Fig 1 - uploaded by Alberto Petrilli-Barceló
Content may be subject to copyright.
(a) RGB image; the pixels without depth information are shown with less brightness. b) Depth image, the dark pixels correspond to faraway points and the white to close points. (c) The cloud of points in 3D space; the geometric reconstruction of the scene.
Source publication
The understanding of scenes is a key aspect of computer vision. Edge detection helps us to understand more about the scene structure since the edges mark a clear distinction for a transition from one region with similar properties to another one. When the edges are obtained from changes in orientation, we can use them to find key planes and describ...
Context in source publication
Context 1
... f x d f y d c x d c y d are the intrinsic parameters of the depth camera. Therefore, from the RGB-D image, we can associate a cloud of points in the 3D space that is the reconstruction of the scene. Figure 1 shows the RGB image and its corresponding cloud of 3D points; we will denote the cloud of 3D points by X RGB-D , ...
Similar publications
Juxtapleural lung nodules are often excluded from the lung region in many CT image processing algorithms which are based on intensity information. For solving this problem, a suspicious edge line detection algorithm is proposed to obtain the edge line of the suspicious local lung region in this manuscript. Firstly, the lung region in the CT image i...
The spiral phase contrast microscope can clearly distinguish the morphological information of the low contrast objects (i.e., biological samples) owing to the isotropic edge‐enhancement effect, while the bright field microscope can image the overall morphology of amplitude objects. However, the imaging resolution, magnification, and field of view o...
To retrieve the images from large database that are highly related to the query image where query image is given by user. Three features are used for retrieving the images, which are color, shape and texture. These features are extracted by different techniques. Color feature is extracted by Color Histogram and Color Descriptor. Shape feature is ex...
IP Camera is a device that used for surveillance system. IP Camera can be used to identify the captured object. This study uses the IP Camera to recognize hand shapes were captured by IP camera. Hand shape recognition process is done by using three feature extraction methods. All of these methods are Edge Detection, Vector Analysis and Pixel to Pix...
Citations
... Edge detection is the foundation of many other image processing techniques. Common edge detection operators include Roberts [1], Sobel [2], Prewitt [3], Laplacan [4], Kirsh [5], Hurckel [6], LOG [7], Canny [8], etc. Among them, Canny algorithm has better denoising ability and higher detection precision than other algorithms, and has a wide range of applications. ...
... A direct detection of these features in the RGB space will disregard any captured depth information and lead to a redundant set of features (e.g., the texture edges in Figure 8 (Left)). An intuition on extracting edges from depth data is to first compute 3D planes and the edges are naturally their intersections [24,4]. In the following, we design a viable solution particularly tailored for our system, which bears the similar idea of model fitting [24] for edge estimation using depth. ...
The creation of 3D contents still remains one of the most crucial problems for the emerging applications such as 3D printing and Augmented Reality. In Augmented Reality, how to create virtual contents that seamlessly overlay with the real environment is a key problem for human-computer interaction and many subsequent applications. In this paper, we present a sketch-based interactive tool, which we term emph{SweepCanvas}, for rapid exploratory 3D modeling on top of an RGB-D image. Our aim is to offer end-users a simple yet efficient way to quickly create 3D models on an image. We develop a novel sketch-based modeling interface, which takes a pair of user strokes as input and instantly generates a curved 3D surface by sweeping one stroke along the other. A key enabler of our system is an optimization procedure that extracts pairs of spatial planes from the context to position and sweep the strokes. We demonstrate the effectiveness and power of our modeling system on various RGB-D data sets and validate the use cases via a pilot study.
Scrap steel grading is a vital stage of steel production. Thickness is an important indicator in determining the grade of scrap steel. Existing methods based on 2-D vision cannot accurately estimate the thickness of scrap steel due to the lack of 3-D information. Consequently, estimation results from 2-D methods cannot satisfy the requirements of the steel industry. To solve this problem, we propose a 3-D vision-based scrap steel grading system. We introduce a novel thickness feature descriptor that can perform edge detection on organized point clouds. It can detect the pairs of points that satisfy the thickness feature from edge points. Once the detection of all thickness features is completed, invalid thickness features are filtered and correct thickness features are merged based on the contextual information. Finally, a thickness feature histogram (TFH) is calculated, and TFH is used for grading scrap steel. Our proposed method was integrated into a scrap steel grading system, which has been used in an actual production environment. Comprehensive experiments have been conducted to validate the proposed method. Moreover, a specialized scrap steel image dataset was created to train deep-learning-based methods in comparison experiments. Experimental results show that our method can extract thickness features and estimate the distribution of thickness of scrap steel effectively. The grading system has been successfully used in actual task scenarios and satisfies the industrial grading requirements. The scrap steel dataset is publicly available at
https://github.com/zichengzichengzi/Scrap
Steel Image Dataset.
