driving condition in front of the vehicle. This system can increase the safety of driving during low light condition. The features of this system includes: lane detection, surrounding vehicles detection, lane deviation detection, and distance estimation. After testing on highways with high volume of vehicles, the system in this study can actually reach the ideal results. The camera execution speed can reach about 20 frames per second. This could accomplish the real-time image progressing on highways.

Real-time video stabilization for fast-moving vehicle cameras

Most previous methods of real-time video stabilization are only effective for low-vibrating frames which are usually captured by in-vehicle camera at the low-speed moving. To overcome their ineffectiveness on high-vibrating frames, this paper presents a real-time video stabilization system for the video sequences captured by a fast-moving in-vehicle camera without additional sensors. The proposed method is composed of four parts: frame-shaking judgment, feature classification, evaluating global motion and rotation angle, and frame compensation. Feature points and their motion vectors are employed for judging whether the current frame is shaking or not, and then a conversion matrix is deduced through the perspective projection for classifying such feature points into background or foreground type. Next, the optical flows of background’s feature points are mapped to polar coordinates for obtaining the representative optical-flow cluster of the background. Finally, such a cluster is utilized to calculate the global motion and rotation angle for compensation followed by the Kalman filtering in order to provide the better video stabilization. Experimental results show that the proposed method has good real-time video stabilization for a vehicle camera moving at various speeds and better stabilization performance than other methods for high-vibrating frames when both real-time processing and acceptable stabilization result are considered.

A Cost-Effective Driver-Assistance System in Nighttime

A nighttime driver-assistance system is developed in this study. Through lane detection, neighboring vehicle detection, lane deviation detection, and front vehicle distance estimation of real-time road images retrieved using a charge-coupled device camera, the developed system can issue timely alarms to warn drivers and increase their driving safety at nighttime. In lane detection, the developed system employs clear edge information and lane orientation, and performs edge operations and lane marking using Hough Transform. Vehicle detection is performed by recognizing vehicle characteristics (e.g., tail lights and symmetry) and colors. The front vehicle distance is estimated by counting the number of lane segments. The experimental results of numerous highway image tests show that the developed system can effectively facilitate safe driving in a common environment.