MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

An introduction to computer vision illumination and fixturing sensors image acquisition and representation fundamentals of digital image processing image analysis the segmentation problem 2-D shape description and recognition 3-D object representations robot programming and robot vision bin picking trends and aspirations.

Machine vision: automated visual inspection and robot vision

The developers of path planning algorithms and localization have significantly improved the usability of the robot those days. By using software such as a Gmapping, the robot will be able to create a map of the surrounding area. This research utilizes the 3D sensor Asus_xtion_ pro to create an indoor map using SLAM and create 3D models for surrounding objects with a Turtlebot robot. In the first case, we used the Turtlebot to generate an indoor map of the robotic lab room using the Gmapping ROS packet. In the second case, we used the robot to create 3D models for the surrounding objects in the room. We used the Raspberry Pi 3 as a replacement of the laptop that was used to control the Turtlebot. The same implementation of the first and second tasks have been repeated to compare the performance. The Raspberry Pi accomplishes the given tasks successfully; however, there is some delay due to the different on the CPU power. Finally, the low cost proposed solution is capable of running ROS based SLAM algorithm and using the point on cloud to create 3D models. In addition, the use of Raspberry Pi allows the robot save considerable amount of power in contrast with the use of a normal laptop.

An Asus_xtion_probased indoor MAPPING using a Raspberry Pi with Turtlebot robot Turtlebot robot

Over the past two decades, the use of low power Field Programmable Gate Arrays (FPGA) for the acceleration of various vision systems mainly on embedded devices have become widespread. The reconfigurable and parallel nature of the FPGA opens up new opportunities to speed-up computationally intensive vision and neural algorithms on embedded and portable devices. This paper presents a comprehensive review of embedded vision algorithms and applications over the past decade. The review will discuss vision based systems and approaches, and how they have been implemented on embedded devices. Topics covered include image acquisition, preprocessing, object detection and tracking, recognition as well as high-level classification. This is followed by an outline of the advantages and disadvantages of the various embedded implementations. Finally, an overview of the challenges in the field and future research trends are presented. This review is expected to serve as a tutorial and reference source for embedded computer vision systems.

/pdf/embedded-vision-systems-a-review-of-the-literature-7zzsy4qzoj.pdf

Embedded Vision Systems: A Review of the Literature

This paper presents the development of a car model that can detect edge, line, and corner of the road image and also the model can detect the red color of a traffic light image. The car model is equipped with a camera which is used for computer vision purpose. The image comes from a camera is read by using Raspberry Pi single-board computer. The algorithms for image processing methods are selected to detect edge, line, corner, and traffic light color of the road model. The algorithms are developed in Simulink diagram block and embedded into Raspberry Pi using Simulink Support Package for Raspberry Pi Hardware. The embedded algorithms for detecting line, edge, corner and red color of traffic light will be tested. The test will be conducted in real-time mode. Based on the test results, the embedded image processing algorithms can successfully detect line, edge, and corner of the road images, and detect the red color of traffic light image.

Real-Time Image Processing Method Using Raspberry Pi for a Car Model

We have designed a small robot called Cube for simple robotics tasks and students works. The Cube carries only small and lightweight computational platform Raspberry Pi equipped with a camera. This paper serves as an introduction to using image processing methods on a Raspberry Pi platform via Simulink in Matlab. We have designed a cheap framework for fast image processing in real-time including feature extraction and image transformation methods. In the paper a several selected methods frequently used not only in robotics are implemented and tested on the Raspberry Pi 2 equipped with a native camera board. Algorithms for edge, corner and line detection have been implemented by using Simulink with the Computer Vision System Toolbox and other in-build tools.

K. Horak and L. Zalud

Papers

Image Processing on Raspberry Pi for Mobile Robotics