The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Although Time-of-Flight (TOF) camera can provide real-time depth information from a real scene, the resolution of depth map captured by TOF camera is rather limited compared to HD color cameras, and thus it cannot be directly used in 3D reconstruction. In order to handle this problem, this paper proposes a novel compressive sensing (CS) based depth map super-resolution method, which transforms a low...
For the demands of surgical navigation, this paper proposes some simple 3-D point reconstruction methods. These methods regard the perpendicular feet on back-projection lines as the measurements of a 3-D point, since these feet are close to the 3-D point. And then the methods utilize the distance between 3-D point and camera and error propagation rules to adjust the weights of the feet. Finally, the...
Semi-automatic 2D-to-3D conversion becomes very popular in 3D contents creation due to its advantages over balancing the tradeoff between labor cost and 3D conversion effect. However, the key-frame extraction, as a very important step, has not been specifically put forward in the existing systems. In this paper, a novel key-frame extraction method based on cumulative occlusion is proposed for 2D-to-3D...
A 1D object is a segment with several known-distance markers, and calibration methods with 1D objects are more flexible than those with 2D/3D objects. Under the pinhole camera model, it is proved that the calibration with free-moving 1D objects is not possible. For a central catadioptric camera setup, can the camera be calibrated by a 1D object under general motions? In this paper, we prove that a...
We propose an effective virtual view synthesis approach, which utilizes the technology of depth-image-based rendering (DIBR). In our scheme, two reference color images and their associated depth maps are used to generate the arbitrary virtual viewpoint. Firstly, the main and auxiliary viewpoint images are warped to the virtual viewpoint. After that, the cracks and error points are removed to enhance...
Virtual view synthesis has been considered as a crucial technique in three-dimensional television (3DTV) display, where depth-image-based rendering (DIBR) is a key technology. In order to improve the virtual image quality, a method without preprocessing the depth image is proposed. During the synthesis, the hole-flag map is fully utilized. A Horizontal, Vertical and Diagonal Extrapolation (HVDE) using...
This paper presents a programmable full frame CCD camera system with high performance based on the Texas Instruments (TI) TMS320C6416T Digital Signal Processor (DSP). The Kodak KAF-16803 image sensor is used in this system named CMR6416T. One major advantage of the system is that, after capturing an image from the CCD sensor at a high speed, the raw image processing is performed in the TMS320C6416T...
With the popularization of industrial automation, the efficiency requirement of manual work has been increased significantly. Motion analysis is a very good method to improve operational efficiency. However, because of its fixed observation equipment and narrow scope of view, the motion situation can't be recorded comprehensively and accurately. This paper presents an automatic identification tracking...
Using multi-vision system to implement the Point Positioning is more robust and accurate than using bi-vision system. However, multi-vision system is not feasible for real time Point Positioning; because multi-vision system mainly use optimization method. This paper proposes a fast Point Position method to address this problem. This method regard the average of all feet, which are determined by Back-Projection...
This paper proposes a robust rear-view camera based moving object detection algorithm for backup aid and parking assist applications. A single fish-eye camera is used in order to get much larger FOV (field of view) for object detection. To detect various moving objects such as vehicles and pedestrians, the ego-motion of host vehicle is firstly estimated by A robust NGPP (near ground point projection)...
Zoom tracking plays an important role in camera tracking. It is always a challenge for camera calibration when the focal length becomes long, for the principal plane would move and rotate inevitably in the process of zoom. To deal with this problem, a new method is presented in this paper, in which we does not lay emphasis on the camera calibration itself, but focuses on the compensation to the extrinsic...
In this paper, an intelligent control scheme based on remote gaze tracking is proposed. First, the eye-moving video of the user is captured by ordinary resolution camera under the illumination of near infrared light sources, then the images of the eye region and the pupil region are extracted by processing the video in real time. We process the image of the pupil region, and get the coordinates of...
In order to achieve the goal of high accuracy and low cost in a visual localization system, we present a novel localization method based on four inexpensive video cameras. The method mainly consists of two parts: The “16-points interpolation algorithm” is proposed to enhance the accuracy of 2D coordinates of the detected target on the image plane. Another important aspect is that the Perpendicular...
This paper presents a feature recognition method based on randomized trees. We aim to improve the performance of Lepetit's work, whose actual results are very sensitive to large changes of viewpoint due to its limited ability of samples synthesizing and learning. We propose an approach to alleviate its limitation, which simulates the image appearance changes under actual viewpoint changes by applying...
The accuracy of corner detection is critical for many machine vision applications. A novel corner detector based on video is proposed in this paper. The corner detector can effectively constrain camera noise by using multiple frames from video. The kernel of this method is the similarity algorithm which including a special representation of binary image, a robust template, a simple similarity function...
Consistent labeling is a fundamental problem in multiple-camera-multiple-human tracking. We present a new consistent labeling method called CPSPL that is used in our P2P human tracking system with multiple calibrated cameras, media servers, human trackers and trajectory mergers. The proposed method differs from most existent ones in that it only uses projective lines for establishing the correspondence...
This paper presents an evaluation of the SIFT (scale invariant feature transform), Colour SIFT, and SURF (speeded up robust feature) descriptors on very low resolution images. The performance of the three descriptors are compared against each other on the precision and recall measures using ground truth correct matching data. Our experimental results show that both SIFT and colour SIFT are more robust...
This paper presents a FPGA-based auto focusing system for object ranging. It overcomes the disadvantage of manual focusing wise in traditional method of objects ranging. In our system, the distance of objects can be measured automatically by the auto focusing algorithm. We have experimentally demonstrated the effectiveness of this method. The best performance of our system is about 3% relative errors...
This paper presents an algorithm based on the method of supervised machine learning and multi-keyframes to achieve markerless augmented reality (AR) application when there is a locally planar object in the scene. The main goal is to solve the problem of AR tracking in outdoor environment by only using vision and natural features. Instead of tracking fiducial markers, we track natural keypoints, during...
Localization is of vital importance to a mobile vehicle system. Most of the existing algorithms are based on laser range finders, sonar sensors, artificial landmarks or GPS information. In this paper, we present a sequential probability location method for mobile vehicle, which uses scale-invariant image features as natural landmarks in unmodified environments. First, we construct a ground truth map...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.