Registered Color Images Research Articles

Color-guided optimization model with reliable self-structure priors for depth map restoration

Depth maps captured by Kinect or time of flight (ToF) cameras have an active role in many visual applications. However, a brutal truth is that these depth maps are often contaminated with compound noise, which includes intrinsic noise and missing pixels. In addition, depth maps captured with ToF-based cameras are low in resolution. As these depth maps carry rich and critical information about 3D space, high quality post-processing is crucial for supporting subsequent visual applications. Previous works were proposed via the guiding of the registered color image and bicubic interpolation as an initialization for the up-sampling task, where challenges arose from texture coping and blurry depth discontinuities. Motivated by these challenges, in this paper, we propose a new optimization model depending on the relative structures of both depth and color images for both depth map filtering and up-sampling tasks. In our general model, two self-structure priors for depth and color images are constructed individually and used for the two tasks. For overcoming the texture coping problem, the color-based and depth-based priors are used near the depth edges and at the homogeneous regions respectively. To this end, we further propose a confidence map at every task for managing where every prior is used. Experimental results on both simulated and real datasets for Kinect and ToF cameras demonstrate that the proposed method has a superior performance than benchmarks.

A Fusion Approach to Detect Traffic Signs Using Registered Color Images and Noisy Airborne LiDAR Data

Traffic sign detection is considered as one of the active research topics in transportation and computer vision. The previous works mainly focus on detecting traffic signs in images or in mobile light detection and ranging (LiDAR) data. In this paper, we propose a novel deep learning method to accurately detect traffic signs by fusing the complementary features from registered airborne geo-referenced color images and noisy airborne LiDAR data. Specifically, we first segment the airborne color images to road and non-road segments by integrating various local features in an inequality constraint quadratic optimization model. Next, we find the corresponding road regions in LiDAR data and extract high elevated objects above the road. We then segment the extracted objects to different regions corresponding to traffic sign candidates using Euclidean distance-based clustering. Finally, we find the corresponding traffic sign candidates in color images, extract their deep features, and represent them in a convex optimization model to classify the candidates. A set of extensive experiments have been carried out on the airborne geo-referenced color images and noisy airborne LiDAR data captured by Utah State University from I-15 highway. The results show the effectiveness of the proposed method in detecting traffic signs.

High-Throughput Phenotyping Analysis of Potted Soybean Plants Using Colorized Depth Images Based on A Proximal Platform

Canopy color and structure can strongly reflect plant functions. Color characteristics and plant height as well as canopy breadth are important aspects of the canopy phenotype of soybean plants. High-throughput phenotyping systems with imaging capabilities providing color and depth information can rapidly acquire data of soybean plants, making it possible to quantify and monitor soybean canopy development. The goal of this study was to develop a 3D imaging approach to quantitatively analyze soybean canopy development under natural light conditions. Thus, a Kinect sensor-based high-throughput phenotyping (HTP) platform was developed for soybean plant phenotyping. To calculate color traits accurately, the distortion phenomenon of color images was first registered in accordance with the principle of three primary colors and color constancy. Then, the registered color images were applied to depth images for the reconstruction of the colorized three-dimensional canopy structure. Furthermore, the 3D point cloud of soybean canopies was extracted from the background according to adjusted threshold, and each area of individual potted soybean plants in the depth images was segmented for the calculation of phenotypic traits. Finally, color indices, plant height and canopy breadth were assessed based on 3D point cloud of soybean canopies. The results showed that the maximum error of registration for the R, G, and B bands in the dataset was 1.26%, 1.09%, and 0.75%, respectively. Correlation analysis between the sensors and manual measurements yielded R2 values of 0.99, 0.89, and 0.89 for plant height, canopy breadth in the west-east (W–E) direction, and canopy breadth in the north-south (N–S) direction, and R2 values of 0.82, 0.79, and 0.80 for color indices h, s, and i, respectively. Given these results, the proposed approaches provide new opportunities for the identification of the quantitative traits that control canopy structure in genetic/genomic studies or for soybean yield prediction in breeding programs.

Real-time RGB-D image stitching using multiple Kinects for improved field of view

This article concerns the problems of a defective depth map and limited field of view of Kinect-style RGB-D sensors. An anisotropic diffusion based hole-filling method is proposed to recover invalid depth data in the depth map. The field of view of the Kinect-style RGB-D sensor is extended by stitching depth and color images from several RGB-D sensors. By aligning the depth map with the color image, the registration data calculated by registering color images can be used to stitch depth and color images into a depth and color panoramic image concurrently in real time. Experiments show that the proposed stitching method can generate a RGB-D panorama with no invalid depth data and little distortion in real time and can be extended to incorporate more RGB-D sensors to construct even a 360° field of view panoramic RGB-D image.

Quaternion Wiener Deconvolution for Noise Robust Color Image Registration

In this letter, we propose a global method for registering color images with respect to translation. Our approach is based on the idea of representing translations as convolutions with unknown shifted delta functions, and performing Wiener deconvolution in order to recover the shift between two images. We then derive a quaternionic version of the Wiener deconvolution filter in order to register color images. The use of Wiener filter also allows us to explicitly take into account the effect of noise. We prove that the well-known algorithm of phase correlation is a special case of our method, and we experimentally demonstrate the advantages of our approach by comparing it to other known generalizations of the phase correlation algorithm.

Analysis of Color Images using Cluster based Segmentation Techniques

segmentation divides an image into several constituent components such as color, structure, shape, and texture. It forms a major research topic for many image processing researchers as the applications are endless. Its applications include image enhancement, object detection, image retrieval, image compression, and medical image processing to name a few. The segmentation of color images is necessary for efficient pattern recognition and feature extraction involving various color spaces such as RGB, HSV and CIE L*A*B*, etc. This paper describes the different cluster based segmentation techniques used for segmenting the different color images and the resultant is analyzed with subjective and objective measures. Initially, registered color images are considered as input. Then the cluster based segmentation techniques namely K-Means clustering, Pillar-Kmeans clustering and Fuzzy C-means (FCM) clustering techniques are applied. Further, the segmented image is analyzed with measures such as compactness and execution time. From the experimental results, it has been observed that K-means and Pillar-Kmeans are the most suitable techniques for RGB, HSV and LAB color spaces than the FCM technique.

Free-form object segmentation and representation from registered range and color images

This paper describes a new technique to 3D surface segmentation and representation of free-form objects from registered range and color images. The proposed approach combines edge and region information to derive a surface description using algebraic implicit surfaces. This is done by propagating and blending Piecewise Hermite Interpolation Surfaces. The proposed technique, not only reduces the number of used patches, but also preserves surface-depth and orientation continuity. It can also be used to generate partial surface models for CAD-based vision and object recognition purposes. Realistic partial models are obtained by mapping texture extracted from a registered color image onto the generated surfaces. Experimental results show that the system can produce reliable surface segmentation as well as realistic 3D surface models of free-form objects.