this paper presents a novel LCD screen based photometric stereo method. the method is implemented with only a normal laptop. the screen of the computer is used as the light source and portioned into some different reg...
this paper presents a novel LCD screen based photometric stereo method. the method is implemented with only a normal laptop. the screen of the computer is used as the light source and portioned into some different regions to simulate various lighting conditions. And the embedded camera is used for the image capture. With a deduction and proof, we show that a circular partition scheme can obtain optimal lighting effects. By the proposed lighting direction calibration means, a traditional photometric stereo algorithm is utilized for the 3D reconstruction. the experiments are conducted with a real object and compared with conventional means to demonstrate its feasibility and reconstruction accuracy.
3D point clouds registration is an important research topic in bothcomputervision and graphics. Subject to the disadvantages of classical closest point iterative(ICP) algorithm, it is difficult to be applied directl...
详细信息
3D point clouds registration is an important research topic in bothcomputervision and graphics. Subject to the disadvantages of classical closest point iterative(ICP) algorithm, it is difficult to be applied directly in current 3D scanning systems. In this work, a structured light system is cooperated with a turntable to realize fully automatic 3D scanning. To realize the automatic 3D scanning data registration, the rotation axis is first estimated by scanning a calibration plane. Withthis initial estimation of transform matrix, and the proposed overlap region segmentation method, the ICP algorithm is applied to get and optimized registration. the registration errors and efficiency are evaluated with different point cloud datasets. And a full scanning with 12 models is successfully registered automatically. the result shows distinct accuracy improvement.
the serious performance decline with decreasing resolution is the major bottleneck for current pedestrian detection techniques [14, 23]. In this paper, we take pedestrian detection in different resolutions as differen...
详细信息
ISBN:
(纸本)9780769549897
the serious performance decline with decreasing resolution is the major bottleneck for current pedestrian detection techniques [14, 23]. In this paper, we take pedestrian detection in different resolutions as different but related problems, and propose a Multi-Task model to jointly consider their commonness and differences. the model contains resolution aware transformations to map pedestrians in different resolutions to a common space, where a shared detector is constructed to distinguish pedestrians from background. For model learning, we present a coordinate descent procedure to learn the resolution aware transformations and deformable part model (DPM) based detector iteratively. In traffic scenes, there are many false positives located around vehicles, therefore, we further build a context model to suppress them according to the pedestrian-vehicle relationship. the context model can be learned automatically even when the vehicle annotations are not available. Our method reduces the mean miss rate to 60% for pedestrians taller than 30 pixels on the Caltech Pedestrian Benchmark, which noticeably outperforms previous state-of-the-art (71%).
Recently, methods with learning procedure have been widely used to solve person re-identification (re-id) problem. However, most existing databases for re-id are small-scale, therefore, over-fitting is likely to occur...
详细信息
ISBN:
(纸本)9780769549903
Recently, methods with learning procedure have been widely used to solve person re-identification (re-id) problem. However, most existing databases for re-id are small-scale, therefore, over-fitting is likely to occur. To further improve the performance, we propose a novel method by fusing multiple local features and exploring their structural information on different levels. the proposed method is called Structural Constraints Enhanced Feature Accumulation (SCEFA). three local features (i.e., Hierarchical Weighted Histograms (HWH), Gabor Ternary pattern HSV (GTP-HSV), Maximally Stable Color Regions (MSCR)) are used. Structural information of these features are deeply explored in three levels: pixel, blob, and part. the matching algorithms corresponding to the features are also discussed. Extensive experiments conducted on three datasets: VIPeR, EthZ and our own challenging dataset MCSSH, show that our approach outperforms stat-of-the-art methods significantly.
When dealing with objects with complex structures, saliency detection confronts a critical problem - namely that detection accuracy could be adversely affected if salient foreground or background in an image contains ...
详细信息
ISBN:
(纸本)9780769549897
When dealing with objects with complex structures, saliency detection confronts a critical problem - namely that detection accuracy could be adversely affected if salient foreground or background in an image contains small-scale high-contrast patterns. this issue is common in natural images and forms a fundamental challenge for prior methods. We tackle it from a scale point of view and propose a multi-layer approach to analyze saliency cues. the final saliency map is produced in a hierarchical model. Different from varying patch sizes or downsizing images, our scale-based region handling is by finding saliency values optimally in a tree model. Our approach improves saliency detection on many images that cannot be handled well traditionally. A new dataset is also constructed.
In this paper we present and start analyzing the iCub World data-set, an object recognition data-set, we acquired using a Human-Robot Interaction (HRI) scheme and the iCub humanoid robot platform. Our set up allows fo...
详细信息
ISBN:
(纸本)9780769549903
In this paper we present and start analyzing the iCub World data-set, an object recognition data-set, we acquired using a Human-Robot Interaction (HRI) scheme and the iCub humanoid robot platform. Our set up allows for rapid acquisition and annotation of data with corresponding ground truth. While more constrained in its scopes - the iCub world is essentially a robotics research lab - we demonstrate how the proposed data-set poses challenges to current recognition systems. the iCubWorld data-set is publicly available (1).
Computational color constancy is a very important topic in computervision and has attracted many researchers' attention. Recently, lots of research has shown the effects of using high level visual content cues fo...
详细信息
ISBN:
(纸本)9780769549897
Computational color constancy is a very important topic in computervision and has attracted many researchers' attention. Recently, lots of research has shown the effects of using high level visual content cues for improving illumination estimation. However, nearly all the existing methods are essentially combinational strategies in which image's content analysis is only used to guide the combination or selection from a variety of individual illumination estimation methods. In this paper, we propose a novel bilayer sparse coding model for illumination estimation that considers image similarity in terms of both low level color distribution and high level image scene content simultaneously. For the purpose, the image's scene content information is integrated with its color distribution to obtain optimal illumination estimation model. the experimental results on real-world image sets show that our algorithm is superior to some prevailing illumination estimation methods, even better than some combinational methods.
this paper presents a practical means for the calibration of a binocular structured light system(SLS). Considering the characteristics of binocular SLS, 3D coordinates of space points are indicated by the average valu...
详细信息
this paper presents a practical means for the calibration of a binocular structured light system(SLS). Considering the characteristics of binocular SLS, 3D coordinates of space points are indicated by the average values of two cameras and then used to calibrate the projector. According to the idea of bundle adjustment, an error function is constructed to minimize the whole calibration errors. And a non-linear least squares function is applied to find the minimum to the sum of squares of the function. the experimental results show that, withthe optimized calibration results, less calibration errors and better alignment of 3D scanning data can be obtained.
Discrete graphical models (also known as discrete Markov random fields) are a major conceptual tool to model the structure of optimization problems in computervision. While in the last decade research has focused on ...
详细信息
ISBN:
(纸本)9780769549897
Discrete graphical models (also known as discrete Markov random fields) are a major conceptual tool to model the structure of optimization problems in computervision. While in the last decade research has focused on fast approximative methods, algorithms that provide globally optimal solutions have come more into the research focus in the last years. However, large scale computervision problems seemed to be out of reach for such methods. In this paper we introduce a promising way to bridge this gap based on partial optimality and structural properties of the underlying problem factorization. Combining these preprocessing steps, we are able to solve grids of size 2048x2048 in less than 90 seconds. On the hitherto unsolvable chinese character dataset of Nowozin et al. we obtain provably optimal results in 56% of the instances and achieve competitive runtimes on other recent benchmark problems. While in the present work only generalized Potts models are considered, an extension to general graphical models seems to be feasible.
Image cropping is a common operation used to improve the visual quality of photographs. In this paper, we present an automatic cropping technique that accounts for the two primary considerations of people when they cr...
详细信息
ISBN:
(纸本)9780769549897
Image cropping is a common operation used to improve the visual quality of photographs. In this paper, we present an automatic cropping technique that accounts for the two primary considerations of people when they crop: removal of distracting content, and enhancement of overall composition. Our approach utilizes a large training set consisting of photos before and after cropping by expert photographers to learn how to evaluate these two factors in a crop. In contrast to the many methods that exist for general assessment of image quality, ours specifically examines differences between the original and cropped photo in solving for the crop parameters. To this end, several novel image features are proposed to model the changes in image content and composition when a crop is applied. Our experiments demonstrate improvements of our method over recent cropping algorithms on a broad range of images.
暂无评论