Huei-Yung Lin

Vehicle speed detection from a single motion blurred image

An image-based method for vehicle speed detection is presented. Conventional speed measurement techniques use radar- or laser-based devices, which are usually more expensive compared to a passive camera system. In this work, a single image captured with vehicle motion is used for speed measurement. Due to the relative motion between the camera and a moving object during the camera exposure time, motion blur occurs in the dynamic region of the image. It provides a visual cue for the speed measurement of a moving object. An approximate target region is first segmented and blur parameters are estimated from the motion blurred subimage. The image is then deblurred and used to derive other parameters. Finally, the vehicle speed is calculated according to the imaging geometry, camera pose, and blur extent in the image. Experiments have shown the estimated speeds within 5% of actual speeds for both local and highway traffic.

An Intelligent Surveillance System Based on an Omnidirectional Vision Sensor

Video surveillance, object tracking and activity monitoring are some of the important issues for a home-care robotic system. In this work, an omnidirectional video camera is adopted to provide a 360 degree view angle of the indoor scene with a single image sequence. Some basic functions for smart living and elderly care, such as motion detection, object tracking and target behavior analysis, are implemented. For the motion detection, a background model is first created and the CamShift algorithm is used for object tracking by extracting color information of the target. To make the motion detection and object tracking fully automatic and robust under different illumination conditions, an optical flow approach is cooperated to detect small changes of the mobile object. In addition, the camera is calibrated to obtain the one-to-one correspondences between the image pixels and the locations on the ground. They are used for fall detection of the target by comparing the object length appeared in the image and the computed length according to the objects physical height

High dynamic range imaging for stereoscopic scene representation

This paper presents a method for generating high dynamic range and disparity images by simultaneously capturing the high and low exposure images using a pair of cameras. The proposed stereoscopic high dynamic range imaging technique is able to record multiple exposures without any time delay, and thus suitable for high dynamic range video synthesis. We have demonstrated that it is possible to construct the camera response function using a pair of images with different amount of exposure. The intensities of the stereo images can then be normalized for correspondence matching. Experiments using the Middlebury stereo datasets are presented.

Vehicle Speed Detection and Identification from a Single Motion Blurred Image

Motion blur is a result of finite acquisition time of practical cameras and the relative motion between the camera and moving objects. Traditionally, the image degradations caused by motion blur are treated as undesirable artifacts and usually have to be removed before further processing. In this work, we propose a novel approach for vehicle speed detection based on a single motion blurred image as opposed to the most commonly used RADAR and LIDAR devices for traffic law enforcement. The motion blur parameters are estimated from a single motion blurred image and the length of motion blur is used for image restoration. The restored image is then used to obtain other parameters for vehicle speed estimation. The images taken with the vehicles license plates are used for both the assistance of image restoration and the identification of the vehicle. We have established a link between the motion blur information of a 2D image and the speed information of a moving object. Experiments have shown the results of less than 2% error for both local and highway traffic compared to video-based speed estimation methods

Reconstruction of shredded document based on image feature matching

Highlights? An image-based technique for shredded document reconstruction is presented. ? Image-based algorithm for similarity comparison between the shreds. ? Graph-based algorithm for shred sorting and document reconstruction. This paper presents an image-based technique for shredded document reconstruction. Currently, most research on document recovery focuses on image feature exaction and analysis. In this work, we have presented a complete procedure to recover a shredded document. The problem is different from solving jigsaw puzzles since curved boundaries and color information are not available. In our two-stage reconstruction approach, image-based techniques are first used to identify the shred images with high spatial proximity and evaluate the similarity between any pair of shreds. A graph-based algorithm is then used to derive the best shred sorting result for document reconstruction. Experiments are presented for both the synthetic and real datasets.

Automatic speed measurements of spherical objects using an off-the-shelf digital camera

A method for automatic speed measurements of spherical objects using a digital camera is presented. Conventional speed measurement techniques use radar or laser based devices, which are usually more expensive compared to a passive camera system. In this work, a single image captured with object motion is used to estimate the speed of a spherical object (such as baseball). Due to the relative motion between the camera and a moving object during the camera exposure time, motion blur occurs in the dynamic region of the image. By identifying the motion blur parameters, the speed of a moving object can be obtained. Automatic target identification and motion estimation are first done by motion blur analysis, followed by more accurate blur identification using circle fitting of the spherical object. Finally, the object speed is calculated according to the imaging geometry, camera pose, and blur extent in the image.

A vision system for fast 3D model reconstruction

A desktop vision system is presented for complete 3D model acquisition. It is fast, low-cost, and accurate. Partial 3D shapes and texture information are acquired from multiple viewing directions using rotational stereo and shape from focus (SFF). The resulting range images are registered to a common coordinate system and a surface representation is created for each range image. The resulting surfaces are integrated using a new algorithm named Region-of-Construction. Unlike previous approaches, the Region-of-Construction algorithm directly exploits the structure of the raw range images. The algorithm determines regions in range images corresponding to non-redundant surfaces which can be stitched along the boundaries to construct the complete 3D surface model. The algorithm is computationally efficient and less sensitive to registration error. It also has the ability to construct complete 3D models of complex objects with holes. A photo realistic 3D model is obtained by mapping texture information onto the complete surface model representing 3D shape. Experimental results for several real objects are presented.

Motion blur removal and its application to vehicle speed detection

Motion blur is the result when the camera shutter remains open for an extended period of time and a relative motion between camera and object occurs. Most research on this type of image degradation is focused on motion blur removal. In this work, we propose a novel approach for vehicle speed detection based on motion blurred images. The motion blur parameters are first estimated from the acquired images and then used to detect the speed of the moving object in the scene. We have established a link between the motion blur information of a 2D image and the speed information of a moving object. Experimental results are presented for both indoor environments and outdoor vehicle speed detection.

3D reconstruction by combining shape from silhouette with stereo

In this paper we propose a 3D reconstruction algorithm by combining shape from silhouette with stereo. Visual hull of the object is first derived from multi-view silhouette images. Pairwise stereo matching for shape refinement is then accomplished using the best viewable images. Based on the reduced correspondence searching range constrained by contact points and bounding edges, significant improvement of visual hull is possible even if the number of cameras is limited. Experimental results are presented for both synthetic data and real scene images.

Lane departure and front collision warning using a single camera

Improving the driving safety is one major concern for the design of intelligent vehicles. In this paper, we present a monocular vision based driver assistance system for dangerous traffic warning. The video sequences captured from a single camera mounted behind the windshield are used for lane detection and front vehicle identification. Two basic modules, lane departure warning system (LDWS) and front collision warning system (FCWS), are developed and then integrated on an embedded DSP platform for automotive electronics applications. Error analysis on system installation is carried out to verify the correctness of measurements. Experimental results have demonstrated that the proposed technique is able to achieve 97% of accuracy on dangerous traffic warning while maintaining the real-time processing requirement.