Specular highlights detection and removal in images is a fundamental yet non-trivial problem of interest. Most modern techniques proposed are inadequate at dealing with real-world images taken under uncontrolled conditions with the presence of complex textures, multiple objects, and bright colours, resulting in reduced accuracy and false positives. To detect specular pixels in a wide variety of real-world images independent of the number, colour, or type of illuminating source, we propose an efficient Specular Segmentation (SpecSeg) network based on the U-net architecture that is expeditious to train on nominal-sized datasets. The proposed network can detect pixels strongly affected by specular highlights with a high degree of precision, as shown by comparison with the state-of-the-art methods. The technique proposed is trained on publicly available datasets and tested using a large selection of real-world images with highly encouraging results.
In the context of exponential demographic growth, the imbalance between human resources and public health problems impels us to envision other solutions to the difficulties faced in the diagnosis, prevention, and large-scale management of the most common diseases. Cardiovascular diseases represent the leading cause of morbidity and mortality worldwide. A large-scale screening program would make it possible to promptly identify patients with high cardiovascular risk in order to manage them adequately. Optical coherence tomography angiography (OCT-A), as a window into the state of the cardiovascular system, is a rapid, reliable, and reproducible imaging examination that enables the prompt identification of at-risk patients through the use of automated classification models. One challenge that limits the development of computer-aided diagnostic programs is the small number of open-source OCT-A acquisitions available. To facilitate the development of such models, we have assembled a set of images of the retinal microvascular system from 499 patients. It consists of 814 angiocubes as well as 2005 en face images. Angiocubes were captured with a swept-source OCT-A device of patients with varying overall cardiovascular risk. To the best of our knowledge, our dataset, Retinal oct-Angiography and cardiovascular STAtus (RASTA), is the only publicly available dataset comprising such a variety of images from healthy and at-risk patients. This dataset will enable the development of generalizable models for screening cardiovascular diseases from OCT-A retinal images.
This paper presents preliminary work to utilize a commercial time of flight depth camera for real-time 3D scene reconstruction of underwater objects. Typical RGB stereo camera imaging for 3D capturing suffers from blur and haziness due to turbidity of water in addition to critical dependence on light, either from natural or artificial sources. We propose a method for repurposing the low-cost Microsoft Kinect™ Time of Flight camera for underwater environment enabling dense depth data acquisition that can be processed in real time. Our motivation is the ease of use and low cost of the device for high quality real-time scene reconstruction as compared to multi view stereo cameras, albeit at a smaller range. Preliminary results of depth data acquisition and surface reconstruction in underwater environment are also presented. The novelty of our work is the utilization of the Kinect depth camera for real-time 3D mesh reconstruction and our main objective is to develop an economical and compact solution for underwater 3D mapping.
One of the major research directions in robotic vision focuses on calculating the real world size of objects in a scene using stereo imaging. This information can be used while decision making for robots, manipulator localization in the workspace, path planning and collision prevention, augmented reality, object classification in images and other areas that require object sizes as a feature. In this paper we present a novel approach to calculate real world object size using RGB-D image acquired from Microsoft Kinect™, as an alternative to stereo imaging based approaches. We introduce a dynamic resolution matrix that estimates the size of each pixel in an image in real world units. The main objective is to convert the size of objects represented in the image in pixels; to real world units (such as feet, inches etc.).We verify our results using available OpenSource RGB-D datasets. The experimental results show that our approach provides accurate measurements.
For everyday inspection jobs in offshore oil and gas industry, the human divers are being replaced by underwater vehicles. This paper proposes a visual feedback based control of an autonomous underwater vehicle for pipeline inspection. The hydrodynamic disturbances in water severely affect the movement of the vehicle resulting in performance degrading. The heading of the autonomous underwater vehicle under such disturbances is controlled using visual feedback to track the pipeline for inspection. The proposed method does not demand expensive position feedback devices such as underwater acoustic positioning system. By using built-in camera of the vehicle and few image processing techniques a simpler, easier and low-cost solution is proposed. The performance evaluation of the proposed technique on sample underwater images is also presented.